自动抓取ArXiv论文，使用 Google Gemini 评分筛选高质量内容
专为 计算机科学学者/程序员 设计
- 🆓 完全免费 - 使用 Google AI Studio 免费 API
- 🤖 自动运行 - GitHub Actions 每天自动运行
- 🎯 智能评分 - 四维度评估（0-100分）
- 💡 AI摘要 - 自动生成论文核心贡献摘要
- Fork 本仓库
- 配置 API Key - 添加
GOOGLE_AI_API_KEY到 GitHub Secrets（获取地址） - 启用 Actions - Actions → Daily Papers → Enable workflow
- 订阅通知 - Watch → All Activity
完成！系统每天 UTC 17:00（北京时间 1:00）自动运行。
📖 详细设置请查看 SETUP.md
查看所有历史精选论文：papers
| 标题 | 评分 | Gemini 摘要 | 评分理由 | 原始摘要 |
|---|---|---|---|---|
| Forecasting Downstream Performance of LLMs With Proxy Metrics | ⭐ 88/100 | 提出基于专家轨迹的LLM性能预测代理指标 | 方法创新且实用，显著提升模型开发效率与评估准确性 | 展开Progress in language model development is often driven by comparative decisions: which architecture to adopt, which pretraining corpus to use, or which training recipe to apply. Making these decisions well requires reliable performance forecasts, yet the two commonly used signals are fundamentally limited. Cross-entropy loss is poorly aligned with downstream capabilities, and direct downstream evaluation is expensive, sparse, and often uninformative at early training stages. Instead, we propose to construct proxy metrics by aggregating token-level statistics, such as entropy, top-k accuracy, and expert token rank, from a candidate model's next token distribution over expert-written solutions. Across three settings, our proxies consistently outperform loss- and compute-based baselines: 1) For cross-family model selection, they rank a heterogeneous population of reasoning models with mean Spearman Rho = 0.81 (vs. Rho = 0.36 for cross-entropy loss); 2) For pretraining data selection, they reliably rank 25 candidate corpora for a target model at roughly |
| What Does the AI Doctor Value? Auditing Pluralism in the Clinical Ethics of Language Models | ⭐ 84/100 | 提出评估大模型医疗伦理多元性的审计框架 | 方法创新且严谨，揭示了模型医疗决策的伦理偏差风险。 | 展开Medicine is inherently pluralistic. Principles such as autonomy, beneficence, nonmaleficence, and justice routinely conflict, and such ethical dilemmas often sharply divide reasonable physicians. Good clinical practice navigates these tensions in concert with each patient's values rather than imposing a single ethical stance. The ethical values that large language models bring to medical advice, however, have not been systematically examined. We present a framework for auditing value pluralism in medical AI, comprising a benchmark of clinician-verified dilemmas and an attribution method that recovers value priorities directly from decisions. The ecosystem of frontier models spans physician-level value heterogeneity, and models discuss competing values in their reasoning (Overton pluralism) before committing to a decision. However, individual model decisions are near-deterministic across repeated sampling and semantic variations, failing to reproduce the distributional pluralism of the physician panel. Across benchmark cases, these consistent decisions reflect committed, systematic value preferences. While most model priorities fall within the natural range of inter-physician variation, some significantly underweight patient autonomy. A single LLM deployed without regard for its value priorities could amplify those priorities at scale to every patient it serves. Without explicit efforts to balance ethical perspectives with one or multiple models, these tools risk replacing clinical pluralism with a deployment monoculture. |
| GIM: Evaluating models via tasks that integrate multiple cognitive domains | ⭐ 84/100 | 提出GIM基准，通过多认知域整合评估模型能力。 | 方法论严谨，通过IRT模型提升了基准评估的科学性。 | 展开As LLM benchmarks saturate, the evaluation community has pursued two strategies to increase difficulty: escalating knowledge demands (GPQA, HLE) or removing knowledge entirely in favor of abstract reasoning (ARC-AGI). The first conflates memorization with capability; the second divorces reasoning from the practical contexts in which it matters. We take a different approach. The Grounded Integration Measure (GIM) is a benchmark of 820 original problems (615 public, 205 private) where difficulty comes from integration; individual problems require coordinating multiple cognitive operations (constraint satisfaction, state tracking, epistemic vigilance, audience calibration) over broadly accessible knowledge, so that reasoning stays grounded in realistic tasks without being gated on specialized expertise. Each problem is an original expert-authored composition, majority with rubric-decomposed scoring (median 6 independently judged criteria). A balanced public--private split provides built-in contamination diagnostic. We calibrate a continuous response 2-parameter logistic (2PL) IRT model over >200k prompt-response pairs across 28 models, producing robust ability estimates that correctly order test-configurations even when raw accuracy is distorted by errors or missing data, addressing a common challenge in benchmark reporting. Using this framework, we present a comprehensive leaderboard spanning 22 models and 47 test-configurations (unique model, thinking-level pairs), and conduct what is to our knowledge the most extensive published study of how test-time compute trades off against model capability on a fixed benchmark: 11 models swept across 35 test-configurations. We observe that within-family configuration choices, such as thinking budget and quantization, matter as much as model selection. We release the evaluation framework, calibrated IRT parameters, and all public problems. |
| DashAttention: Differentiable and Adaptive Sparse Hierarchical Attention | ⭐ 82/100 | 提出可微自适应稀疏层级注意力机制 | 通过α-entmax实现端到端可微，提升长文本建模效率。 | 展开Current hierarchical attention methods, such as NSA and InfLLMv2, select the top-k relevant key-value (KV) blocks based on coarse attention scores and subsequently apply fine-grained softmax attention on the selected tokens. However, the top-k operation assumes the number of relevant tokens for any query is fixed and it precludes the gradient flow between the sparse and dense stages. In this work, we propose DashAttention (Differentiable and Adaptive Sparse Hierarchical Attention), which leverages the adaptively sparse |
| Predictable Confabulations: Factual Recall by LLMs Scales with Model Size and Topic Frequency | ⭐ 82/100 | 揭示LLM事实召回与模型规模及训练频率的缩放定律 | 通过实证分析量化了事实召回的缩放规律，方法严谨且具有高实用价值。 | 展开While scaling laws govern aggregate large language model performance, no scaling law has linked factual recall to both model size and training-data composition. We evaluated 38 models on over 8,900 scholarly references evaluated by an automated reference verification system. Recall quality follows a sigmoid in the log-linear combination of model parameter count and topic representation in training data. These two variables alone explain 60% of the variance across 16 dense models from four families, rising to 74-94% within individual families. The form matches a superposition-inspired account in which recall is gated by a signal-to-noise ratio: signal strength scales with concept frequency and the noise floor with model capacity. |
| 标题 | 评分 | Gemini 摘要 | 评分理由 | 原始摘要 |
|---|---|---|---|---|
| Presupposition and Reasoning in Conditionals: A Theory-Based Study of Humans and LLMs | ⭐ 82/100 | 对比人类与LLM在条件句预设推理上的差异 | 研究方法严谨，揭示了LLM在语用推理上的局限性 | 展开Presupposition projection in conditionals is central to theories of meaning and pragmatics, yet it remains largely unevaluated in large language models. We address this gap through a parallel behavioral study comparing human judgments and LLM predictions on a normed dataset of conditional sentences that controls the relation between the antecedent and the projected presupposition. We collect likelihood ratings from 120 participants and four LLMs under matched contextual conditions. Results show that humans integrate probabilistic and pragmatic cues in their judgment, whereas LLMs show variable alignment with human patterns. Using a linguistically motivated checklist within an LLM-as-a-Judge framework, we further evaluate model reasoning. We observe models that best match human ratings often lack coherent pragmatic reasoning, while models with stronger reasoning produce less human-like judgments. These findings suggest that LLMs' performance on such tasks may result from surface pattern matching rather than pragmatic competence. Our findings highlight the importance of benchmarks grounded in linguistic theory for comparing humans and models. |
| Readers make targeted regressions to plausible errors in reanalysis of "noisy-channel garden-path" sentences | ⭐ 78/100 | 揭示了读者如何通过眼动回归纠正语言理解中的噪声错误。 | 研究结合认知科学与语言模型，方法严谨，具有理论深度。 | 展开A key question in psycholinguistics is how inferences about the meaning of linguistic input unfold incrementally a comprehender's mind. In this work, we study reading dynamics for ``noisy-channel garden-path'' sentences, which temporarily appear well-formed but feature late-appearing violations of expectation that can be resolved not by inferring an alternative syntactic structure, but by inferring the presence of an error. We find evidence for targeted regressions -- eye movements towards regions that are promising loci of possible errors in light of later-arriving information, showing patterns consistent with the posterior inferences of a model of noisy-channel processing with reanalysis. We discuss the implications of these findings for theories of noisy-channel language comprehension and information-theoretic explanations of reading dynamics. |
| Ancient Greek to Modern Greek Machine Translation: A Novel Benchmark and Fine-Tuning Experiments on LLMs and NMT Models | ⭐ 78/100 | 构建古希腊语-现代希腊语平行语料库并优化翻译模型 | 数据集构建方法创新，实验详实，有效提升了低资源语言翻译性能。 | 展开Machine Translation (MT) for Ancient Greek (AG) to Modern Greek (MG) is a low-resource task, constrained by the lack of large-scale, high-quality parallel data. We address this gap by introducing the AG-MG Parallel Corpus, a new resource containing 132,481 sentence-aligned pairs derived from literary, historical, and biblical texts. We present a novel corpus creation pipeline that combines web-scraped, excerpt-level data with a multi-stage sentence-level alignment, and refinement process. Our method uses VecAlign with LaBSE embeddings, which we first fine-tune on a manually-aligned AG-MG subset, followed by an LLM-based error/misalignment correction phase using Gemini 2.5 Flash to ensure high alignment quality. Furthermore, we provide the first comprehensive benchmark of modern MT models on this task, evaluating three fine-tuning strategies across NMT models (NLLB, M2M100) and a Greek LLM (Llama-Krikri-8B). Our experiments show that fine-tuning yields significant improvements over base models, increasing performance by up to +10.3 BLEU points. Specifically, full-parameter fine-tuning of Llama-Krikri-8B achieves the highest overall performance with a BLEU score of 13.16, while the QLoRA-adapted M2M100-1.2B model demonstrates the largest relative gains and highly competitive results. Our dataset and models represent a significant contribution to Greek NLP. |
| GUT-IS: A Data-Driven Approach to Integrating Constructs and Their Relations in Information Systems | ⭐ 76/100 | 提出一种基于聚类与嵌入的IS领域构念整合方法。 | 方法创新且实用，通过语义纯度与简约性的权衡解决构念不一致问题。 | 展开Structural equation modeling is widely used in IS research. However, inconsistent construct definitions impede the cumulative development of knowledge. In this work, we present an approach that aims at the integration of structural equation models into a unified model: We use a combination of task-adapted text embeddings and clustering to produce a candidate set of construct groupings. Subsequently, we select the optimal solution using a loss function that explicitly trades off semantic purity and parsimony in the number of clusters. By making this trade-off explicit, our approach allows to analyze how construct groupings and their relations change as one shifts the priority from purity to parsimony. Empirically, we evaluate and explore the proposed methodology on two datasets from the IS domain. |
| 标题 | 评分 | Gemini 摘要 | 评分理由 | 原始摘要 |
|---|---|---|---|---|
| Vision-OPD: Learning to See Fine Details for Multimodal LLMs via On-Policy Self-Distillation | ⭐ 82/100 | 通过区域到全局自蒸馏提升多模态模型细粒度感知能力 | 提出无需外部工具的自蒸馏框架，有效提升视觉细节理解，方法创新且实验扎实。 | 展开Multimodal Large Language Models (MLLMs) still struggle with fine-grained visual understanding, where answers often depend on small but decisive evidence in the full image. We observe a regional-to-global perception gap: the same MLLM answers fine-grained questions more accurately when conditioned on evidence-centered crops than on the corresponding full images, suggesting that many failures stem from difficulty to focus on relevant evidence rather than insufficient local recognition ability. Motivated by this observation, we propose Vision-OPD (Vision On-Policy Distillation), a regional-to-global self-distillation framework that transfers the model's own privileged regional perception to its full-image policy. Vision-OPD instantiates two conditional policies from the same MLLM: a crop-conditioned teacher and a full-image-conditioned student. The student generates on-policy rollouts, and Vision-OPD minimizes token-level divergence between the teacher and student next-token distributions along these rollouts. This enables the model to internalize the benefit of visual zooming without external teacher models, ground-truth labels, reward verifiers, or inference-time tool use. Experiments on multiple fine-grained visual understanding benchmarks show that Vision-OPD models achieve competitive or superior performance against much larger open-source, closed-source, and "Thinking-with-Images" agentic models. |
| CrossView Suite: Harnessing Cross-view Spatial Intelligence of MLLMs with Dataset, Model and Benchmark | ⭐ 82/100 | 提出跨视角空间推理框架与数据集，提升MLLM空间智能。 | 系统性解决了跨视角推理的数据、基准与模型对齐难题。 | 展开Spatial intelligence requires multimodal large language models (MLLMs) to move beyond single-view perception and reason consistently about objects, visibility, geometry, and interactions across multiple viewpoints. However, progress in cross-view reasoning remains limited by three major gaps: the scarcity of large-scale well-annotated training data, the lack of comprehensive benchmarks for systematic evaluation, and the absence of explicit alignment mechanisms that establish object-level consistency across views. To address these gaps, we thoroughly develop CrossView Suite across three coordinated components: CrossViewSet, CrossViewBench, and CrossViewer. Firstly, we introduce a multi-agent data engine to meticulously curate a large-scale, high-quality cross-view instruction dataset, termed CrossViewSet, covering 17 fine-grained task types with 1.6M samples. Second, we meticulously create a scene-disjoint CrossViewBench to comprehensively assess the cross-view spatial understanding capability of an MLLM, evaluating it across various aspects. Finally, we propose CrossViewer, a progressive three-stage framework for cross-view spatial reasoning in MLLMs, following a Perception -> Alignment -> Reasoning paradigm. Our method equips an adaptive spatial region tokenizer to capture fine-grained object representations, and then aligns the multi-view objects explicitly, and thus fuses aligned features for boosting the cross-view inference capacity for MLLMs. Extensive experiments and analyses show that large-scale training data, systematic evaluation, and explicit cross-view alignment are all critical for advancing MLLMs from single-view perception toward real-world spatial intelligence. The project page is available at https://github.com/Thinkirin/Crossview-Suite. |
| Starve to Perceive: Taming Lazy Perception in VLMs with Constrained Visual Bandwidth | ⭐ 82/100 | 通过限制视觉带宽强制模型习得主动感知能力 | 方法创新且实用，有效解决了视觉语言模型的懒惰感知问题。 | 展开Vision-Language Models (VLMs) deployed as situated agents in high-resolution visual environments require active perception -- the ability to dynamically decide where to look through operations like zooming, cropping, and panning. However, current training paradigms produce models that mimic the surface form of such operations without functionally depending on their outputs, a phenomenon we term lazy perception. We trace this to a fundamental learning asymmetry: when coarse global views combined with language priors suffice for moderate accuracy, the model has no incentive to learn harder multi-step visual search. If a model can succeed without actively looking, it will never learn to look. This motivates Starve to Perceive, a training paradigm that constrains visual bandwidth -- restricting each observation to a tight token budget so that no single view suffices for task completion, making active perception the only viable strategy. Despite requiring no auxiliary losses, reward shaping, or architectural changes -- serving as a minimal, plug-in modification to standard post-training pipelines -- models trained under perceptual starvation achieve substantial gains of 5% average relative improvement across diverse benchmarks. |
| What is Holding Back Latent Visual Reasoning? | ⭐ 82/100 | 揭示视觉推理中潜在标记的局限性与改进路径 | 研究深入剖析了潜在视觉推理失效的原因，实验严谨且见解深刻。 | 展开Humans can approach complex visual problems by mentally simulating intermediate visual steps, rather than reasoning through language alone. Inspired by this, several works on Vision-Language Models have recently explored chain-of-thought reasoning with continuous latent tokens as intermediate visual imagination steps. In this work, we investigate how recent models leverage such latent tokens. Surprisingly, we find that model accuracy is unaffected when latent tokens are replaced by uninformative ``dummy'' tokens. This indicates that latent tokens play a minimal causal role in the model's final prediction. To better understand this phenomenon, we analyze both the training signal provided by oracle latent representations and the quality of the latent tokens generated at inference time. Our experiments reveal two crucial issues holding back latent visual reasoning: First, in most existing datasets, oracle latent tokens provide limited additional information beyond the original image and do not substantially simplify the task, leading models to ignore them during training and effectively bypassing them at inference time. When fine-tuned on a diagnostic dataset, in which latent tokens provide sufficient support for the final prediction, we show that models can causally rely on them. Second, the latent tokens produced at inference time deviate from their corresponding oracle representations, collapsing to a narrow region and preventing benefits even when the model relies on them. Overall, our findings suggest that future progress in latent visual reasoning depends on two key pillars: high-quality datasets with informative intermediate steps and more precise latent token prediction. |
| Geometry-Aware Uncertainty Coresets for Robust Visual In-Context Learning in Histopathology | ⭐ 82/100 | 提出GAUC方法优化病理学视觉上下文学习 | 提出几何感知核心集选择，显著提升VLM鲁棒性与准确度 | 展开Vision-language models (VLMs) can couple visual perception with open-ended clinical reasoning, making them attractive for computational histopathology. However, fine-tuning billions of parameters on scarce, expert-annotated pathology data is prohibitive, while in-context learning (ICL), which conditions the VLM on demonstrative image-text pairs without parameter updates, suffers from high sensitivity to which examples are selected and how the query is phrased, producing unreliable diagnostics. Existing selection strategies rely on query-dependent nearest-neighbour retrieval that ignores global data structure, require costly parameter updates, or disregard the joint vision-text embedding geometry of VLMs. We propose GAUC, a training-free coreset selection method operating directly in the pre-trained multimodal embedding space. GAUC jointly optimises three objectives: (1) a Maximum Mean Discrepancy term enforcing distributional fidelity between coreset and full dataset, (2) an Effective Mutual Information Difference regulariser bounding performance degradation under prompt paraphrases by exploiting the VLM's joint vision-text alignment, and (3) a predictive-variance penalty suppressing overconfident, unstable outputs. On CRC-100K and MHIST across multiple open-source VLM architectures, GAUC consistently improves accuracy, calibration, and prompt robustness over recent ICL selection methods and dataset-distillation baselines, all without a single gradient update. |
| 标题 | 评分 | Gemini 摘要 | 评分理由 | 原始摘要 |
|---|---|---|---|---|
| SURGE: Approximation-free Training Free Particle Filter for Diffusion Surrogate | ⭐ 82/100 | 提出无梯度扩散模型采样算法URGE | 通过Girsanov定理实现无梯度采样，理论严谨且性能优越。 | 展开Diffusion-based generative models increasingly rely on inference-time guidance, adding a drift term or reweighting mixture of experts, to improve sample quality on task-specific objectives. However, most existing techniques require repeated score or gradient evaluations, introducing bias, high computational overhead, or both. We introduce \texttt{URGE}, Unbiased Resampling via Girsanov Estimation, a derivative-free inference-time scaling algorithm that performs path-wise importance reweighting via a Girsanov change of measure. Instead of computing gradient-based particle weights in previous work, \texttt{URGE} attaches a simple multiplicative weight to each simulated trajectory and periodically resamples. No score, no Hessian, and no PDE evaluation is required. We establish an equivalence between path-wise and particle-wise SMC: the Girsanov path weight admits a backward conditional expectation that recovers the previous particle-level weights, guaranteeing that both schemes produce the same unbiased terminal law. Empirically, \texttt{URGE} outperforms existing inference-time guidance baselines on synthetic tests and diffusion-model benchmarks, achieving better generation quality, while being significantly simpler to implement and fully gradient-free. |
| Spectral Progressive Diffusion for Efficient Image and Video Generation | ⭐ 82/100 | 提出频域渐进扩散加速图像视频生成 | 通过频域分析实现高效生成，方法创新且实用性强。 | 展开Diffusion models have been shown to implicitly generate visual content autoregressively in the frequency domain, where low-frequency components are generated earlier in the denoising process while high-frequency details emerge only in later timesteps. This structure offers a natural opportunity for efficient generation, as high-resolution computation on noise-dominated frequencies is largely redundant. We propose Spectral Progressive Diffusion, a general framework that progressively grows resolution along the denoising trajectory of pretrained diffusion models. To this end, we develop a spectral noise expansion mechanism and derive an optimal resolution schedule from the model's power spectrum. Our framework supports training-free acceleration and a novel fine-tuning recipe that further improves efficiency and quality. We demonstrate significant speedups on state-of-the-art pretrained image and video generation models while preserving visual quality. |
| SafeDiffusion-R1: Online Reward Steering for Safe Diffusion Post-Training | ⭐ 82/100 | 提出在线强化学习框架实现扩散模型安全对齐 | 通过CLIP嵌入引导实现高效安全对齐，性能提升显著 | 展开Diffusion models have been widely studied for removing unsafe content learned during pre-training. Existing methods require expensive supervised data, either unsafe-text paired with safe-image groundtruth or negative/positive image pairs, making them impractical to scale. Furthermore, offline reinforcement learning and supervised fine-tuning approaches that generate synthetic data offline suffer from catastrophic forgetting, degrading generation quality. We propose a novel online reinforcement learning framework that addresses both data scarcity and model degradation through post-training with Group Relative Policy Optimization (GRPO) on both negative and positive text prompts. To eliminate the need for fine-tuning specialized safe/unsafe reward models, we introduce a \textit{steering reward mechanism} that exploits an inherent property of CLIP embeddings: steering text representations toward positive safety directions and away from negative ones in the embedding space. Our online-policy approach enables the model to learn from diverse prompts, including explicit unsafe content, without catastrophic forgetting. Extensive experiments demonstrate that our method reduces inappropriate content to 18.07% (vs. 48.9% for SD v1.4) and nudity detections to 15 (vs. 646 baseline) while improving compositional generation quality from 42.08% to 47.83% on GenEval. Remarkably, these safety gains generalize to out-of-domain unsafe prompts across seven harm categories, achieving state-of-the-art performance without supervised paired data or reward tuning. Github: https://github.com/MAXNORM8650/SafeDiffusion-R1. |
| Continuous Diffusion Scales Competitively with Discrete Diffusion for Language | ⭐ 82/100 | 提出RePlaid实现连续扩散模型高效扩展 | 通过架构对齐证明连续扩散模型具备强竞争力 | 展开While diffusion has drawn considerable recent attention from the language modeling community, continuous diffusion has appeared less scalable than discrete approaches. To challenge this belief we revisit Plaid, a likelihood-based continuous diffusion language model (DLM), and construct RePlaid by aligning the architecture of Plaid with modern discrete DLMs. In this unified setting, we establish the first scaling law for continuous DLMs that rivals discrete DLMs: RePlaid exhibits a compute gap of only |
| 标题 | 评分 | Gemini 摘要 | 评分理由 | 原始摘要 |
|---|---|---|---|---|
| Seeing Together:Multi-Robot Cooperative Egocentric Spatial Reasoning with Multimodal Large Language Models | ⭐ 84/100 | 提出多机器人协作空间推理框架SP-CoR及基准数据集。 | 创新性强，数据集规模大，实验验证充分，方法论严谨。 | 展开Multimodal Large Language Models (MLLMs) have made substantial progress in egocentric video understanding, but their ability to reason cooperatively from multiple embodied viewpoints remains largely unexplored. We study this problem through multi-robot cooperative dynamic spatial reasoning, where a model must answer spatial, temporal, visibility, and coordination questions by integrating synchronized egocentric videos from a team of moving robots. To support this setting, we introduce CoopSR, the first benchmark for this task, together with EgoTeam, a multi-robot egocentric QA dataset. EgoTeam contains 114,227 QA pairs spanning 19 question types, four difficulty tiers, and three team sizes in Habitat and iGibson, along with a real-world test set of around 2,326 QAs collected using two quadruped robots. We further propose SP-CoR (Spectral and Physics-Informed Cooperative Reasoner), an MLLM framework for fine-grained cooperative spatial reasoning. SP-CoR combines dynamics-aware multi-robot frame sampling, spectral- and physics-guided view fusion, and physics-aligned prompt distillation, enabling the model to benefit from privileged robot-pose supervision during training while requiring only egocentric videos at test time. Across 22 MLLM baselines, SP-CoR consistently improves cooperative reasoning, outperforming the strongest fine-tuned baseline by +3.87% on Habitat and +7.12% on iGibson. It also shows stronger generalization to unseen team sizes and real-world robot tests. Code can be found at https://github.com/KPeng9510/seeing-together.git. |
| EgoExoMem: Cross-View Memory Reasoning over Synchronized Egocentric and Exocentric Videos | ⭐ 82/100 | 提出首个跨视角视频记忆推理基准EgoExoMem | 创新性引入双视角推理框架，实验严谨且具有挑战性 | 展开Egocentric memory is widely used in embodied intelligence, but it may be insufficient for comprehensive spatial-temporal reasoning. Inspired by human recall from both field and observer perspectives, we introduce EgoExoMem, the first benchmark for cross-view memory reasoning over synchronized egocentric and exocentric videos. EgoExoMem contains |
| Semantic Generative Tuning for Unified Multimodal Models | ⭐ 82/100 | 提出SGT范式，以分割任务对齐多模态理解与生成。 | 通过生成式代理任务弥合理解与生成鸿沟，方法创新且实验扎实。 | 展开Unified multimodal models (UMMs) strive to consolidate visual understanding and visual generation within a single architecture. However, prevailing training paradigms independently optimize understanding via sparse text signals and generation through dense pixel objectives. Such a decoupled strategy yields misaligned representation spaces, isolating visual understanding from generation and hindering their mutual reinforcement. This work presents the first systematic investigation into generative post-training, where we formulate hierarchical visual tasks as generative proxies to bridge the isolation in UMMs. Our empirical investigation reveals that high-level semantic tasks, particularly image segmentation, serve as optimal proxies. Unlike low-level tasks that distract models with texture details, segmentation provides structural semantics that significantly enhance both vision-centric perception and generative layout fidelity. Building upon these insights, we introduce Semantic Generative Tuning (SGT), a novel paradigm that leverages segmentation as a generative proxy to align and synergize multimodal capabilities. Mechanistic analyses further demonstrate that SGT fundamentally improves feature linear separability and optimizes visual-textual attention allocation pattern. Extensive evaluations show that SGT consistently improves both multimodal comprehension and generative fidelity across mainstream benchmarks. Our code is available on the https://song2yu.github.io/SGT/. |
| OmniPro: A Comprehensive Benchmark for Omni-Proactive Streaming Video Understanding | ⭐ 82/100 | 提出首个全模态主动流式视频理解基准OmniPro | 填补了主动流式评估空白，方法严谨且具有高实用价值。 | 展开Omni-proactive streaming video understanding, i.e., autonomously deciding when to speak and what to say from continuous audio-visual streams, is an emerging capability of omni-modal large language models. Existing benchmarks fall short in three key aspects: they rely primarily on visual signals, adopt polling or fixed-timestamp protocols instead of true proactive evaluation, and cover only a limited range of tasks, preventing reliable assessment and differentiation of omni-proactive streaming models. We present OmniPro, the first benchmark to jointly evaluate omni-modal perception, proactive responding, and diverse video understanding tasks. It comprises 2,700 human-verified samples spanning 9 sub-tasks and 3 cognitive levels, covering 6 basic video understanding capabilities. Notably, 84% of samples require audio signals (speech or non-speech), and each sample is annotated with modality-isolation labels to enable fine-grained multimodal analysis. We further introduce a dual-mode evaluation protocol: Probe mode assesses content understanding by querying the model before and after each ground-truth trigger, while Online mode evaluates full proactive ability by requiring models to autonomously decide when to respond in streaming input. Evaluating 11 representative models reveals three key findings: (1) audio provides consistent gains but with highly variable utilization across models, (2) performance degrades significantly over time, indicating limited long-horizon robustness, and (3) non-speech audio perception remains the weakest dimension. |
| WavFlow: Audio Generation in Waveform Space | ⭐ 78/100 | 提出WavFlow直接生成原始波形音频 | 绕过压缩直接建模波形，方法创新且实验扎实。 | 展开Modern audio generation predominantly relies on latent-space compression, introducing additional complexity and potential information loss. In this work, we challenge this paradigm with WavFlow, a framework that generates high-fidelity audio directly in raw waveform space without intermediate representations. To overcome the inherent difficulties of modeling high-dimensional and low-energy signals, we reshape audio into 2D token grids through waveform patchify and introduce amplitude lifting to align signal scales, enabling stable optimization via direct x-prediction in flow matching. To capture complex semantic alignment and temporal synchronization, we leverage an automated data pipeline to curate 5 million high-quality video-text-audio triplets, allowing the model to learn fine-grained acoustic patterns from scratch. Experimental results show that WavFlow achieves competitive performance on the video-to-audio benchmark VGGSound (FD_PaSST: 59.98, IS_PANNs: 17.40, DeSync: 0.44) and the text-to-audio benchmark AudioCaps (FD_PANNs: 10.63, IS_PANNs: 12.62), matching or exceeding the performance of established latent-based methods. Our work demonstrates that intermediate compression is not a prerequisite for high-quality synthesis, offering a simpler and more scalable alternative for multimodal audio generation. |
| 标题 | 评分 | Gemini 摘要 | 评分理由 | 原始摘要 |
|---|---|---|---|---|
| Vision Foundation Models as Generalist Tokenizers for Image Generation | ⭐ 88/100 | 提出VFMTok通用视觉分词器，提升生成效率与质量。 | 创新性利用冻结VFM实现高效分词，实验结果优异，方法论严谨。 | 展开In this work, we explore the largely unexplored direction of building a generalist image tokenizer directly on top of a frozen vision foundation model (VFM). To build this tokenizer, we utilize a frozen VFM as the encoder and introduce two key innovations: (1) a region-adaptive quantization framework to eliminate spatial redundancy in standard 2D grid features, and (2) a semantic reconstruction objective that aligns the decoded outputs with the VFM's representations to preserve semantic fidelity. Grounded in these designs, we propose VFMTok, a generalist visual tokenizer capable of operating seamlessly in both discrete and continuous latent spaces. VFMTok achieves substantial improvements in synthesis quality while drastically enhancing token efficiency. For discrete autoregressive (AR) generation, it accelerates model convergence by \textbf{3 times} and achieves a state-of-the-art gFID of \textbf{1.36} on ImageNet class-conditional synthesis. Similarly, for continuous-space generation, integrating VFMTok with a denoising model yields an exceptional gFID of \textbf{1.25}. Furthermore, because the latent space inherently captures rich spatial semantics, VFMTok enables high-fidelity class-conditional synthesis without classifier-free guidance (\textbf{w/o CFG}) across both generative paradigms, significantly accelerating inference speed. Beyond these remarkable empirical results, we systematically investigate the underlying mechanisms of our approach. We discover that the specific self-supervised learning objectives utilized during VFM pre-training dictate its effectiveness as a tokenizer. Specifically, a VFM jointly optimized with global contrastive learning and latent masked image modeling provides the optimal representations for image tokenization. These insights establish a strong foundation and offer valuable guidance for the design of future image tokenizers. |
| Improved Baselines with Representation Autoencoders | ⭐ 82/100 | 提出RAEv2，通过多层特征融合与重参数化提升扩散模型效率。 | 方法创新显著，实验详实，大幅提升了训练效率与生成质量。 | 展开Representation Autoencoders (RAE) replace traditional VAE with pretrained vision encoders. In this paper, we systematically investigate several design choices and find three insights which simplify and improve RAE. First, we study a generalized formulation where the representation is defined as sum of the last k encoder layers rather than solely the final layer. This simple change greatly improves reconstruction without encoder finetuning or specialized data (e.g., text, faces). Second, we study the prevalent assumption that RAE (using pretrained representation as encoder) replaces representation alignment (REPA), which distills the same representation to intermediate layers instead. Through large-scale empirical analysis, we uncover a surprising finding: RAE and REPA exhibit complementary working mechanisms, allowing the same representation to be used as both encoder and target for intermediate diffusion layers. Finally, the original RAE struggles with classifier-free guidance (CFG) and requires training a second, weaker diffusion model for AutoGuidance (AG). We show that REPA itself can be viewed as x-prediction in RAE latent space. By simply re-parameterizing the output of the DiT model, it can provide guidance for "free". Overall, RAEv2 leads to more than 10x faster convergence over the original RAE, achieving a state-of-the-art gFID of 1.06 in just 80 epochs on ImageNet-256. On FDr^k, RAEv2 achieves a state-of-the-art 2.17 at just 80 epochs compared to the previous best 3.26 (800 epochs) without any post-training. This motivates EP_FID@k (epochs to reach unguided gFID <= k) as a measure of training efficiency. RAEv2 attains an EP_FID@2 of 35 epochs, versus 177 for the original RAE. We also validate our approach across diverse settings for text-to-image generation and navigation world models, showing consistent improvements. Code is available at https://raev2.github.io. |
| 标题 | 评分 | Gemini 摘要 | 评分理由 | 原始摘要 |
|---|---|---|---|---|
| Incantation: Natural Language as the Action Interface for Multi-Entity Video World Models | ⭐ 88/100 | 提出自然语言驱动的多实体交互视频世界模型。 | 创新性引入语言接口实现精细化控制，实验扎实且性能优异。 | 展开Modern interactive video world models have achieved impressive visual fidelity, yet lack fine-grained multi-entity control and cross-entity, cross-world generalization. We trace this gap to the action interface: standard control protocols (e.g. animation IDs, device inputs, scene-level captions) bind action semantics to specific entities or engines at design time. We propose natural language as the interface to unlock expressiveness that no prior interface can achieve, and we present Incantation, the first interactive video world model with per-latent-frame (0.25 s) natural-language conditioning that supports simultaneous multi-entity control and concept-level cross-entity transfer beyond any fixed rendering pipeline. We pair a pretrained bidirectional video backbone with frame-local text cross-attention, and enable real-time long-horizon streaming through ODE-initialized Self-Forcing distillation with a RoPE-decoupled sliding KV-cache. We surpass the Action-Index baseline on cross-entity transfer (89% vs. 43%) and out-of-vocabulary prompts (90% vs. 0%), and our 2-step student sustains 19.7 FPS at 480p with stable FVD over 2-hour rollouts. We further apply the same architecture and training recipe to The King of Fighters, changing only the per-entity action vocabulary slots. We have released a preview subset of the Incantation dataset at https://huggingface.co/datasets/zhush/incantation-elden-ring-scenes, containing manually collected Elden Ring player-boss combat clips with structured action-oriented metadata. Larger-scale Elden Ring and KOF data will be released with the full project. |
| Aurora: Unified Video Editing with a Tool-Using Agent | ⭐ 82/100 | 提出Aurora智能体框架实现视频编辑自动化 | 通过VLM智能体解决视频编辑中的输入模糊问题，创新性强。 | 展开Recent video editing models have converged on a unified conditioning design: a single diffusion transformer jointly consumes text, source video, and reference images, and one set of weights covers replacement, removal, style transfer, and reference-driven insertion. The design is flexible, but it assumes that the user already provides model-ready text, reference images, and spatial grounding for local edits, which real requests often omit. We present Aurora, an agentic video editing framework that pairs a tool-augmented vision-language model (VLM) agent with a unified video diffusion transformer. The VLM agent maps a raw user request to a structured edit plan aligned with the transformer's conditioning channels, thereby resolving textual and visual underspecification before generation. We train the VLM agent with supervised data for complete edit planning and reference-image selection, together with preference pairs for robust tool use and instruction refinement. We introduce AgentEdit-Bench to evaluate agent-enhanced video editing under textual and visual underspecification. Experiments on AgentEdit-Bench and two existing video editing benchmarks show that Aurora improves over instruction-only baselines and that the VLM agent transfers to compatible frozen video editing models. Project page: https://yeates.github.io/Aurora-Page |
| LongLive-2.0: An NVFP4 Parallel Infrastructure for Long Video Generation | ⭐ 82/100 | 基于NVFP4的长视频生成并行训练与推理架构 | 提出NVFP4并行架构显著提升长视频生成效率，实验扎实。 | 展开We present LongLive-2.0, an NVFP4-based parallel infrastructure throughout the full training and inference workflow of long video generation, addressing speed and memory bottlenecks. For training, we introduce sequence-parallel autoregressive (AR) training, instantiated as Balanced SP, which co-designs the efficient teacher-forcing layout with SP execution by pairing clean-history and noisy-target temporal chunks on each rank, enabling a natural teacher-forcing mask with SP-aware chunked VAE encoding. Combined with NVFP4 precision, it reduces GPU memory cost and accelerates GEMM computation during training, the proportion of which increases as video length grows. Moreover, we show that a high-quality infrastructure and dataset enable a remarkably clean training pipeline. Unlike existing Self-Forcing series methods that rely on ODE initialization and subsequent distribution matching distillation (DMD), LongLive-2.0 directly tunes a diffusion model into a long, multi-shot, interactive auto-regressive (AR) diffusion model. It can be further converted to real-time generation (4 to 2 denoising steps) with standalone LoRA weights. For inference on Blackwell GPUs, we enable W4A4 NVFP4 inference, quantize KV cache into NVFP4 for memory savings, and boost end-to-end throughput with asynchronous streaming VAE decoding. On non-Blackwell GPU architectures, we deploy SP inference to match the speed on Blackwell GPUs, while the quantized KV cache can lower inter-GPU communication of SP. Experiments show up to 2.15x speedup in training, and 1.84x in inference. LongLive-2.0-5B achieves 45.7 FPS inference while attaining strong performance on benchmarks. To our knowledge, LongLive-2.0 is the first NVFP4 training and inference system for long video generation. |
| Advancing Narrative Long Video Generation via Training-Free Identity-Aware Memory | ⭐ 82/100 | 提出IAMFlow框架实现长视频身份一致性生成 | 创新性引入显式身份追踪，实验严谨且性能优越。 | 展开Autoregressive video generation has improved rapidly in visual fidelity and interactivity, but it still suffers from long-term inconsistency and memory degradation. Most existing solutions either compress historical frames using predefined strategies or retrieve keyframes based on coarse implicit attention signals, both of which fail to handle evolving prompts with shifting entity references, leading to identity drift, character duplication, and attribute loss. To address this, we propose IAMFlow, a training-free identity-aware memory framework that explicitly models and tracks persistent entity identities, enabling consistent generation across prompt transitions. Specifically, an LLM extracts entities with visual attributes from each prompt and assigns unique global IDs for identity-aware memory, while a VLM asynchronously verifies and refines attributes from rendered frames, enabling explicit entity tracking in place of implicit similarity-based matching. To keep the proposed framework computationally practical, we design a systematic inference acceleration pipeline, including asynchronous visual verification, adaptive prompt transition, and model quantization, which achieves faster generation than existing baselines. Furthermore, we introduce NarraStream-Bench, a benchmark for narrative streaming video generation that features 324 multi-prompt scripts spanning six dimensions and a three-dimensional evaluation protocol that integrates both traditional metrics and multimodal large language model-based assessments. Extensive experiments show that IAMFlow, despite being training-free, achieves the best overall performance on NarraStream-Bench, outperforming the strongest baseline by 2.56 points, while achieving a 1.39$\times$ speedup over the most efficient baseline in the 60-second multi-prompt setting. |
| InstructAV2AV: Instruction-Guided Audio-Video Joint Editing | ⭐ 82/100 | 首个指令引导的音视频联合编辑框架 | 提出了创新的音视频协同编辑方法，数据集与实验扎实。 | 展开Recent diffusion-based methods have achieved impressive progress in video content manipulation. However, they typically ignore the accompanying audio, leaving the audio disjointed from the edited results. In this paper, we propose InstructAV2AV, the first end-to-end framework for instruction-guided audio-video joint editing. We first develop a scalable data synthesis pipeline and construct InsAVE-80K, the first large-scale audio-video editing dataset with high-quality source-to-target pairs. With this data foundation, we adapt an audio-video generation backbone to leverage its robust priors. We concatenate the audio-video input with noisy latent codes to anchor the source context, propose the source-instruction gated attention to improve instruction following and content preservation, and introduce a two-stage training strategy to effectively transfer these pre-trained priors. Extensive experiments demonstrate that InstructAV2AV outperforms state-of-the-art methods across 11 metrics spanning three aspects on two evaluation sets, highlighting its potential for controllable content creation. Project page: https://hjzheng.net/projects/InstructAV2AV/. |
| 标题 | 评分 | Gemini 摘要 | 评分理由 | 原始摘要 |
|---|---|---|---|---|
| Overeager Coding Agents: Measuring Out-of-Scope Actions on Benign Tasks | ⭐ 88/100 | 提出评估AI智能体越权行为的基准框架 | 研究揭示了智能体越权风险，方法严谨且具有重要安全价值。 | 展开Coding agents now run autonomously with shell, file, and network privileges. When a user issues a benign request, the agent sometimes does more than asked: it deletes unrelated files, wipes a stale credentials backup, or rewrites configuration the user never mentioned. We call these scope expansions overeager actions, an authorization problem distinct from capability failures, prompt injection, or sandbox escapes. We present OverEager-Gen, a benchmark dedicated to overeager behavior on benign tasks. Building it surfaces a measurement-validity issue: if a benchmark spells out the authorized scope inside the prompt, the agent stops inferring boundaries and starts pattern-matching declaration text. On Claude Code, stripping the consent declaration alone raises the overeager rate from 0.0% to 17.1% on paired scenarios (McNemar exact p = 2.4 x 10^-4). OverEager-Gen therefore certifies each scenario's discriminative power before admission via a behavioral-gradient validator, audits internal tool calls through a dual-channel stack (PATH-injected shim plus per-agent event streams), and ships byte-identical consent_kept and consent_stripped variants. OverEager-Bench contains 500 validated scenarios and ~7,500 runs across four agent products (Claude Code, OpenHands, Codex CLI, Gemini CLI) and six base models; a 50-sample re-annotation gives Cohen's kappa = 0.73 and rule-judge recall = 1.00. Stripping consent multiplies the overeager rate on every shared base model (Delta in [11.9, 17.2] pp). The framework axis dominates effect size: a permissive cluster (Claude Code, Codex CLI, Gemini CLI) runs at 5.4-27.7% while the ask-to-continue framework (OpenHands) sits at 0.2-4.5% (Fisher p <= 10^-5). Within-framework base-model variance reaches 15.9 pp, indicating that model-layer alignment does not fully propagate through permissive permission gating. |
| Qumus: Realization of An Embodied AI Quantum Material Experimentalist | ⭐ 88/100 | 首个实现量子材料自主制备的具身智能实验系统 | 将具身智能与物理实验结合，实现了材料制备的自动化突破 | 展开While modern Large Language Models (LLMs) and agentic artificial intelligence (AI) have demonstrated transformative capabilities in digital domains, the realization of embodied AI capable of real-world scientific discovery remains a difficult frontier. The advancements are hindered by the inherent complexity of integrating high-level reasoning, multimodal information processing and real-time physical execution. Here we introduce Qumus, the first AI quantum materials experimentalist. Physically embodied within a robotic mini-laboratory, Qumus is an intelligent, multimodal, and multi-agent system designed for the creation and nano-processing of atomically thin two-dimensional (2D) materials and stacked van der Waals (vdW) structures. Qumus autonomously navigates the full scientific cycle, from hypothesis generation and protocol planning to multi-step experimental execution, result analysis and reporting, acting as an experimentalist. Markedly, the system has achieved, for the first time, the AI-creation of graphene, as well as the first AI-fabrication of complex nanodevices including atomically thin field-effect transistors via vdW stacking. Qumus excels at these tasks by demonstrating autonomous error correction and closed-loop experimentation. Our results establish a generalizable framework for self-improving embodied AI systems that learn directly from the quantum world, opening a pathway toward accelerated discovery in quantum materials, electronics and beyond. |
| Same Signal, Different Semantics: A Cross-Framework Behavioral Analysis of Software Engineering Agents | ⭐ 88/100 | 揭示软件工程智能体行为信号的框架依赖性与语义差异 | 大规模实证研究揭示了框架对智能体行为的决定性影响，方法严谨且结论具有重要启示意义。 | 展开Behavioral studies of LLM-based software engineering agents extract operational rules about which trajectory shapes correlate with higher resolution rates: that a test step follows a code modification, that error cascades are short, or that trajectories are compact. Each rule is typically derived from a single framework, and whether it transfers, in sign as well as magnitude, to structurally different agent designs has not been directly tested. We address this at ecosystem scale: 64,380 SWE-bench runs from 126 agent configurations spanning 43 frameworks, where each configuration pairs an LLM with a framework (e.g., SWE-Agent, OpenHands) that supplies its tools and workflow. We separate framework effects from LLM effects by holding each layer fixed in turn, then measure one behavior-outcome effect per configuration and examine how those effects agree or disagree. Swapping the framework while the LLM is held fixed produces large behavioral differences in every action feature. On most signals, configurations disagree not merely in magnitude but in direction. Error rate is the cleanest case: 47 configurations resolve more issues when their error rate is lower, while 48 resolve more when it is higher. Five other continuous features and three of seven binary patterns from prior SE literature show similar directional disagreement. Framework identity accounts for more of this variation than LLM family: for mean turns, framework explains 64% of the between-configuration variance against the LLM's 10%. The implication is that the same observable behavioral signal can carry opposite meaning for different agent configurations. Behavioral findings from any single framework therefore warrant cross-configuration validation before being claimed as general. |
| Code as Agent Harness | ⭐ 82/100 | 提出以代码作为智能体基础设施的统一框架 | 系统梳理了代码在智能体系统中的核心作用，视角新颖且实用性强。 | 展开Recent large language models (LLMs) have demonstrated strong capabilities in understanding and generating code, from competitive programming to repository-level software engineering. In emerging agentic systems, code is no longer only a target output. It increasingly serves as an operational substrate for agent reasoning, acting, environment modeling, and execution-based verification. We frame this shift through the lens of agent harnesses and introduce code as agent harness: a unified view that centers code as the basis for agent infrastructure. To systematically study this perspective, we organize the survey around three connected layers. First, we study the harness interface, where code connects agents to reasoning, action, and environment modeling. Second, we examine harness mechanisms: planning, memory, and tool use for long-horizon execution, together with feedback-driven control and optimization that make harness reliable and adaptive. Third, we discuss scaling the harness from single-agent systems to multi-agent settings, where shared code artifacts support multi-agent coordination, review, and verification. Across these layers, we summarize representative methods and practical applications of code as agent harness, spanning coding assistants, GUI/OS automation, embodied agents, scientific discovery, personalization and recommendation, DevOps, and enterprise workflows. We further outline open challenges for harness engineering, including evaluation beyond final task success, verification under incomplete feedback, regression-free harness improvement, consistent shared state across multiple agents, human oversight for safety-critical actions, and extensions to multimodal environments. By centering code as the harness of agentic AI, this survey provides a unified roadmap toward executable, verifiable, and stateful AI agent systems. |
| ESI-Bench: Towards Embodied Spatial Intelligence that Closes the Perception-Action Loop | ⭐ 82/100 | 提出ESI-Bench基准以评估具身智能体的主动感知与决策能力。 | 通过主动感知闭环评估具身智能，方法严谨且具有重要研究价值。 | 展开Spatial intelligence unfolds through a perception-action loop: agents act to acquire observations, and reason about how observations vary as a function of action. Rather than passively processing what is seen, they actively uncover what is unseen - occluded structure, dynamics, containment, and functionality that cannot be resolved from passive sensing alone. We move beyond prior formulations of spatial intelligence that assume oracle observations by recasting the observer as an actor. We introduce ESI-BENCH, a comprehensive benchmark for embodied spatial intelligence spanning 10 task categories and 29 subcategories built on OmniGibson, grounded in Spelke's core knowledge systems. Agents must decide what abilities to deploy - perception, locomotion, and manipulation - and how to sequence them to actively accumulate task-relevant evidence. We conduct extensive experiments on state-of-the-art MLLMs and find that active exploration substantially outperforms passive counterparts, with agents spontaneously discovering emergent spatial strategies without explicit instructions, while random multi-view often adds noise rather than signal despite consuming far more images. Most failures stem not from weak perception but from action blindness: poor action choices lead to poor observations, which in turn drive cascading errors. While explicit 3D grounding stabilizes reasoning on depth-sensitive tasks, imperfect 3D representation proves more harmful than 2D baselines by distorting spatial relations. Human studies further reveal that unlike humans who seek falsifying viewpoints and revise beliefs under contradiction, models commit prematurely with high confidence regardless of evidence quality, exposing a metacognitive gap that neither better perception nor more embodied interaction alone can close. |
| 标题 | 评分 | Gemini 摘要 | 评分理由 | 原始摘要 |
|---|---|---|---|---|
| A Readiness-Driven Runtime for Pipeline-Parallel Training under Runtime Variability | ⭐ 82/100 | 提出RRFP运行时以解决流水线并行中的负载不均 | 通过动态调度解决流水线气泡问题，性能提升显著，实验扎实。 | 展开Pipeline parallelism is a key technique for scaling large-model training, but modern workloads exhibit runtime variability in computation and communication. Existing pipeline systems typically consume static, profiled, or adaptively generated schedules as pre-committed execution orders. When realized task readiness diverges from the pre-committed order, stages may wait for not-yet-ready work even though other executable work is available, creating stage misalignment, idle bubbles, and reduced utilization. We present Runtime-Readiness-First Pipeline (RRFP), a readiness-driven runtime for pipeline-parallel training. RRFP changes how schedules are consumed at runtime: instead of treating a schedule as a sequence that stages must wait to follow, it treats the schedule as a non-binding hint order for ranking currently ready work. To support this model, RRFP combines message-driven asynchronous communication, lightweight tensor-parallel coordination for collective consistency, and ready-set arbitration for low-overhead dispatch. We implement RRFP in a Megatron-based training framework and evaluate it on language-only and multimodal workloads at up to 128 GPUs. RRFP improves over fixed-order pipeline baselines across all settings. Using the BFW hint, RRFP achieves up to 1.77$\times$ speedup on language-only workloads and up to 2.77$\times$ on multimodal workloads. In cross-framework comparisons, RRFP with the default BF hint outperforms the faster available external system by up to 1.84$\times$ while preserving training correctness. |
| Ranking Opinions with Few States in Population Protocols | ⭐ 82/100 | 提出CIRCLES协议解决多数派问题 | 显著降低了状态复杂度，理论贡献扎实且逻辑严密。 | 展开Population protocols are a model of distributed computing where |
| PopPy: Opportunistically Exploiting Parallelism in Python Compound AI Applications | ⭐ 82/100 | PopPy通过自动并行化提升复合AI应用性能 | 系统创新性解决Python并行化难题，实验效果显著。 | 展开Compound AI applications, which compose calls to ML models using a general-purpose programming language like Python, are widely used for a variety of user-facing tasks, from software engineering to enterprise automation, making their end-to-end latency a critical bottleneck. In contrast to traditional applications, execution time is dominated by the external components, which cannot be handled by traditional language optimization systems, like optimizing compilers. To address this problem, we develop PopPy, a system that can uncover parallelization opportunities in Python applications that invoke these heavy external components, including those used in compound AI applications. PopPy supports a very expressive fragment of Python and requires minimal developer input to uncover parallelism. It combines an ahead-of-time compiler with a runtime, addressing three key challenges in extracting parallelism from Python applications: language complexity, dynamic dispatch, and variable mutation. On a set of real-world compound AI applications, PopPy achieves up to |
| EPIC: Abstraction and Polymorphism of In-Network Collectives on Ethernet | ⭐ 82/100 | 提出以太网内计算协议EPIC | 架构创新且验证严谨，有效解决以太网计算兼容性 | 展开In-Network Collective (INC) acceleration holds immense potential for optimizing AI training and inference; however, its cross-layer nature has historically hindered investment and adoption within the open Ethernet ecosystem. To bridge this gap, we propose EPIC (Ethernet Polymorphic In-network Collective), an INC protocol specification and reference system built on the principle of "Unified Abstraction, Polymorphic Realization." EPIC introduces an abstraction compatible with standard Ethernet that aligns functional boundaries with participant roles, while offering polymorphic realizations tailored to varying hardware capabilities. We address three fundamental challenges: first, we employ a modular design that enables an evolutionary path from simple to complex implementations, allowing vendors to iterate their hardware incrementally; second, we apply formal verification methodologies to prove the correctness of all proposed polymorphic modes; and third, we develop a unified resource management model versatile enough for diverse INC scenarios. Extensive validation -- spanning model checking, packet/flow simulations, VM emulation, Tofino Testbed, and FPGA/RTL verification -- confirms EPIC's correctness, performance gain, and feasibility. |
| Efficient Gradient Methods for Distributed Saddle Problems | ⭐ 82/100 | 提出分布式鞍点问题最优通信算法 | 理论严谨且通信复杂度达到最优，具有显著学术贡献。 | 展开The distributed setting for Saddle Problems (SPs) has recently emerged as a framework for various modern applications in machine learning and multiagent systems. Despite its relevance, the theoretical foundations of this setting have not yet been thoroughly established. In this paper, we advance this research direction by formalizing the distributed setup for SPs and providing rigorous definitions of communication and computational costs. Our main result is a novel decoupled method that achieves optimal communication cost within the zero-respecting framework. Our method is based on a multi-stage reduction to the decoupled minimization of residual norms, which yields strict improvements over the best known communication cost for the class and the long-standing oracle cost of the Extragradient method. Further, we show by a matching lower bound that our method is communication-optimal within the family of gradient-span algorithms. Finally, we study the extension of distributed SP into Variational Inequality Problem (VIP), which generalizes two-player zero-sum games to multiplayer general-sum games. We show that our decoupled method achieves a new state-of-the-art communication complexity for this broader class. |
| 标题 | 评分 | Gemini 摘要 | 评分理由 | 原始摘要 |
|---|---|---|---|---|
| Will It Go Viral? Grounding Micro-Video Popularity Prediction on the Open Web | ⭐ 82/100 | 引入外部网络上下文预测短视频热度 | 提出新颖的开放网络接地方法，实验严谨且实用性强。 | 展开Micro-video popularity prediction (MVPP) forecasts the popularity a newly uploaded short-form video will attract within a fixed number of days after upload. This task supports downstream applications in recommendation, advertising, and creator analytics, yet the problem is hard since virality depends on external trends rather than video content alone. Prior MVPP methods incorporate context by retrieving similar videos from platform-internal corpora, however historical neighbors cannot reveal whether a topic is currently trending, controversial, or already saturated across the open web. To this end, we reformulate MVPP as open-web grounded prediction and introduce WEBSHORTS, the first micro-video dataset that couples 14K videos with real-time open-web context collected at upload time, alongside daily view counts tracked over 7 days. The context for each video is organized as a structured evidence-card that captures the external attention landscape along three complementary web-context dimensions. We further propose SHORTS-CAST, a framework that generates dimension-wise rationales from the evidence-card to guide popularity regression, then adapts at deployment by selectively updating the context-to-popularity mapping when delayed labels reveal genuine trend shifts. In our experiments, SHORTS-CAST consistently outperforms content-only, video corpus retrieval-augmented, and online adaptation baselines under both offline and delayed-label online protocols, confirming that structured web context and trend-aware adaptation are jointly necessary for popularity forecasting under realistic deployment constraints in fast-evolving short-form video ecosystems. |
| Improving BM25 Code Retrieval Under Fixed Generic Tokenization: Adaptive q-Log Odds as a Drop-In BM25 Fix | ⭐ 82/100 | 提出q-log odds改进BM25代码检索 | 方法创新且提升显著，实验严谨，实用性强 | 展开In retrieval-augmented coding, failures often begin when the relevant file is absent from the retrieved context. Under frozen generic tokenization, where a BM25 index has been built by a search system whose analyzer the practitioner does not control, this failure is routine: BM25's logarithmic RSJ-odds IDF under-separates the identifier tail that distinguishes one function from another. We replace the outer logarithm of the Robertson-Spärck-Jones odds with a q-logarithm. At q=1 the transform recovers BM25 exactly by L'Hôpital's rule, and for q<1 it is a Box-Cox transform of the RSJ odds with lambda = 1-q. On CoIR CodeSearchNet Go (182K documents), oracle-tuned NDCG@10 rises from 0.2575 to 0.4874 (absolute +0.2299; +89.3% relative; zero sign reversals in 10,000 paired-bootstrap resamples, reported as p <= 10^-4). The effect is graded across code languages and is near-zero on BEIR text. A one-parameter closed form estimates a corpus-level q from hapax density and stays near q=1 on corpora where BM25 is already optimal. The index-time cost is a single pass over the sparse score matrix and query latency is unchanged. A tokenizer ablation shows that identifier-aware tokenization largely removes the incremental gain from q-IDF. |
| Infini-News: Efficiently Queryable Access to 1.3 Billion Processed Common Crawl News Articles | ⭐ 82/100 | 构建大规模新闻语料检索工具 | 提供了高效的CC-News索引与处理工具，极大降低了研究门槛。 | 展开Large-scale news corpora support a wide range of research in Computational Social Science and NLP, yet access remains constrained: commercial archives impose prohibitive costs and licensing restrictions, while open alternatives like Common Crawl's CC-News require terabyte-scale storage and computationally intensive processing. We present Infini-News, a retrieval toolkit and index for the entire CC-News archive from August 2016 to the latest available snapshot. Our contributions are threefold. First, we extract, clean the text, and parse the structured metadata of over 1.35B articles. Second, we enrich the corpus with language detection using three frontier language classifiers (GlotLID, lingua, and CommonLingua), and with multi-source geographic attribution that resolves a country of origin for 83.4% of articles across 222 countries. Third, we construct Infini-gram indexes: suffix-array structures that let researchers search the full archive for arbitrary text patterns in sub-second time. Together, these resources lower the barrier to longitudinal, cross-national media research. |
| Traditional statistical representations outperform generative AI in identifying expert peer reviewers | ⭐ 78/100 | 统计方法在专家识别中优于大模型 | 通过实证对比揭示了传统检索在细分领域优于生成式AI | 展开The exponential growth of scientific submissions has strained the peer review system. Despite the rapidly expanding global pool of researchers, this unprecedented scale has rendered the previous approach of manual expert identification unfeasible. Therefore, institutions have naturally turned to Large Language Models (LLMs) to automate intricate processes like expert reviewer identification. However, the reliability of these new models in accurately identifying domain experts lacks rigorous evaluation. We conduct a comprehensive empirical evaluation of statistical and AI-driven expertise identification methodologies to benchmark their reliability and limitations. Framing expert identification as an information retrieval problem, we utilize the distributed peer review system of a major international astronomical observatory, where proposal authorship serves as our proxy ground truth for domain expertise. Evaluating six retrieval methodologies utilized across observatories and computer science conferences, we demonstrate that traditional statistical representations outperform generative AI. Specifically, Term Frequency-Inverse Document Frequency successfully identified a labeled expert within the top 25 recommendations 79.5% of the time, compared to 51.5% for GPT-4o mini. Our results highlight that distinguishing subfield expertise requires fine-grained vocabulary, which is obscured by the semantic smoothing in generative methods. By establishing a rigorous evaluation framework for automated peer review, we demonstrate that transparent and reproducible statistical representations still outperform computationally expensive LLMs in specialized scientific tasks. |
| Query-Conditioned Knowledge Alignment for Reliable Cross-System Medical Reasoning | ⭐ 78/100 | 提出查询条件化实体对齐框架，提升跨系统医疗推理可靠性。 | 方法创新且实验扎实，有效解决了医疗知识图谱的非对称对齐难题。 | 展开Cross-domain knowledge alignment is essential for integrating heterogeneous medical systems, yet existing approaches typically treat entity alignment as a static matching problem, ignoring query context and cross-system asymmetry. This limitation is particularly critical in integrative medical settings, where correspondence between concepts is inherently context-dependent, non-bijective, and direction-sensitive. In this paper, we propose Query-Conditioned Entity Alignment (QCEA), which reformulates entity alignment as a query-conditioned correspondence problem. Instead of learning a fixed mapping between entity representations, QCEA treats the textual description of a source entity as a query and ranks candidate entities in the target graph, enabling context-dependent alignment. The framework integrates semantic encoding, graph-based representation learning, and a direction-aware transformation module to capture asymmetric and many-to-many correspondence across heterogeneous knowledge systems. We evaluate QCEA on TCM--WM knowledge graphs derived from SymMap, covering both symptom alignment and herb--molecule alignment tasks. Experimental results show consistent improvements over representative baselines, particularly on rank-sensitive metrics such as Hit@K and MRR. Furthermore, downstream retrieval-augmented generation (RAG) experiments demonstrate that improved alignment leads to better evidence retrieval, stronger grounding, and higher answer accuracy. These findings highlight that alignment is not merely a data integration step, but a key factor that shapes knowledge accessibility and reliability in cross-system medical reasoning. |
| 标题 | 评分 | Gemini 摘要 | 评分理由 | 原始摘要 |
|---|---|---|---|---|
| Can These Views Be One Scene? Evaluating Multiview 3D Consistency when 3D Foundation Models Hallucinate | ⭐ 82/100 | 提出评估多视角3D一致性的鲁棒性基准 | 通过几何验证改进了现有度量指标的可靠性 | 展开Multiview 3D evaluation assumes that the images being scored are observations of one static 3D scene. This assumption can fail in NVS and sparse-view reconstruction: inputs or generated outputs may contain artifacts, outlier frames, repeated views, or noise, yet still receive high 3D consistency scores. Existing reference-based metrics require ground truth, while ground-truth-free metrics such as MEt3R depend on learned reconstruction backbones whose failure modes are poorly characterized. We study this reliability problem by comparing neural reconstruction priors with classical geometric verification. We introduce \benchmark, a controlled robustness benchmark for multiview 3D consistency, and a parametric family that decomposes neural metrics into backbone, residual, and aggregation components. This family recovers MEt3R and yields variants up to |
| PIXLRelight: Controllable Relighting via Intrinsic Conditioning | ⭐ 82/100 | 提出一种基于内在条件控制的实时单图重光照方法 | 结合物理渲染与神经渲染，实现了高效且高质量的重光照。 | 展开We present PIXLRelight, a feed-forward approach for physically controllable single-image relighting. Existing methods either provide limited lighting control (e.g. through text or environment maps), accumulate errors when chaining inverse and forward rendering, or require costly per-image optimization. Our key idea is to bridge physically based rendering (PBR) and learned image synthesis through a shared intrinsic conditioning that can be obtained from either real photographs or PBR renders. At training time, paired multi-illumination photographs are decomposed into albedo, diffuse shading, and non-diffuse residuals, which condition the model. At inference time, the same conditioning is computed from a path-traced render of a coarse 3D reconstruction of the input under user-specified PBR lights. A transformer-based neural renderer then applies the target illumination to the source photograph, preserving fine image detail through a per-pixel affine modulation. PIXLRelight enables arbitrary PBR-style lighting control, achieves state-of-the-art relighting quality, and runs in under a tenth of a second per image. Code and models are available at https://mlfarinha.github.io/pixl-relight/. |
| CMAG: Concept-Scaffolded Retrieval for Marketplace Avatar Generation | ⭐ 82/100 | 提出CMAG框架实现语义驱动的3D虚拟形象生成。 | 方法创新且流程严谨，有效解决了多模态检索的兼容性问题。 | 展开Metaverse platforms rely on creator-driven marketplaces where avatars are assembled from discrete, taxonomy-labeled 3D assets (e.g., tops, bottoms, shoes, accessories) under strict category and topology constraints. While users increasingly expect free-form text control, text-only retrieval is brittle: natural language is ambiguous with respect to platform taxonomies, metadata is often noisy or informal, and independently retrieved components can be stylistically inconsistent or geometrically incompatible. We propose \textbf{CMAG}, a concept-scaffolded retrieval and verified composition framework for marketplace avatar generation. Given a prompt, CMAG first synthesizes an intermediate 3D concept scaffold that disambiguates intent beyond text by providing global spatial and stylistic context. In parallel, a view-aware part discovery module extracts localized visual evidence via prompt decomposition and text-grounded segmentation. A prompt-conditioned taxonomy router enforces category coverage and resolves semantic-to-taxonomic mismatch, after which a hybrid category-wise retriever combines part-based fusion with a concept-residual fallback using feature suppression. Finally, an agentic vision--language model filters and re-ranks candidates across categories and drives an iterative verification loop to assemble prompt-faithful, topologically consistent avatars from catalog assets. We evaluate CMAG on diverse compositional prompts and demonstrate improved retrieval robustness and compositional correctness compared to strong baselines, highlighting the importance of 3D concept scaffolding under prompt ambiguity. |
| StableHand: Quality-Aware Flow Matching for World-Space Dual-Hand Motion Estimation from Egocentric Video | ⭐ 82/100 | 提出质量感知流匹配模型，提升自我中心双手的运动估计精度。 | 通过质量评估优化流匹配，在遮挡场景下效果显著，方法创新且实验扎实。 | 展开Recovering world space 4D motion of two interacting hands from egocentric video is a fundamental capability for supervising robot policy learning, where wrist trajectories track the end-effector and finger articulations specify the grasp pose. Two major challenges arise in this setting: hands frequently leave the camera view for extended periods due to head motion, and persistent hand-object interactions cause severe occlusions of one or both hands. Existing methods uniformly condition on noisy hand motion observations without accounting for their per-frame reliability, leading to substantial performance degradation. Our key insight is that accurate world space hand motion estimation is tightly coupled with the quality of per-frame hand observations. To this end, we decompose the quality of hand motion observations extracted from an off-the-shelf hand pose estimator into four channels: wrist global translation and finger articulations for both hands. We propose StableHand, a quality-aware flow-matching framework conditioned on these four-channel quality signals, which are predicted by a learned quality network. We naturally incorporate the quality signals into the flow-matching process through a per-channel forward schedule, a quality-adjusted velocity target, AdaLN modulation of the DiT denoiser, and a quality-aware ODE initialization. This unified generative process preserves high-quality observations while reconstructing unreliable ones using a learned bimanual motion prior. Experiments on HOT3D and ARCTIC, two egocentric benchmarks featuring long missing-hand spans and persistent hand-object occlusions, show that StableHand achieves state-of-the-art performance across all reported metrics, reducing W-MPJPE by 20-25% compared to the strongest baseline, with the largest gains on heavily occluded ARCTIC sequences. |
| LESSViT: Robust Hyperspectral Representation Learning under Spectral Configuration Shift | ⭐ 82/100 | 提出LESSViT实现跨传感器高光谱鲁棒表征学习 | 通过低秩分解优化注意力机制，有效解决了跨光谱配置泛化难题。 | 展开Modeling hyperspectral imagery (HSI) across different sensors presents a fundamental challenge due to variations in wavelength coverage, band sampling, and channel dimensionality. As a result, models trained under a fixed spectral configuration often fail to generalize to other sensors. Existing Vision Transformer (ViT) approaches either rely on implicit spectral modeling with fixed channel assumptions or adopt explicit spatial-spectral attention with prohibitive computational cost, leading to a fundamental trade-off between efficiency and expressiveness. In this work, we introduce Low-rank Efficient Spatial-Spectral ViT (LESSViT), a sensor-flexible architecture for cross-spectral generalization. LESSViT is built on LESS Attention, a structured low-rank factorization that models joint spatial-spectral interactions through separable spatial and spectral components, reducing the complexity of full spatial-spectral attention from |
| 标题 | 评分 | Gemini 摘要 | 评分理由 | 原始摘要 |
|---|---|---|---|---|
| Learning Normal Representations for Blood Biomarkers | ⭐ 88/100 | 提出NORMA模型优化血液生物标志物个性化解读 | 大规模数据验证了方法有效性，兼具创新与临床应用价值 | 展开Blood-based biomarkers underpin clinical diagnosis and management, yet their interpretation relies largely on fixed population reference intervals that ignore stable, intra-patient variability. As such, population-based interpretation can mask meaningful deviation from an individual's baseline, risking delayed disease detection. To remedy this, there have been increasing efforts to personalize blood biomarker interpretation using individual testing histories. However, these methods may overfit to sparse data, inflating false-positive rates and unnecessary follow-up, and can also unwittingly include unrecognized or subclinical disease. Here, we leverage nearly 2 billion longitudinal laboratory measurements from over 1.6 million individuals across North America, the Middle East, and East Asia, to show that while laboratory values are highly individual, purely personalized intervals routinely overfit, classifying up to 68% of measurements as abnormal, without corresponding associations with adverse clinical outcomes. We then introduce NORMA, a conditional transformer-based framework that generates reference intervals by conditioning on both a patient's history and population-level data about "normal" variation. NORMA-derived intervals achieve higher precision for predicting outcomes, including mortality, acute kidney injury, and chronic disease. These findings caution against over-personalization in laboratory medicine and demonstrate that anchoring individual trajectories to population-level priors outperforms either approach alone. To promote transparency, we publicly release the model, code, and an interactive user interface for accessible, individualized laboratory interpretation. |
| Pocket Foundation Models: Distilling TFMs into CPU-Ready Gradient-Boosted Trees | ⭐ 88/100 | 通过蒸馏将大模型转化为高效树模型 | 方法创新且实用，实验规模大，论证严谨。 | 展开A fraud scorer needs to answer in under 2 ms. The best tabular foundation models (TFMs) take 151-1,275 ms on GPU. We close this gap by distilling the TFM offline into an XGBoost or CatBoost student that runs natively on CPU. The central obstacle is specific to in-context learning (ICL) teachers: they leak labels when scoring their own training set, so the soft targets collapse to near-one-hot vectors with no inter-class structure left to distill. Stratified out-of-fold (OOF) teacher labeling prevents this. Across 153 classification datasets drawn from TALENT, OpenML-CC18, TabZilla, and TabArena, distilling TabICLv2 into XGBoost gives 0.882 macro-mean AUC (96.5% of teacher AUC) at 1.9 ms on CPU, a 38x to 860x speedup across teacher-student pairs with a statistically significant edge over a tuned CatBoost baseline (Wilcoxon p = 0.0008; 51% win rate). Four further findings: teacher rank transfers exactly to student rank; gains concentrate on low-dimensional data (< 21 features: +0.011 over CatBoost vs. >21 features: +0.001); multi-teacher averaging helps MLP students (+0.006, p = 0.003) but adds less than 0.001 for tree students; and on high-dimensional tasks where the teacher itself trails CatBoost, distillation makes things worse rather than better. The full pipeline is open-sourced as part of the TabTune library. |
| Generating Physically Consistent Molecules with Energy-Based Models | ⭐ 88/100 | 提出EBMol模型实现物理一致分子生成 | 创新性引入能量模型并结合流匹配，性能达到SOTA。 | 展开Molecules in equilibrium follow a Boltzmann distribution, making the underlying energy landscape a physically grounded modeling objective. However, such landscapes are difficult to learn from data and, once learned, hard to sample from. Diffusion and flow-matching models sidestep these difficulties by learning a time-conditional score or transport field between noise and data, losing the energy inductive bias in exchange for a more tractable training objective. We introduce EBMol, an energy-based model (EBM) that restores this inductive bias by learning an atom-additive scalar potential without explicit simulation during training. Our method employs a flow-inspired Restoring Field Matching objective to approximate the energy landscape. We adopt the Mirror-Langevin algorithm for sampling, enabling unified updates of atomic positions and types, and incorporate parallel tempering for inference-time compute scaling. EBMol is the first EBM for 3D molecular generation to achieve state-of-the-art performance on QM9 and GEOM-Drugs. Moreover, we show that the learned energy landscape serves as a principled quality metric for ranking and filtering configurations, and demonstrate controllable generation without retraining through shape-steered sampling via potential composition and zero-shot linker design. |
| Learned Memory Attenuation in Sage-Husa Kalman Filters for Robust UAV State Estimation | ⭐ 82/100 | 提出NDR-SHKF提升无人机状态估计鲁棒性 | 结合递归网络与自适应滤波，方法创新且实验扎实。 | 展开Unmanned Aerial Vehicles in dynamic environments face telemetry outages, structural vibrations, and regime-dependent noise that invalidate the stationary covariance assumptions of classical Kalman filters. The Sage-Husa Kalman Filter (SHKF) estimates noise statistics online, but its reliance on a static, scalar forgetting factor forces a strict compromise between steady-state stability and transient responsiveness. We introduce the N-Deep Recurrent Sage-Husa Filter (NDR-SHKF), which replaces this scalar parameter with a vector-valued memory attenuation policy learned by a hierarchical recurrent network operating on whitened innovation sequences. A bifurcated architecture routes shallow recurrent states to capture instantaneous sensor anomalies and deep states to encode sustained dynamic trends, while an auxiliary reconstruction objective prevents feature collapse. The complete filter, including recursive covariance updates, is trained end-to-end via backpropagation through time to directly minimize state estimation error. Evaluations on topologically distinct chaotic attractors demonstrate cross-domain generalization, outperforming purely data-driven baselines that diverge under out-of-distribution dynamics. Furthermore, evaluations on recorded real-world UAV flight datasets validate the framework's practical viability, demonstrating its capacity to bridge transitions into proprioceptive dead reckoning and outperform classical adaptive estimators during sensor outages. |
| Distilling Tabular Foundation Models for Structured Health Data | ⭐ 82/100 | 提出抗泄露蒸馏法，提升医疗表格模型推理效率。 | 方法创新且实验详实，有效解决了医疗场景部署难题。 | 展开Tabular foundation models (TFMs) achieve strong performance on health datasets, but their inference cost and infrastructure requirements limit practical use. We study whether their predictive behavior can be transferred to lightweight tabular models through knowledge distillation. Since in-context TFMs condition on the training set at inference time, naive distillation can introduce context leakage; we address this with stratified out-of-fold teacher labeling. Across |