Trending AI papers today

1. 226votes

   WeVisOne-VL: Unified Visual Perception from Objects to Pixels

   Tianming Liang, Junyi Pan, Yuxi Li and 5 more · Tencent

   Existing vision-language models (VLMs) remain unreliable for fine-grained visual perception. In this report, we present WeVisOne-VL (WeChat Vision All-in-One), a powerful VLM that unifies object-level and pixel-level perception through structured next-token prediction. It supports multiple visual tasks including object detection, referring localization, counting, OCR, segmentation, and matting, enabling localization at any user-specific granularity, from points and boxes to masks and alpha mattes. Architecturally, we integrate a lightweight pixel decoder into the VLM via a special <OBJ> token to generate instance-level pixel outputs. We train the model with a three-stage curriculum SFT followed by mixed-task RL. Across over 30 benchmarks, WeVisOne-VL demonstrates leading performance on both object-level and pixel-level tasks, while maintaining robust rejection for object-absent queries. By releasing WeVisOne-VL to the open-source community, we hope to advance VLMs from broad visual understanding toward truly reliable perception systems for real-world deployment.

   arXiv 2610.31329 ↗ (opens in a new tab)PDF ↗ (opens in a new tab)Code (78 stars) ↗ (opens in a new tab)Repository on GitHub Trending Today ↗ (opens in a new tab)

2. 165votes

   Making MLLM Latents Matter: Factor-Aware Predictive Learning for Cinematic Video Generation

   Songlin Yang, Zhe Wang, Xiaotong Zhao and 8 more · Tencent

   Cinematic video generation requires both temporal inference from limited inputs (i.e., sparse rather than frame-by-frame guidance) and factor-aware control of character, scene, action, and camera. Multimodal large language models (MLLMs) offer useful priors for both capabilities, but their representations are not automatically actionable for video generation: a Video Diffusion Transformer (DiT) may bypass them through native conditioning pathways, and using them does not ensure either factor-aware control or generation-compatible temporal prediction. We propose Factor-Aware Predictive Learning (FAPL), which establishes effective MLLM latent use as a shared prerequisite and then targets the two capabilities with complementary learning signals. First, latent-only generator grounding trains the DiT with a frozen MLLM and connector, strengthening the DiT's use of MLLM latents for generation. Second, for factor-aware control, paired videos specify a target-factor change and non-target preservation, and factor-span replacement trains the DiT to realize this relationship in its output. Third, for temporal inference, text-only and text-plus-complete-video observations share a video target, and the trained DiT is then frozen while the MLLM and connector are optimized through it. This final stage trains limited-input representations for generation while retaining complete-observation reconstruction as a complementary training mode. Extensive experiments demonstrate our consistently better performance on three cinematic video generation tasks (i.e., sparse-to-video, factor-aware editing, and multi-shot generation) over baselines and validate FAPL's contributions to MLLM feature use, temporal control, and factor coordination.

   arXiv 2610.30926 ↗ (opens in a new tab)PDF ↗ (opens in a new tab)Code (1 stars) ↗ (opens in a new tab)Repository on GitHub Trending Today ↗ (opens in a new tab)

3. 152votes

   Deep Search in Real-World Web Environments

   Xiaomin Yu, Hongliang Chen, Zhe Huang and 22 more

   Despite substantial progress in Deep Search agents, their ability to conduct end-to-end research in real-world open Web environments remains insufficiently evaluated. Unlike static retrieval settings, information on the real-world Web is distributed across diverse sources, modalities, and heterogeneous formats, often involving complex interaction mechanisms that require agents to autonomously search for, access, and integrate relevant evidence during execution. To address this gap, we introduce the OpenDS task, designed to evaluate agents' ability to perform multi-step deep search in the live, open Web. This task requires agents to autonomously explore the real Web, discover and connect relevant evidence from multiple independent sources through Web search, browser interaction, and evidence processing, and ultimately determine a unique factual answer. Building on this task formulation, we construct OpenDS-World, a benchmark comprising 200 challenging tasks spanning diverse information modalities, heterogeneous file formats, and interactive access requirements, with independent human verification to ensure evidence validity and answer uniqueness. We evaluate 12 frontier models under a unified tool environment and execution protocol. The best-performing model achieves 39.0% accuracy, while human evaluation across 1,000 independent attempts yields 21.1% accuracy. Further analyses of tool usage, search cost, termination behavior, and failure recovery reveal substantial differences in research strategies across models, as well as persistent challenges in tool coordination and long-horizon search management. OpenDS-World provides a unified evaluation platform for systematically assessing and advancing agents' autonomous deep search capabilities in real-world open Web environments.

   arXiv 2610.30181 ↗ (opens in a new tab)PDF ↗ (opens in a new tab)Code (23 stars) ↗ (opens in a new tab)Repository on GitHub Trending Today ↗ (opens in a new tab)

4. 74votes

   Editing Images into Reusable Layers via Compositional Edit-Prior Distillation

   Wen Xue, Yong Liu, Xueheng Li and 5 more · jingdong

   High-quality image editing requires precise modification of target regions while preserving the content of unrelated regions. Existing editing models produce flattened outputs that limit precise local manipulation and layer reuse, while decomposition methods typically optimize layer recovery separately from instruction-driven editing. To this end, we introduce LayerEditor, a unified framework that couples instruction-guided image editing with controllable generation of reusable RGBA layers. At its core, In-Context RGB-Alpha Token Modeling jointly represents the edited canvas and an ordered sequence of RGB-Alpha layers within a single token sequence, enabling semantic edits and explicit control over individual layer content. To retain the pretrained model's editing capability during adaptation to layered outputs, we propose Compositional Edit-Prior Distillation, which transfers its editing prior to both the edited canvas and the image composed from the predicted layers. To support training and evaluation, we construct LayerEditor-100K, a large-scale paired image-editing dataset with ordered RGBA layer annotations, and introduce dedicated benchmarks for layered editing. Extensive experiments demonstrate that LayerEditor maintains strong editing fidelity while generating accurate RGBA layers, supporting both flexible layer-level manipulation and multi-layer decomposition.

   arXiv 2610.24738 ↗ (opens in a new tab)PDF ↗ (opens in a new tab)

5. 56votes

   IQuest-Q1: Advancing Foundation Capabilities for Agentic CLI Systems

   A. Jian Yang, An Huang, Bo Dan and 174 more · IQuest

   We present IQuest-Q1, a sparse Mixture-of-Experts (MoE) agentic foundation model with 320B total parameters (15B activated). IQuest-Q1 is developed through a three-stage process: (1) stable and efficient pre-training, combining Stable SplitNorm, Muon, and muP with a two-stage curriculum whose second stage increases the coding-data mixture, preserving a wide stability margin between safe and optimal learning rates; (2) fine-grained mid-training, expanding the data mixture across domains and formats and progressively extending the context; and (3) multi-scaffold with multi-version post-training, combining SFT, domain-specialized RL, and MOPD across various scaffolds to integrate complementary training signals and strengthen agentic coding capabilities. Furthermore, model merging combines different experts and checkpoints from different stages while mitigating conflicts among their parameter updates. The resulting IQuest-Q1 demonstrates capabilities in both coding and general tasks. We release IQuest-Q1 as an open-source model to support community research and development.

   arXiv 2610.30949 ↗ (opens in a new tab)PDF ↗ (opens in a new tab)

6. 49votes

   Toward Recursive Self-Improvement in Physical AI

   Meng Luo, Zechen Bai, Shanqing Xu and 9 more · National University of Singapore

   Recursive self-improvement (RSI) describes a system that improves not only its behavior but also the process by which it improves. Recent digital agents test this idea by rewriting their own code and checking each version with executable tests. Bringing these mechanisms into the physical world requires learning from partial observations through costly trials, while accounting for changing operating conditions and potentially irreversible consequences. We position RSI within robot learning and trace pathways from improving robot capabilities to improving the processes that generate them. We examine how physical experience can strengthen these improvement mechanisms and when the resulting gains can support further self-improvement of the mechanisms themselves. Gains carry forward only when feedback addresses remaining learning needs, the receiving component can use the change, its value survives changes in tasks or hardware, and continued practice remains safe and affordable. Existing studies, concentrated in manipulation, support behavioral improvement, benefits to later learning, and procedure improvement. Some systems also change the improver's knowledge or tools, but the physical studies reviewed here have yet to isolate gains attributable to recursion. We synthesize these findings into evaluation principles and research directions for machines that, trial by trial, safely improve the way they improve.

   arXiv 2610.29677 ↗ (opens in a new tab)PDF ↗ (opens in a new tab)Code (15 stars) ↗ (opens in a new tab)Repository on GitHub Trending Today ↗ (opens in a new tab)

7. 40votes

   Deep Fusion Memory: A Chunk-Level Parametric Memory for Large Language Models

   Rubin Wei, Siyuan Sun, Hao Sun and 5 more

   Large language models need effective ways to acquire and use external knowledge beyond what they retain from pretraining. Continued pretraining risks catastrophic forgetting, while retrieval at inference time can add substantial overhead. External parametric memory avoids online retrieval, but constructing its training data requires extensive offline search, and output-level interpolation provides only shallow fusion. We introduce Deep Fusion Memory (DFM), a parametric memory architecture that reduces this construction workload and incorporates learned memory into intermediate hidden states. A causal memory predictor learns to generate memory from the preceding context, using retrieved chunk embeddings from the corpus as supervision. The predicted memory is shared across tokens within each chunk and fused into their hidden states through gated cross-attention. Memory prediction and fusion are trained end to end with the backbone frozen, and inference requires no explicit retrieval. Compared with existing parametric memory approaches, which often construct token-level memory targets, DFM requires 32times fewer retrieval queries and 2048times fewer retrieved items to construct its training data. Across six QA tasks, DFM performs better over the strongest baseline by 12.71% on Mistral-7B-v0.3 and 11.19% on Qwen3-8B-Base. Beyond QA, domain adaptation yields average gains of 6.51 and 4.38 points over Qwen3-4B-Base and Qwen3-8B-Base, respectively.

   arXiv 2610.25100 ↗ (opens in a new tab)PDF ↗ (opens in a new tab)

8. 32votes

   What Generation Knows: Unlocking Fine-Grained Understanding in Unified Multimodal Models

   Tengju Ru, Weitong Lian, Zecong Tang and 6 more

   Fine-grained visual understanding requires distinguishing subtle differences in local attributes and spatial relations, yet remains challenging for existing vision-language models. Unified multimodal models (UMMs) offer a new opportunity through generation pathways that preserve rich visual information complementary to understanding. However, existing generation-assisted understanding methods mainly rely on generative supervision or explicit generation and have not systematically explored direct use of native generation-side representations. To address this gap, we systematically analyze what generation-side representations offer for fine-grained understanding, finding that they are more sensitive to fine-grained semantic changes, capture task-relevant changes missed by understanding-side representations, and depend on correct spatial organization for this advantage. Guided by these findings, we design GAFU, a post-training framework that unlocks native generation-side information for fine-grained understanding. It compresses generation-side visual representations into compact \(G\) tokens that preserve fine-grained visual details, enabling task-conditioned retrieval by the understanding pathway. Experiments show that GAFU consistently outperforms SFT baselines trained on the same data across diverse visual understanding tasks and UMM architectures, with maximum relative improvements of 20.00\%, 17.94\%, and 8.62\% on VStar-Bench, OmniSpatial, and VSR-Bench, respectively. Overall, GAFU converts complementary information from the generation pathway into gains in fine-grained visual understanding, providing an effective path toward synergy between generation and understanding in UMMs.

   arXiv 2610.23987 ↗ (opens in a new tab)PDF ↗ (opens in a new tab)Code (28 stars) ↗ (opens in a new tab)Repository on GitHub Trending Today ↗ (opens in a new tab)

9. 29votes

   LaLa-World: Scaling Latent World Models with Natural Language Actions

   Junha Song, Geonmo Gu, Jeongeun Park and 5 more · NAVER AI Lab

   This paper shows that JEPA-style latent world models (LWMs) can learn across diverse domains and data sources by adopting the language-conditioned interface of video generation models. We establish this approach as an effective and efficient basis for planning with imagination and downstream policy fine-tuning. To this end, we introduce LaLa-World, a Language-conditioned Latent World model that learns from simulation and robot trajectories together with broader image and video data. Two designs make this work. First, we describe both numerical actions and visual changes in language, enabling joint training of a single future predictor across heterogeneous datasets. Second, we build the predictor on a language model, allowing it to interpret language conditions while predicting future latent states. The resulting predictor achieves higher average MPC planning performance than existing LWMs trained separately for each domain or task. Adding image and video data further improves average planning performance and robustness to action phrasing. In a matched comparison with an RAEv2-based video generation model baseline, LaLa-World reaches comparable planning performance with 6times less training cost and 13.9times faster planning. Beyond planning, the pretrained LaLa-World serves as an initialization for LaLa-Policy, which jointly predicts actions and future visual representations. LaLa-Policy performs competitively with Cosmos Policy on LIBERO and RoboCasa, with up to 5.5times faster inference.

   arXiv 2610.27851 ↗ (opens in a new tab)PDF ↗ (opens in a new tab)Code (4 stars) ↗ (opens in a new tab)Repository on GitHub Trending Today ↗ (opens in a new tab)

10. 26votes

    FilmFlow: Agentic System for 3D Virtual Film Cinematography

    Yiming Zhang, Jiarui Guo, Haojia Wei and 5 more

    Complex camera motion is central to visual storytelling, yet translating cinematographic intent into controllable, executable camera trajectories remains challenging. We introduce FilmFlow, an agentic framework that converts natural-language instructions or reference videos into explicit camera trajectories for dynamic 3D environments. To generate these trajectories, a Director agent constructs executable camera plans by composing high-level motions from concurrent atomic operations that jointly control translation, rotation, and framing. The Director is supported by three specialized agents: an Interpreter that extracts scene-grounded cinematographic intent, a Scout that selects initial viewpoints, and a Critic that evaluates rendered results and provides visual feedback for iterative plan refinement. We also introduce CinemaBench, comprising 150 Blender scenes from self-created and licensed sources, with five camera instructions per scene for 750 text-directed tasks and 60 reference videos associated with a subset of scenes. CinemaBench supports evaluation of both text-directed camera generation and video reference-directed camera generation. Across a diverse set of evaluated baselines, FilmFlow achieves the strongest benchmark performance and the highest user preference, demonstrating effective spatial reasoning, temporal coordination, and visual composition for executable 3D cinematography.

    arXiv 2610.30753 ↗ (opens in a new tab)PDF ↗ (opens in a new tab)

11. 26votes

    Self-Distilling Future Video Representations for World Action Models

    Huiwon Jang, Suhyeok Jang, Hyeonmo Kang and 3 more · KAIST AI

    World Action Models (WAMs) have emerged as a promising approach to learning generalist robot policies using rich spatiotemporal priors from pre-trained video diffusion models. A recent line of WAMs improves inference efficiency by conditioning a separate action decoder on intermediate future video representations extracted from a single denoising step, avoiding costly iterative denoising required for video generation. This design makes action prediction depend directly on the quality of these future representations. In this paper, we introduce Future REpresentation learning via self-Distillation with temporal context (FRED), a framework that trains WAMs to improve the quality of future video representations from noise in a single denoising step. Specifically, FRED uses self-distillation to predict future representations from noise, using representations extracted from ground-truth future observations as targets. We further condition the video model on historical observations, providing temporal context for predicting future representations better. Across diverse real-world manipulation scenarios, FRED consistently outperforms competing WAMs. It achieves particularly large gains on long-horizon and out-of-domain tasks under zero-shot environment generalization, and substantially improves human-to-robot skill transfer, reaching 50.0% task success on tasks absent from robot training data and demonstrated only in human videos, compared with 19.4% for the best competing WAM.

    arXiv 2610.30320 ↗ (opens in a new tab)PDF ↗ (opens in a new tab)Code (7 stars) ↗ (opens in a new tab)Repository on GitHub Trending Today ↗ (opens in a new tab)

12. 25votes

    Meta Expert: Cross-Layer Expert Sharing for Storage- and Retrieval-Efficient MoE

    Ermo Hua, Xiangyu Hong, Baiting Wu and 11 more · TsinghuaC3I

    As model parameters scale up, sparsely activated Mixture-of-Experts (MoE) approaches have become essential for model scaling. However, mainstream models currently adopt hierarchical architectures, where experts in different layers, although topologically independent, exhibit substantial similarity and redundancy in their stored content. Compared to the hierarchically arranged Local Expert in existing mainstream models, we hypothesize that inter-layer shared Meta Expert hold greater potential. To this end, we conduct a multi-dimensional empirical comparison between Local and Meta Experts, and find that models incorporating Meta Experts exhibit lower parameter redundancy, together with lower cross-entropy loss and higher downstream task accuracy. With the activated quantity and the expert granularity held fixed, our model matches the performance of Vanilla MoE using only 70--80\% of the experts, substantially improving the model's scaling potential. Beyond removing inter-layer redundancy among experts and improving information storage efficiency, our theoretical analysis further shows that, compared with Local Experts, Meta Experts provide hidden states with more flexible residual pathways, thereby improving information retrieval efficiency.

    arXiv 2610.27598 ↗ (opens in a new tab)PDF ↗ (opens in a new tab)

13. 24votes

    Policy-Mask: Budget-Aware Adaptation of Diffusion Features to Discriminative Tasks

    Ivan Listopadov, Maksim Nakhodnov, Aibek Alanov

    Selecting intermediate features from a frozen diffusion model for discriminative tasks is non-trivial because the useful signal is distributed across the denoising trajectory, network depth, and channels. In practice, this requires choosing a timestep, a block, and a channel subset. Existing methods either fix these choices by hand or optimize only a few extraction hyperparameters, most often the timestep, then reuse…

    arXiv 2610.28889 ↗ (opens in a new tab)PDF ↗ (opens in a new tab)

14. 18votes

    Heartbeat Thinking: Speculative Reasoning and Tool Execution While Listening in Realtime Voice Agents

    Zhenyu Zhang, Kewei Fu, Yongqi Tong and 4 more · ant-international

    Tool-using voice agents often leave users waiting after speech ends, even when actionable information arrives earlier in the request. Speculative approaches begin work during speech, but chunk-bounded or interrupt-on-update generation can truncate a tool call before its arguments are complete. This couples computation time to speech updates, limiting useful work completed in advance. We introduce Heartbeat Thinking…

    arXiv 2610.26233 ↗ (opens in a new tab)PDF ↗ (opens in a new tab)

15. 18votes

    Code2Video-Compass: A Comprehensive Benchmark for General-Purpose Code-Based Video Generation across T2V, I2V, and V2V

    Zhenghan Chen, Zekai Shao, Xin Lin and 2 more · Fudan University

    Code-based video generation offers fine-grained control, targeted editing, and component reuse compared with direct video generation. This approach requires multimodal large language models (MLLMs) to translate visual and temporal requirements into executable programs that produce complete videos. However, existing code-based benchmarks primarily target specialized tasks, leaving complete video creation across…

    arXiv 2610.28416 ↗ (opens in a new tab)PDF ↗ (opens in a new tab)Code (5 stars) ↗ (opens in a new tab)Repository on GitHub Trending Today ↗ (opens in a new tab)

16. 17votes

    Beyond Watching and Searching: Benchmarking Agents for Video-centered Deep Research Reports

    Jiahao Meng, Qize Yang, Yuxuan Wang and 4 more · Qwen

    Deep research agents synthesize open-web evidence into long reports, but current benchmarks do not evaluate research centered on a source video. We introduce Video-Centered Deep Research Report Generation. Given a video and user request, an agent identifies research questions, retrieves external multimodal evidence, and produces an interactive report linked to relevant video moments. This task has direct practical…

    arXiv 2610.31158 ↗ (opens in a new tab)PDF ↗ (opens in a new tab)Code (12 stars) ↗ (opens in a new tab)Repository on GitHub Trending Today ↗ (opens in a new tab)

17. 16votes

    Agent Mosaic: Recognizing Confidentiality Leaks in Agentic LLM Systems

    Daniel Ruiz, Luca Luceri, Emilio Ferrara · University of Southern California

    Modern LLM agents can retrieve information from accessible documents, and then disclose a sensitive conclusion assembled from them. This mosaic effect creates a critical risk for agents operating over confidential data. We quantify its realization with 30 synthetic cybersecurity, medical, and military examples, yielding 10,800 final answers from three LLM agents in controlled simulation and 1,440 answers from live…

    arXiv 2610.30418 ↗ (opens in a new tab)PDF ↗ (opens in a new tab)

18. 16votes

    RouteWeaver: Weaving Mode Selection and Execution into Unified LLM Routing

    Xiaohan Wang, Haozhen Zhang, Qingyuan Liu and 2 more · Nanyang Technological University

    LLM routing dynamically selects and coordinates heterogeneous language models across diverse tasks. However, existing approaches are largely built around a predefined execution paradigm, such as single-round, multi-round, or agentic routing, which fixes how model calls are organized and limits adaptation to different query needs. We propose RouteWeaver, a unified routing framework that integrates these routing modes…

    arXiv 2610.19705 ↗ (opens in a new tab)PDF ↗ (opens in a new tab)Code (2 stars) ↗ (opens in a new tab)Repository on GitHub Trending Today ↗ (opens in a new tab)

19. 15votes

    RLSplat: Resource-Linear Budget Control for Feed-forward 3D Gaussian Splatting

    Injae Kim, Minseok Joo, Jihwan Park and 3 more

    Feed-forward 3D Gaussian Splatting (FF3DGS) reconstructs 3D scenes from images in a single forward pass, making it well-suited to applications that must operate within limited resource budgets. To further improve its practicality, recent budget-controllable FF3DGS methods allow the number of Gaussians to be adjusted at inference, so that the output meets a given storage limit or rendering-latency constraint. However…

    arXiv 2610.27712 ↗ (opens in a new tab)PDF ↗ (opens in a new tab)Code (8 stars) ↗ (opens in a new tab)Repository on GitHub Trending Today ↗ (opens in a new tab)

20. 15votes

    Is Complex Agentic Memory Always Needed? Naive RAG Is Stronger Than We Thought

    Zhengye Bao, Shengtao Zhang, Haokai Zhang and 3 more · Xi'an Jiaotong University

    LLM memory is widely used in long-term conversation understanding. Agentic memory systems often use mutation, structural organization, learned retrieval strategies, or other complex operations. Is this complexity always necessary? We study Raw-RAG, a naive RAG baseline using dense retrieval and reranking over raw history to supply evidence to a reader LLM. Across LoCoMo, LongMemEval, MEME, and MemoryAgentBench…

    arXiv 2610.30755 ↗ (opens in a new tab)PDF ↗ (opens in a new tab)Code (13 stars) ↗ (opens in a new tab)Repository on GitHub Trending Today ↗ (opens in a new tab)

21. 14votes

    Cola2: Co-Adaptive Hierarchical Language Modeling with Continuous Semantic Compression and Balanced Discrete Generation

    Hongcan Guo, Yian Zhao, Feng Wang and 4 more · ByteDance Seed

    Hierarchical language generation separates continuous semantic modeling from discrete text realization, but its effectiveness depends on what the latent space compresses and how the discrete generator uses it. We propose Cola2, a framework that jointly studies continuous semantic compression, the balance between reconstruction and generation, and continuous-discrete co-adaptation. Cola2 dynamically segments text into…

    arXiv 2610.31305 ↗ (opens in a new tab)PDF ↗ (opens in a new tab)

22. 12votes

    RTAformer: Relation-Transition-Aware Transformer for Video Scene Graph Generation

    Jaeyeon Heo, Geuntaek Lim, Yukyung Choi

    Video scene graph generation (VidSGG) aims to capture objects and their evolving relationships in videos. This requires accounting for both the persistence of object identities and abrupt changes in relationships. Existing methods aggregate information across frames to exploit temporal context, but an emphasis on consistency can obscure these changes. As a result, a model may retain its previous prediction even after…

    arXiv 2610.20091 ↗ (opens in a new tab)PDF ↗ (opens in a new tab)Code (3 stars) ↗ (opens in a new tab)Repository on GitHub Trending Today ↗ (opens in a new tab)

23. 12votes

    Verus-Insight: Towards Explainable Artifact Detection in AI-Generated Videos

    Zhuoran Zhang, Yang Shi, Qixun Wang and 11 more

    Recent advances in video generation have made synthetic videos increasingly realistic, placing greater demands on reliable AI-generated video detection. Existing artifact-based detectors typically identify generation artifacts as evidence for source prediction, yet they may either fail to recognize subtle artifacts or reach the correct source decision without faithfully identifying the evidence underlying it. In this…

    arXiv 2610.30866 ↗ (opens in a new tab)PDF ↗ (opens in a new tab)Code (5 stars) ↗ (opens in a new tab)Repository on GitHub Trending Today ↗ (opens in a new tab)

24. 12votes

    Rethinking Sequence Compression with Test-time Regression

    Sihan Yang, Jie Huang, Hanxuan Li and 4 more · CUHK SphereLab

    Sequence compression is a fundamental operation and a critical information bottleneck in efficient language and multimodal models, and yet prevailing approaches based on pooling or learned projections remain underperforming. We revisit sequence compression through the lens of test-time regression: input tokens define a regression problem whose fitted coefficients form the compressed representation. Importantly, the…

    arXiv 2610.31574 ↗ (opens in a new tab)PDF ↗ (opens in a new tab)Code (12 stars) ↗ (opens in a new tab)Repository on GitHub Trending Today ↗ (opens in a new tab)

25. 11votes

    AgentVQA: A Unified Benchmark for Agentic Visual Understanding

    Advait Gupta, Sachin Konan, Tom Yin and 2 more · zlab-princeton

    Vision-language models (VLMs) can perform a broad range of tasks across diverse settings, yet their performance in agentic contexts remains poorly understood. Although online evaluations in simulators and real-world environments are essential for measuring interactive agent performance, they are costly and challenging to scale. Complementary offline VQA benchmarks can enable faster and more reliable comparisons…

    arXiv 2610.31494 ↗ (opens in a new tab)PDF ↗ (opens in a new tab)Code (8 stars) ↗ (opens in a new tab)Repository on GitHub Trending Today ↗ (opens in a new tab)

26. 10votes

    AnyGameRenderer: Entity-Consistent Generative Rendering Across Games and an Entity-Level Benchmark

    Ruicong Liu, Liangyang Ouyang, Fengbo Lan and 2 more · Alaya Lab

    AI coding agents can now build small playable games in minutes, but the results usually look like programmer art: gray blockouts, colored geometric primitives, and flat semantic blobs. We present AnyGameRenderer, a video-to-video generative renderer that turns such footage into high-quality visuals with characters, motion detail, and effects. Throughout, it keeps the layout, camera, and every entity's position and…

    arXiv 2610.31466 ↗ (opens in a new tab)PDF ↗ (opens in a new tab)Code (19 stars) ↗ (opens in a new tab)Repository on GitHub Trending Today ↗ (opens in a new tab)

27. 8votes

    MolLean: A Process-Verifiable Language for Chemical Reasoning

    Jiatong Li, Yatao Bian

    Chemical chain-of-thought can contain hallucinated structural and property claims. We thereby introduce MolLean, a process-verifiable language that grounds chemical reasoning in an explicit molecular state. A layered Lean-based kernel checks state transitions and assertions over molecular readouts, from primitive graph edits to compound transformations. Meanwhile, a typed witness protocol separates native structural…

    arXiv 2610.20459 ↗ (opens in a new tab)PDF ↗ (opens in a new tab)Code (3 stars) ↗ (opens in a new tab)Repository on GitHub Trending Today ↗ (opens in a new tab)

28. 7votes

    RIDAR: Safeguarding Research Integrity in Autonomous Research Agents via Automated Detection and Runtime Intervention

    Jiening Siow, Amy Xin, Junjie Wang and 7 more · Knowledge Engineer Group @ Tsinghua University

    Autonomous research agents are increasingly used to automate large portions of scientific research, yet they are prone to research integrity violations (RIVs): behaviors that compromise the validity, reproducibility, or faithfulness of the research process. We present RIDAR, a framework for automated RIV detection and runtime intervention. First, we introduce RIVT, a comprehensive taxonomy of 14 RIV types spanning…

    arXiv 2610.31372 ↗ (opens in a new tab)PDF ↗ (opens in a new tab)Code (4 stars) ↗ (opens in a new tab)Repository on GitHub Trending Today ↗ (opens in a new tab)

29. 7votes

    Inherited, Not Invented: Tracing the Provenance of Wait in Reasoning Models

    Zhizhuo Kou, Sizai Hou, Long Chen and 6 more · HUAWEI Noah's Ark Lab

    Reinforcement learning (RL) is credited with teaching reasoning models to write {wait} before reconsidering a step, yet large RL accuracy gains do not require the word. This view can confuse what RL discovers with what a model inherits from its training data. We trace the word through open models' training histories, reading it with label-free indices of frequency, position, form and usage and an injected-error test…

    arXiv 2610.30882 ↗ (opens in a new tab)PDF ↗ (opens in a new tab)Code (0 stars) ↗ (opens in a new tab)Repository on GitHub Trending Today ↗ (opens in a new tab)

30. 7votes

    Reading, Writing, Sharing, and Interacting with the World through Video

    Shengqiong Wu, Meng Luo, Bobo Li and 5 more

    Video foundation models have advanced rapidly in understanding and generating visual sequences, while video world models seek to capture the underlying dynamics of the world they depict. Despite their different objectives, both concern the relationship between video observations and an evolving world. This survey adopts world modeling as a unifying lens for examining these developments. Viewing an observed video as a…

    arXiv 2610.31668 ↗ (opens in a new tab)PDF ↗ (opens in a new tab)

Abstracts are the authors’ original text, and the votes are those of the list of October 23, 2026. Past the leading papers the abstract is an excerpt; the full text is one click away on arXiv.

Source: Hugging Face public API · updated Oct 24, 2026