{"papers":[{"arxiv_id":"2611.15777","title":"SO-Arena: Benchmarking the Capability Spectrum and Reliability of System One Models","upvotes":91,"github_repo":"https://github.com/holdrain/SO-Arena","github_stars":24,"org":"National University of Singapore","source_url":"https://huggingface.co/api/daily_papers","first_seen":1794551979122,"updated_at":1794671895793},{"arxiv_id":"2611.14815","title":"BirdDreams: Joint Perspective and BEV Video Generation for a Plausible, Reactive Driving World Model","upvotes":49,"github_repo":null,"github_stars":null,"org":"NVIDIA","source_url":"https://huggingface.co/api/daily_papers","first_seen":1794544779121,"updated_at":1794671895793},{"arxiv_id":"2610.40394","title":"Scaling Mathematical Proof Supervision from Structured Textbooks","upvotes":47,"github_repo":null,"github_stars":null,"org":"Intern Large Models","source_url":"https://huggingface.co/api/daily_papers","first_seen":1794465579143,"updated_at":1794671895793},{"arxiv_id":"2611.16748","title":"PhysLoop: Harnessing LLMs' Physics Awareness for Self-Improving Video Generation Models","upvotes":45,"github_repo":"https://github.com/DAGroup-PKU/PhysLoop","github_stars":34,"org":"DAGroup-PKU","source_url":"https://huggingface.co/api/daily_papers","first_seen":1794548379095,"updated_at":1794671895793},{"arxiv_id":"2611.13004","title":"G-STAR: Group-Scaled Token Capacity for Deeply Compressed Autoregressive Generation","upvotes":44,"github_repo":"https://github.com/DAGroup-PKU/G-STAR","github_stars":25,"org":"LongCat","source_url":"https://huggingface.co/api/daily_papers","first_seen":1794544779121,"updated_at":1794671895793},{"arxiv_id":"2611.13001","title":"One Table, Many Queries: Benchmarking Generalist Tabular Models Across Generation, Imputation, and Prediction","upvotes":40,"github_repo":"https://github.com/limix-ldm-ai/OTBench","github_stars":1,"org":"Stable AI","source_url":"https://huggingface.co/api/daily_papers","first_seen":1794451179130,"updated_at":1794584379216},{"arxiv_id":"2611.15131","title":"Duo: A Reciprocal World Model for Full-Duplex Interaction","upvotes":39,"github_repo":"https://github.com/inclusionAI/Duo","github_stars":40,"org":"inclusionAI","source_url":"https://huggingface.co/api/daily_papers","first_seen":1794544779121,"updated_at":1794671895793},{"arxiv_id":"2611.13410","title":"SteerDistill: Quantizing LLM Agents via Closed-Loop Teacher Steering","upvotes":36,"github_repo":"https://github.com/air-embodied-brain/SteerDistill","github_stars":10,"org":null,"source_url":"https://huggingface.co/api/daily_papers","first_seen":1794472779163,"updated_at":1794671895793},{"arxiv_id":"2611.17167","title":"Actor, Judge, or Teacher? Understanding Decision Models in Long-Horizon Agents","upvotes":32,"github_repo":"https://github.com/ZJU-REAL/decision-agents","github_stars":42,"org":"Zhejiang University","source_url":"https://huggingface.co/api/daily_papers","first_seen":1794551979122,"updated_at":1794671895793},{"arxiv_id":"2611.15844","title":"Open Vision Banana: A Fully Open Recipe for Generative Visual Perception","upvotes":32,"github_repo":"https://github.com/OpenVisionBanana/OpenVisionBanana","github_stars":21,"org":"Fundamental AI Lab at UTN","source_url":"https://huggingface.co/api/daily_papers","first_seen":1794566379261,"updated_at":1794671895793},{"arxiv_id":"2610.39671","title":"Incentivizing Self-Learning in Large Language Models via Reinforcement Learning","upvotes":30,"github_repo":null,"github_stars":null,"org":"Intern Large Models","source_url":"https://huggingface.co/api/daily_papers","first_seen":1794458379171,"updated_at":1794602379323},{"arxiv_id":"2611.05984","title":"On the Design of Hyper-Connections: Simplification, Stability, and Scalability","upvotes":27,"github_repo":"https://github.com/aHapBean/SimpleHC","github_stars":20,"org":"dots studio","source_url":"https://huggingface.co/api/daily_papers","first_seen":1794541179107,"updated_at":1794671895793},{"arxiv_id":"2611.17060","title":"Ropedia Xperience 2: A Gold Standard for Scaling Physical AI Environments and Behaviors","upvotes":26,"github_repo":"https://github.com/Ropedia/Ropedia-Xperience-2","github_stars":16,"org":"Ropedia","source_url":"https://huggingface.co/api/daily_papers","first_seen":1794551979122,"updated_at":1794671895793},{"arxiv_id":"2608.22237","title":"Read Less, Solve More: Token-Efficient Sparse Reading of External Content for AI Agents","upvotes":22,"github_repo":"https://github.com/Liuzedooong/SparseReading","github_stars":38,"org":"Institute of Computing Technology","source_url":"https://huggingface.co/api/daily_papers","first_seen":1794469179108,"updated_at":1794671895793},{"arxiv_id":"2611.17331","title":"TTB: Test-time Baking for Efficient Rendering of Decoder-only View Synthesis Models","upvotes":22,"github_repo":"https://github.com/NVlabs/DVSM","github_stars":35,"org":"NVIDIA","source_url":"https://huggingface.co/api/daily_papers","first_seen":1794559179085,"updated_at":1794671895793},{"arxiv_id":"2611.08318","title":"Learning the Task or Learning the Verifier? Rethinking Criteria Exposure in Embodied Self-Improvement","upvotes":18,"github_repo":null,"github_stars":null,"org":"DAGroup-PKU","source_url":"https://huggingface.co/api/daily_papers","first_seen":1794562779108,"updated_at":1794671895793},{"arxiv_id":"2611.16217","title":"WorldDraft: If Code Builds the World, Can Video Models Just Render It?","upvotes":16,"github_repo":"https://github.com/KevinHuge/WorldDraft","github_stars":10,"org":null,"source_url":"https://huggingface.co/api/daily_papers","first_seen":1794548379095,"updated_at":1794671895793},{"arxiv_id":"2611.17334","title":"Unbundling Multimodal Vision Encoding","upvotes":14,"github_repo":null,"github_stars":null,"org":"Meta","source_url":"https://huggingface.co/api/daily_papers","first_seen":1794587979222,"updated_at":1794671895793},{"arxiv_id":"2611.10193","title":"Ensemble Routing for Prompt-Adaptive Cost-Aware LLM Inference","upvotes":13,"github_repo":null,"github_stars":null,"org":null,"source_url":"https://huggingface.co/api/daily_papers","first_seen":1794465579143,"updated_at":1794609579338},{"arxiv_id":"2611.08286","title":"Interactive Visual Gym: Evaluating Visual Interaction Models with Simulated Users in Interactive Worlds","upvotes":13,"github_repo":"https://github.com/SalesforceAIResearch/Interactive-Visual-Gym","github_stars":8,"org":null,"source_url":"https://huggingface.co/api/daily_papers","first_seen":1794469179108,"updated_at":1794671895793},{"arxiv_id":"2611.13028","title":"GTAGym: AAA Game Tasks Environment for Evaluation and Reinforcement Learning","upvotes":12,"github_repo":"https://github.com/ljbro/GTAGym","github_stars":11,"org":"OpenMOSS","source_url":"https://huggingface.co/api/daily_papers","first_seen":1794454779151,"updated_at":1794595179318},{"arxiv_id":"2611.12304","title":"Evolving Infra: Agent-Adaptive LLM Serving at Scale","upvotes":12,"github_repo":"https://github.com/mit-han-lab/EvolvingInfra","github_stars":30,"org":"MIT HAN Lab","source_url":"https://huggingface.co/api/daily_papers","first_seen":1794483579052,"updated_at":1794671895793},{"arxiv_id":"2611.16517","title":"UniSpark: Exploring Hybrid Attention for Multimodal Understanding and Generation","upvotes":12,"github_repo":null,"github_stars":null,"org":"Ant Group","source_url":"https://huggingface.co/api/daily_papers","first_seen":1794548379095,"updated_at":1794671895793},{"arxiv_id":"2611.16905","title":"Factored One-sided Adam-Moment for Practical and Scalable SOAP","upvotes":12,"github_repo":"https://github.com/naver-ai/foam","github_stars":0,"org":"NAVER AI Lab","source_url":"https://huggingface.co/api/daily_papers","first_seen":1794551979122,"updated_at":1794671895793},{"arxiv_id":"2611.10486","title":"Test-Time Scaling for Diffusion Language Models with Frequency-Aware Remasking","upvotes":9,"github_repo":null,"github_stars":null,"org":"UC Riverside","source_url":"https://huggingface.co/api/daily_papers","first_seen":1794422379023,"updated_at":1794580779219},{"arxiv_id":"2611.12869","title":"Where Does Alignment Emerge and What Does It Mean? A Closer Look at the Platonic Representation Hypothesis","upvotes":6,"github_repo":"https://github.com/ExplainableML/prh-closer-look","github_stars":8,"org":"Technical University of Munich","source_url":"https://huggingface.co/api/daily_papers","first_seen":1794476379101,"updated_at":1794671895793},{"arxiv_id":"2611.13766","title":"FAME-QP: A GPU-Accelerated Quadratic-Programming Solver for Real-Time Model Predictive Control","upvotes":6,"github_repo":"https://github.com/santoshrajkumar/fame-qp","github_stars":11,"org":"The Ohio State University","source_url":"https://huggingface.co/api/daily_papers","first_seen":1794494379128,"updated_at":1794671895793},{"arxiv_id":"2607.13920","title":"DeepStress: Stress-Testing Deep Search Agents","upvotes":6,"github_repo":null,"github_stars":null,"org":"Orange","source_url":"https://huggingface.co/api/daily_papers","first_seen":1794562779108,"updated_at":1794671895793},{"arxiv_id":"2611.10439","title":"Who Remembers What? Multi-Granularity Memory Extraction for Multi-User, Multi-Agent Interaction","upvotes":6,"github_repo":null,"github_stars":null,"org":"Amazon Web Services","source_url":"https://huggingface.co/api/daily_papers","first_seen":1794623979382,"updated_at":1794671895793},{"arxiv_id":"2611.08538","title":"Subliminal Learning in Vision-Language Models","upvotes":5,"github_repo":null,"github_stars":null,"org":"Johns Hopkins University","source_url":"https://huggingface.co/api/daily_papers","first_seen":1794533979109,"updated_at":1794671895793},{"arxiv_id":"2607.24999","title":"CogBattery: Human-Referenced Evaluation of Cognitive Task Behavior and Structure in Language Models","upvotes":4,"github_repo":"https://github.com/dengzhe-hou/CogBattery","github_stars":1,"org":null,"source_url":"https://huggingface.co/api/daily_papers","first_seen":1794465579143,"updated_at":1794620379381},{"arxiv_id":"2603.27343","title":"WMIP: A Working-Memory-Inspired Programmable Probe of Cumulative State Tracking in Large Language Models","upvotes":4,"github_repo":"https://github.com/dengzhe-hou/WMIP","github_stars":1,"org":null,"source_url":"https://huggingface.co/api/daily_papers","first_seen":1794465579143,"updated_at":1794616779369},{"arxiv_id":"2611.14418","title":"Precision on Demand: Escalating Weight Bits at Uncertain Decoding Steps in a Small Local Model","upvotes":4,"github_repo":null,"github_stars":null,"org":null,"source_url":"https://huggingface.co/api/daily_papers","first_seen":1794476379101,"updated_at":1794671895793},{"arxiv_id":"2611.08219","title":"Agent-R^2: Scaling Agents for Realistic Productivity Work via Real-Source Data Synthesis","upvotes":4,"github_repo":"https://github.com/ZJU-REAL/Agent-R2","github_stars":7,"org":"Zhejiang University","source_url":"https://huggingface.co/api/daily_papers","first_seen":1794555579107,"updated_at":1794671895793},{"arxiv_id":"2611.16009","title":"JustRUA: A Controlled Study of GPT-6 Robot-Use Agents","upvotes":4,"github_repo":"https://github.com/ZefanW/JustRUA","github_stars":1,"org":null,"source_url":"https://huggingface.co/api/daily_papers","first_seen":1794569979204,"updated_at":1794671895793},{"arxiv_id":"2611.09567","title":"TurtLES: A Large-Scale Benchmark for Turbulent 3D Neural PDE Surrogates","upvotes":4,"github_repo":"https://github.com/itsakk/TurtLES","github_stars":1,"org":"Sorbonne University, Institute of Intelligent Systems and Robotics","source_url":"https://huggingface.co/api/daily_papers","first_seen":1794598779276,"updated_at":1794671895793},{"arxiv_id":"2611.13425","title":"Prompt2Echo (P2Echo): Text-Prompted Multi-View Echocardiography Segmentation with One Model","upvotes":3,"github_repo":"https://github.com/moeinheidari7829/P2Echo","github_stars":5,"org":"University of British Columbia","source_url":"https://huggingface.co/api/daily_papers","first_seen":1794422379023,"updated_at":1794584379216},{"arxiv_id":"2611.14116","title":"Visual Similarity in Adult Word Extension and Artificial Word Learning","upvotes":3,"github_repo":null,"github_stars":null,"org":null,"source_url":"https://huggingface.co/api/daily_papers","first_seen":1794425979046,"updated_at":1794584379216},{"arxiv_id":"2611.08379","title":"Module-Aware Optimization for Graph Neural Networks","upvotes":3,"github_repo":"https://github.com/guy-hadad/GraphMuon","github_stars":3,"org":null,"source_url":"https://huggingface.co/api/daily_papers","first_seen":1794469179108,"updated_at":1794671895793},{"arxiv_id":"2611.13758","title":"Mixed Signals: Weight-Space Programming for EEG and ECG","upvotes":3,"github_repo":null,"github_stars":null,"org":"EPFL","source_url":"https://huggingface.co/api/daily_papers","first_seen":1794472779163,"updated_at":1794671895793},{"arxiv_id":"2611.05862","title":"CARTBench: Rubric-Based Evaluation of Shopping Advice for Complex and Ambiguous Requests with Timelines","upvotes":3,"github_repo":"https://github.com/Da1yuqin/CARTBench","github_stars":0,"org":null,"source_url":"https://huggingface.co/api/daily_papers","first_seen":1794479979049,"updated_at":1794671895793},{"arxiv_id":"2611.11531","title":"Probing Transformer Representations Layer by Layer, Module by Module","upvotes":3,"github_repo":"https://github.com/ambroiseodt/waldo","github_stars":1,"org":null,"source_url":"https://huggingface.co/api/daily_papers","first_seen":1794519579085,"updated_at":1794671895793},{"arxiv_id":"2610.41453","title":"Evidence-Guided Recovery for AI Agents with Ambiguous Tool Outcomes and Partial Execution","upvotes":3,"github_repo":null,"github_stars":null,"org":null,"source_url":"https://huggingface.co/api/daily_papers","first_seen":1794551979122,"updated_at":1794671895793},{"arxiv_id":"2611.00428","title":"Do Multimodal Models Decide Consistently on Equivalent Optical Spectra?","upvotes":3,"github_repo":"https://github.com/zwang-devv/spectra-decision-audit","github_stars":1,"org":null,"source_url":"https://huggingface.co/api/daily_papers","first_seen":1794551979122,"updated_at":1794671895793},{"arxiv_id":"2611.00359","title":"Humanized but Still True? Auditing Facts and Detection in AI-Text Humanizers","upvotes":3,"github_repo":"https://github.com/zwang-devv/humanizer-fact-audit","github_stars":1,"org":null,"source_url":"https://huggingface.co/api/daily_papers","first_seen":1794551979122,"updated_at":1794671895793},{"arxiv_id":"2611.12872","title":"HiVe-Mem: Interleaving Horizontal Memory Expansion and Vertical Evidence Composition for Multimodal Agents","upvotes":3,"github_repo":"https://github.com/ViktorAxelsen/HiVe-Mem","github_stars":0,"org":"Nanyang Technological University","source_url":"https://huggingface.co/api/daily_papers","first_seen":1794559179085,"updated_at":1794671895793},{"arxiv_id":"2611.16409","title":"Experience-Handoff Reinforcement Learning for Recursive Self-Improvement","upvotes":3,"github_repo":"https://github.com/doyoungkim-ml/ehrl","github_stars":3,"org":"KAIST AI","source_url":"https://huggingface.co/api/daily_papers","first_seen":1794584379216,"updated_at":1794671895793},{"arxiv_id":"2611.17190","title":"Consensus Capture in Reference-Based UAV Video Stabilization: A Benchmark on Dynamic Urban Scenes","upvotes":3,"github_repo":"https://github.com/rfonod/stabilo-benchmark","github_stars":0,"org":"EPFL","source_url":"https://huggingface.co/api/daily_papers","first_seen":1794605979343,"updated_at":1794671895793},{"arxiv_id":"2611.17336","title":"Back to Pixels: Lifting Latent Video Diffusion into Pixel Space","upvotes":3,"github_repo":null,"github_stars":null,"org":"Roblox Corporation","source_url":"https://huggingface.co/api/daily_papers","first_seen":1794613179495,"updated_at":1794671895793},{"arxiv_id":"2611.14413","title":"Bits or permutations? Spending a fixed inference budget on weight precision or on option-order averaging in small local language models","upvotes":2,"github_repo":null,"github_stars":null,"org":null,"source_url":"https://huggingface.co/api/daily_papers","first_seen":1794476379101,"updated_at":1794671895793},{"arxiv_id":"2611.13843","title":"PolyRoute: A Twelve-Language and Code-Mixed Benchmark for Typed-Decision Routing, with Baselines and a Leaderboard","upvotes":2,"github_repo":null,"github_stars":null,"org":null,"source_url":"https://huggingface.co/api/daily_papers","first_seen":1794476379101,"updated_at":1794671895793},{"arxiv_id":"2611.11306","title":"ScrapeBench: Evaluating Legal Compliance of AI Agents in Website Scraping","upvotes":2,"github_repo":"https://github.com/imperialite/scrapebench","github_stars":0,"org":null,"source_url":"https://huggingface.co/api/daily_papers","first_seen":1794497979139,"updated_at":1794671895793},{"arxiv_id":"2611.16321","title":"From Large Language Models to Efficient System One Models via Adaptive Computation","upvotes":2,"github_repo":"https://github.com/minhkks/NestOne","github_stars":1,"org":null,"source_url":"https://huggingface.co/api/daily_papers","first_seen":1794548379095,"updated_at":1794671895793},{"arxiv_id":"2611.14046","title":"Structured Confidence Perturbation via Fisher Geometry for Adversarial Training","upvotes":2,"github_repo":null,"github_stars":null,"org":"XJTLU","source_url":"https://huggingface.co/api/daily_papers","first_seen":1794559179085,"updated_at":1794671895793},{"arxiv_id":"2611.14256","title":"A Cross-Scenario Survey and Analysis of Self-Evolving Multimodal Agents","upvotes":2,"github_repo":"https://github.com/jingjing12110/SE-MMAgents","github_stars":0,"org":null,"source_url":"https://huggingface.co/api/daily_papers","first_seen":1794566379261,"updated_at":1794671895793},{"arxiv_id":"2611.12750","title":"The Narrative Gap: Can LLMs Help Us Navigate Diverse Narratives Across Languages?","upvotes":2,"github_repo":"https://github.com/isle-dev/Narrative-Bench-NeurIPS-2026","github_stars":0,"org":"Johns Hopkins University","source_url":"https://huggingface.co/api/daily_papers","first_seen":1794587979222,"updated_at":1794671895793},{"arxiv_id":"2611.16961","title":"The Value of Thinking: Learning When to Reason in Hybrid Decision Models","upvotes":2,"github_repo":"https://github.com/zhengxuyu/HDM-code","github_stars":1,"org":null,"source_url":"https://huggingface.co/api/daily_papers","first_seen":1794591579293,"updated_at":1794671895793},{"arxiv_id":"2611.11912","title":"LO-World: Unified BEV Latent Modeling for Joint 4D Occupancy and LiDAR Forecasting","upvotes":1,"github_repo":"https://github.com/lzzzzzm/LO-World","github_stars":5,"org":null,"source_url":"https://huggingface.co/api/daily_papers","first_seen":1794451179130,"updated_at":1794587979222},{"arxiv_id":"2611.15094","title":"A frontier machine intelligence for human neuroimaging","upvotes":1,"github_repo":"https://github.com/MLNeurosurg/neuro-vl","github_stars":4,"org":"Machine Learning in Neurosurgery Lab","source_url":"https://huggingface.co/api/daily_papers","first_seen":1794587979222,"updated_at":1794671895793},{"arxiv_id":"2611.16728","title":"EgoX: Egocentric Cross-Embodiment Manipulation with Embodiment Dreaming","upvotes":1,"github_repo":"https://github.com/egox-dream/egox","github_stars":9,"org":"Carnegie Mellon University","source_url":"https://huggingface.co/api/daily_papers","first_seen":1794620379381,"updated_at":1794671895793}]}