The Tape · Papers
Daily Papers
Title and upvotes of each paper in the top tenth of the twelve-week baseline, linked to the paper.
Hugging Face, Daily Papers 84 events recorded hf-papers.csv RSS read 9 Nov 2026, 22:42 UTC
Embed
The frame credits Hugging Face, Daily Papers and links back to its page. Preview it.
Cite
Download
The last 30 days
times in UTCFriday 6 November 20263 events
- day Daily PapersPapers VFlash: Fast, Accurate Visual Planning via Flash Primitive Decoding 93.3
- day Daily PapersPapers SLA: Scaling Spatial-Language-Action Model via Continual Pre-training 92.3
- day Daily PapersPapers From Autonomous Agents to Cognitive Symbionts: Toward AI-Augmented Human Intelligence 94.5
Thursday 5 November 20261 event
Wednesday 4 November 20262 events
Tuesday 3 November 20264 events
- day Daily PapersPapers CoworkOS:Scaling Agent Coworkers for Real-world Automation 92.5
- day Daily PapersPapers Wave Forcing: Towards Speed-of-Light Streaming Video Generation 94.7
- day Daily PapersPapers Advances in Agentic Computer Graphics 95.7
- day Daily PapersPapers CUA-Master: Scaling Computer-use Agents through Open-World Recursive Improvements 92.3
Monday 2 November 20263 events
- day Daily PapersPapers FrameForge: Harnessing Priors of Video Foundation Models for Unified Image Generation 93.7
- day Daily PapersPapers R^2Orch: Recursive Self-Improvement for Agent Orchestration via Self-Play within a Skill-Internalization Loop 91.7
- day Daily PapersPapers REA: A Routed Embodied Agent Runtime for Asynchronous Brain-Cerebellum Control 94.9
Friday 30 October 20263 events
Thursday 29 October 20263 events
- day Daily PapersPapers OmniShowcase: Omnidirectional Subject-Consistent Video Generation from Multi-View Images 95.4
- day Daily PapersPapers Efficient Streaming Audio-Visual Target Speaker Extraction for Real-World Acoustic Scenes 94.9
- day Daily PapersPapers TAO: Tool-Aware Joint Scheduling for LLM-Based Agentic Serving 92.1
Wednesday 28 October 202610 events
- day Daily PapersPapers VibeVideoBench: Evaluating Multimodal Agents on Code-Driven Video Generation 91.2
- day Daily PapersPapers The Trinity:Capability-Driven Recursive Self-Improvement for Multimodal Agents 90.0
- day Daily PapersPapers Can Test-Time Memory Evolution Outperform Test-Time Training for Scientific Discovery? 94.4
- day Daily PapersPapers ChronoReplay: One Answer Interface Is Not Enough for Streaming Spatial Intelligence 95.2
- day Daily PapersPapers Multiscale Policy Optimization for Long-Horizon LLM Agents 99.1
- day Daily PapersPapers HABIT-Bench: Evaluating Habit Induction from Longitudinal Weak Evidence in Agent Memory 91.3
- day Daily PapersPapers Rollback: Experience Backtracking in World Models for Policy Improvement 90.3
- day Daily PapersPapers Memory Tax: Dissecting the Net Value of Agent Memory 91.5
- day Daily PapersPapers PDRVLA: A Vision-Language-Action Model with Physical Dynamics Representations 96.0
- day Daily PapersPapers Hy-Nomas: Towards Free-form Interactive World Generation 93.6
Tuesday 27 October 20266 events
- day Daily PapersPapers Work Agents: Systems, Capabilities, and Optimization 93.7
- day Daily PapersPapers Trajectory2Gym: Decision-Grounded Compositional Interaction Synthesis for Tool-Use Agents 94.8
- day Daily PapersPapers InteractiveWorld: A Verifiable Human-Centric Environment for Building Better Interactive MLLM Assistants 94.6
- day Daily PapersPapers StreamVibe: Proactive Video Agents for Evolving User Intent 91.3
- day Daily PapersPapers Trial by Trace: Benchmarking AI Agent Harnesses for Reliability and Failure Attribution 97.6
- day Daily PapersPapers DynaFlow: Learning Free-Form Multi-Agent Orchestration 92.1
Monday 26 October 20262 events
Friday 23 October 20265 events
- day Daily PapersPapers WeVisOne-VL: Unified Visual Perception from Objects to Pixels 98.3
- day Daily PapersPapers IQuest-Q1: Advancing Foundation Capabilities for Agentic CLI Systems 92.7
- day Daily PapersPapers Making MLLM Latents Matter: Factor-Aware Predictive Learning for Cinematic Video Generation 94.8
- day Daily PapersPapers Deep Search in Real-World Web Environments 97.5
- day Daily PapersPapers Editing Images into Reusable Layers via Compositional Edit-Prior Distillation 93.8
Thursday 22 October 20268 events
- day Daily PapersPapers Cache Engineering for Agents 96.5
- day Daily PapersPapers SpatialScout: Can VLM Agents Actively Explore and Map 3D Scenes? 97.0
- day Daily PapersPapers Right Screen, Wrong Transition: World Models as Verifiers for GUI Agents 97.5
- day Daily PapersPapers Spectral-Spatial Interpretation 99.9
- day Daily PapersPapers Looking Ahead: Modeling Future Evolution in Autoregressive Video Generation 97.0
- day Daily PapersPapers StreamEval: Evaluating Interactive Streaming Video Generation Models 99.7
- day Daily PapersPapers DONIC: Generalist Dexterous Bimanual Tracking Control from Human Demonstrations 96.6
- day Daily PapersPapers Agent World Model in the Wild: Computer-Use Agent Environment Synthesis 92.5
Wednesday 21 October 20266 events
- day Daily PapersPapers CoEvo-RSI: When Harnesses Evolve, Which Models Should Follow? 94.4
- day Daily PapersPapers Ropedia W0: Scaling Loco-Manipulation World Models across Embodiments with Human Experience 95.9
- day Daily PapersPapers PAR: Progress-Aligned Recurrence for Length Generalization in State Tracking 96.7
- day Daily PapersPapers Focused Omni-Modal GUI Agents 94.9
- day Daily PapersPapers S-Agent 2.0: Spatial Reasoning with a General Coding Agent 93.2
- day Daily PapersPapers Matrix-Game 4.0: Harnessing Video Models for Real-Time Playable Game Worlds 97.6
Tuesday 20 October 20268 events
- day Daily PapersPapers Scaling Parameter-Efficient Fine-Tuning for Brain Encoding 98.1
- day Daily PapersPapers OpenVLHarness: Real World Visual Agentic Tool-Use with Multimodal Memory 94.4
- day Daily PapersPapers Learning from Fleet Experience: A Collective Learning Paradigm for Robots 95.0
- day Daily PapersPapers MemT-1.0: Towards Memory-Native Evolution 95.3
- day Daily PapersPapers ScaleNav: Scalable Internet Video Pretraining for Language-Conditioned Local Navigation 91.4
- day Daily PapersPapers EgoXperience: Learning World-Grounded Egocentric Representations from Human Experience 97.5
- day Daily PapersPapers Holi-World: Building Holistic World Intelligence from Human-Ego Experience 97.0
- day Daily PapersPapers SpecMRL: Redesign Matryoshka Representation Learning within Parametric Spectrum 91.0
Monday 19 October 20269 events
- day Daily PapersPapers BizBench: Unveiling Hidden Challenges in Deploying Long-Horizon Agents for Real-World Business 99.6
- day Daily PapersPapers HexaShell: A Thin Harness for Exploring the Limits of VLM Agents as Robot Coding Agents 94.5
- day Daily PapersPapers LEV: Thinking Fast and Deep with Looped Decision Models 93.1
- day Daily PapersPapers MOSS-Image Technical Report 92.7
- day Daily PapersPapers Has GPT-6-Astra Achieved Embodied Intelligence? 99.5
- day Daily PapersPapers Pack Light, CarryOn: Building Object-Oriented Context for Long-Horizon Agents 94.5
- day Daily PapersPapers Into the Unknown: Benchmarking AI agents on open scientific research problems 96.5
- day Daily PapersPapers Learning to Think and Explore in 3D World 95.3
- day Daily PapersPapers Speculative Sampling in Interactive Video Generation 90.7
Friday 16 October 20267 events
- day Daily PapersPapers InfiniSplat v2: Analyzing and Improving Feed-Forward 3DGS from Any Views 94.8
- day Daily PapersPapers MAI-Gym: An Open All-in-One Platform for GUI Agent Evaluation and RL Training across Mobile and Computer Environments 95.8
- day Daily PapersPapers Waypoint-OPD: Transferring RL-Induced Policy Shifts via Gated On-Policy Distillation 97.8
- day Daily PapersPapers MJev-Spatial: System One Spatial Intelligence via Native Attention Matching 99.3
- day Daily PapersPapers Speculative Forcing for Efficient Autoregressive Video Generation 91.8
- day Daily PapersPapers Self-Evolving Agent Harness 92.4
- day Daily PapersPapers OpenGCUA: Toward a Fully Open Stack for Generalist Computer Use 92.7
Thursday 15 October 20264 events
- day Daily PapersPapers LatentLoop: Scaling Looped MoE Models with Asymmetric Compute Allocation 90.0
- day Daily PapersPapers Beyond Domain-Routed Supervision: Cross-Teacher Guarding for Multi-Teacher On-Policy Distillation 91.8
- day Daily PapersPapers Player-1: Learning to Play from Synthetic Experience 99.1
- day Daily PapersPapers Any Time, Any Space: A World-State-Centric Framework for Agentic Video Generation 99.1
- Hugging Face, Daily Papers. Title and upvotes of each paper in the top tenth of the twelve-week baseline, linked to the paper. titles and counts only.