Daily Papers of 2026-10-23

  1. Reading, Writing, Sharing, and Interacting with the World through Video 295 upvotes, #1 of 2026-10-23
  2. WeVisOne-VL: Unified Visual Perception from Objects to Pixels 259 upvotes, #2 of 2026-10-23
  3. Making MLLM Latents Matter: Factor-Aware Predictive Learning for Cinematic Video Generation 204 upvotes, #3 of 2026-10-23
  4. Editing Images into Reusable Layers via Compositional Edit-Prior Distillation 196 upvotes, #4 of 2026-10-23
  5. Deep Search in Real-World Web Environments 189 upvotes, #5 of 2026-10-23
  6. IQuest-Q1: Advancing Foundation Capabilities for Agentic CLI Systems 106 upvotes, #6 of 2026-10-23
  7. Toward Recursive Self-Improvement in Physical AI 76 upvotes, #7 of 2026-10-23
  8. Deep Fusion Memory: A Chunk-Level Parametric Memory for Large Language Models 61 upvotes, #8 of 2026-10-23
  9. LaLa-World: Scaling Latent World Models with Natural Language Actions 58 upvotes, #9 of 2026-10-23
  10. Self-Distilling Future Video Representations for World Action Models 52 upvotes, #10 of 2026-10-23
  11. Meta Expert: Cross-Layer Expert Sharing for Storage- and Retrieval-Efficient MoE 47 upvotes, #11 of 2026-10-23
  12. What Generation Knows: Unlocking Fine-Grained Understanding in Unified Multimodal Models 45 upvotes, #12 of 2026-10-23
  13. Code2Video-Compass: A Comprehensive Benchmark for General-Purpose Code-Based Video Generation across T2V, I2V, and V2V 45 upvotes, #12 of 2026-10-23
  14. Is Complex Agentic Memory Always Needed? Naive RAG Is Stronger Than We Thought 38 upvotes, #14 of 2026-10-23
  15. Policy-Mask: Budget-Aware Adaptation of Diffusion Features to Discriminative Tasks 36 upvotes, #15 of 2026-10-23
  16. Heartbeat Thinking: Speculative Reasoning and Tool Execution While Listening in Realtime Voice Agents 35 upvotes, #16 of 2026-10-23
  17. FilmFlow: Agentic System for 3D Virtual Film Cinematography 35 upvotes, #16 of 2026-10-23
  18. RLSplat: Resource-Linear Budget Control for Feed-forward 3D Gaussian Splatting 33 upvotes, #18 of 2026-10-23
  19. SCOPE: Compiling Natural-Language Policies into Neurosymbolic Predicate Programs 32 upvotes, #19 of 2026-10-23
  20. Beyond Watching and Searching: Benchmarking Agents for Video-centered Deep Research Reports 32 upvotes, #19 of 2026-10-23
  21. RouteWeaver: Weaving Mode Selection and Execution into Unified LLM Routing 31 upvotes, #21 of 2026-10-23
  22. Cola2: Co-Adaptive Hierarchical Language Modeling with Continuous Semantic Compression and Balanced Discrete Generation 28 upvotes, #22 of 2026-10-23
  23. Rethinking Sequence Compression with Test-time Regression 28 upvotes, #22 of 2026-10-23
  24. Agent Mosaic: Recognizing Confidentiality Leaks in Agentic LLM Systems 27 upvotes, #24 of 2026-10-23
  25. AgentVQA: A Unified Benchmark for Agentic Visual Understanding 25 upvotes, #25 of 2026-10-23
  26. EvalResearchBench: Can AI Agents Build Their Own Feedback for Recursive Self-Improvement? 24 upvotes, #26 of 2026-10-23
  27. Diffusion Language Models Change Speed Across Tasks and Languages 24 upvotes, #26 of 2026-10-23
  28. Verus-Insight: Towards Explainable Artifact Detection in AI-Generated Videos 23 upvotes, #28 of 2026-10-23
  29. Inherited, Not Invented: Tracing the Provenance of Wait in Reasoning Models 23 upvotes, #28 of 2026-10-23
  30. AnyGameRenderer: Entity-Consistent Generative Rendering Across Games and an Entity-Level Benchmark 22 upvotes, #30 of 2026-10-23
  31. F2G-Pose: Geometry-Aware Foundation Feature Lifting for Direct RGB-D Category-Level Object Pose Estimation 22 upvotes, #30 of 2026-10-23
  32. RTAformer: Relation-Transition-Aware Transformer for Video Scene Graph Generation 21 upvotes, #32 of 2026-10-23
  33. Different Tasks, Different Timesteps: Temporal Task-Aware Quantization for Diffusion Language Models 21 upvotes, #32 of 2026-10-23
  34. Foundation4D: Towards a unified perception and reconstruction model for autonomous vehicles 20 upvotes, #34 of 2026-10-23
  35. MolLean: A Process-Verifiable Language for Chemical Reasoning 19 upvotes, #35 of 2026-10-23
  36. SEAM: Spectral Embedding Alignment and Merging for Low-Resource TTS 18 upvotes, #36 of 2026-10-23
  37. RIDAR: Safeguarding Research Integrity in Autonomous Research Agents via Automated Detection and Runtime Intervention 17 upvotes, #37 of 2026-10-23
  38. MambaAct: Efficient Mamba Action Experts for Flow-Matching Vision-Language-Action Models 16 upvotes, #38 of 2026-10-23
  39. BrickWright: Agentic Creation of Physically Feasible Brick Builds 16 upvotes, #38 of 2026-10-23
  40. TILDE: Teacher-in-the-Loop Distillation from Embodied Foundation Models 14 upvotes, #40 of 2026-10-23
  41. SplatLab: Autonomous Scientific Discovery for 3DGS Research 13 upvotes, #41 of 2026-10-23
  42. What Makes a Good Unmasking Policy? A Controlled Study of Learned Unmasking in Diffusion Language Models 13 upvotes, #41 of 2026-10-23
  43. The LLM-Attacker: A Unified Red-Team Framework for Privacy Evaluation of Split and Distributed LLM Systems 12 upvotes, #43 of 2026-10-23
  44. Skeleton-Grounded Latent Action Model for Robot World Models 12 upvotes, #43 of 2026-10-23
  45. IF-MAP: Influence-Function-Inspired Agent Prioritization in Multi-Agent Systems 11 upvotes, #45 of 2026-10-23
  46. HyperDrone: Simulation-to-Reality Transfer at Millions of Frames per Second 11 upvotes, #45 of 2026-10-23
  47. Realism VS Accuracy: Event Sequence Forecasting from a Generative Modeling Perspective 10 upvotes, #47 of 2026-10-23
  48. Who Takes the Lead? Model Ability and Task-Conditioned Collaboration with Humans 10 upvotes, #47 of 2026-10-23
  49. Bridging Exploration and Persona: Information-Directed Dueling for Test-Time Agent Personalization 9 upvotes, #49 of 2026-10-23
  50. TARSphere: A Robot-Oriented Full-Stack Framework for Long-Horizon Embodied Agents in Evolving Physical and Social Environments 8 upvotes, #50 of 2026-10-23

Data: hysts-bot-data/daily-papers-stats and the Daily Papers API. Open data: tardellirs/paper-pulse-data. Sister project: Model Pulse, the download history of every model on the Hub.