Daily Papers of 2026-06-30

  1. Orca: The World is in Your Mind 304 upvotes, #1 of 2026-06-30
  2. Agentic Abstention: Do Agents Know When to Stop Instead of Act? 146 upvotes, #2 of 2026-06-30
  3. Scaling the Horizon, Not the Parameters: Reaching Trillion-Parameter Performance with a 35B Agent 94 upvotes, #3 of 2026-06-30
  4. LiveEdit: Towards Real-Time Diffusion-Based Streaming Video Editing 82 upvotes, #4 of 2026-06-30
  5. ReFreeKV: Towards Threshold-Free KV Cache Compression 48 upvotes, #5 of 2026-06-30
  6. TUA-Bench: A Benchmark for General-Purpose Terminal-Use Agents 47 upvotes, #6 of 2026-06-30
  7. Trimming the Long-Tail of Visual World Modeling Evaluation 42 upvotes, #7 of 2026-06-30
  8. Beyond IID: How General Are Tabular Foundation Models, Really? 42 upvotes, #7 of 2026-06-30
  9. AsyncOPD: How Stale Can On-Policy Distillation Be? 30 upvotes, #9 of 2026-06-30
  10. Bridging VideoQA and Video-Guided Agentic Tasks via Generalized Keyframe Extraction 28 upvotes, #10 of 2026-06-30
  11. Video-MME-Logical: A Controlled Diagnostic Benchmark for Video Temporal-Logical Reasoning 25 upvotes, #11 of 2026-06-30
  12. One-Step Gradient Delay is Not a Barrier for Large-Scale Asynchronous Pipeline Parallel LLM Pretraining 24 upvotes, #12 of 2026-06-30
  13. One Model, Many Latencies: Universal Speech Enhancement for Diverse Real-Time Applications 22 upvotes, #13 of 2026-06-30
  14. OSWorld2.0: Benchmarking Computer Use Agents on Long-Horizon Real-World Tasks 21 upvotes, #14 of 2026-06-30
  15. Monte Carlo Energy Aggregation for Mobile 3D Gaussian Splatting 21 upvotes, #14 of 2026-06-30
  16. TACO: Tool-Augmented Credit Optimization for Agentic Tool Use 21 upvotes, #14 of 2026-06-30
  17. GUICrafter: Weakly-Supervised GUI Agent Leveraging Massive Unannotated Screenshots 16 upvotes, #17 of 2026-06-30
  18. DreamForge-World 0.1 Preview: A Low-Compute Real-Time Controllable World Model 16 upvotes, #17 of 2026-06-30
  19. Nemotron-Labs-Diffusion-Image: Advancing Masked Discrete Diffusion for High-Resolution Image Synthesis 14 upvotes, #19 of 2026-06-30
  20. SWE-Together: Evaluating Coding Agents in Interactive User Sessions 14 upvotes, #19 of 2026-06-30
  21. Interleaved Speech Language Models Latently Work In Text 13 upvotes, #21 of 2026-06-30
  22. How Good Can Linear Models Be for Time-Series Forecasting? 13 upvotes, #21 of 2026-06-30
  23. TheoremGraph: Bridging Formal and Informal Mathematics 12 upvotes, #23 of 2026-06-30
  24. SAM2Matting: Generalized Image and Video Matting 12 upvotes, #23 of 2026-06-30
  25. MIMFlow: Integrating Masked Image Modeling with Normalizing Flows for End-to-End Image Generation 10 upvotes, #25 of 2026-06-30
  26. Cognitive Episodes in LLM Reasoning Traces Enable Interpretable Human Item Difficulty Prediction 9 upvotes, #26 of 2026-06-30
  27. PolicyGuard: A Dialogue-Grounded Sub-Agent Verifier for Policy Adherence in LLM Agents 8 upvotes, #27 of 2026-06-30
  28. MirrorPPR: Exemplar-Based Portrait Photo Retouching 8 upvotes, #27 of 2026-06-30
  29. Walking in the Implicit: Interactive World Exploration via Neural Scene Representation 8 upvotes, #27 of 2026-06-30
  30. One Forward Beats Two: InnerZoom for Accurate and Efficient GUI Grounding 8 upvotes, #27 of 2026-06-30
  31. ReasoningLens: Hierarchical Visualization and Diagnostic Auditing for Large Reasoning Models 7 upvotes, #31 of 2026-06-30
  32. Beyond Drug Discovery: The Nanotechnology Molecular Optimization (NMO) Benchmark 7 upvotes, #31 of 2026-06-30
  33. The Surprising Effectiveness of Video Diffusion Models for Hand Motion Reconstruction 7 upvotes, #31 of 2026-06-30
  34. RocketSmith: Agentic Additive Manufacturing of High-Powered Rockets 6 upvotes, #34 of 2026-06-30
  35. Focusing on What Matters: Saliency-Harnessing Accurate Routing for Diffusion MoE 6 upvotes, #34 of 2026-06-30
  36. Delayed Verification Destabilizes Multi-Agent LLM Belief: Instability Thresholds and Optimal Corrector Placement 6 upvotes, #34 of 2026-06-30
  37. Drop-Then-Recovery: How Redundant Are Vision-Language-Action Models? 6 upvotes, #34 of 2026-06-30
  38. PoseShield: Neural Collision Fields for Human Self-Collision Resolution 6 upvotes, #34 of 2026-06-30
  39. SafePyramid: A Hierarchical Benchmark for In-context Policy Guardrailing 6 upvotes, #34 of 2026-06-30
  40. Mind the Heads: Topological Representation Alignment for Multimodal LLMs 5 upvotes, #40 of 2026-06-30
  41. ZooClaw-FashionSigLIP2: Distilled Fine-tuning for Robust Fashion Retrieval 5 upvotes, #40 of 2026-06-30
  42. Learning Transferable Dynamics Priors from Action to World Modeling 5 upvotes, #40 of 2026-06-30
  43. LLM Program Optimization via Retrieval Augmented Search 4 upvotes, #43 of 2026-06-30
  44. Large-Scale Tunnel Air-Ground Collaboration With FLISP: Fast LiDAR-IMU Synchronized Path Planner 4 upvotes, #43 of 2026-06-30
  45. A Gravitational Interpretation of Fine-Tuning Reversion 4 upvotes, #43 of 2026-06-30
  46. One Scene, Two Depths: Probing Geometric Ambiguity in Monocular Foundation Models 4 upvotes, #43 of 2026-06-30
  47. Geometric Stability of Neural Population Codes: Regional Variation, Behavioral Relevance, and Circuit Dependence 4 upvotes, #43 of 2026-06-30
  48. Illuminating Unified Multimodal Model for Free-form Interleaved Text-Image Generation 4 upvotes, #43 of 2026-06-30
  49. RaysUp: Ultra-light Universal Feature Upsampling via Geometry-Aware Ray Representation 3 upvotes, #49 of 2026-06-30

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.