Daily Papers of 2026-03-18

  1. Demystifing Video Reasoning 356 upvotes, #1 of 2026-03-18
  2. InCoder-32B: Code Foundation Model for Industrial Scenarios 297 upvotes, #2 of 2026-03-18
  3. SocialOmni: Benchmarking Audio-Visual Social Interactivity in Omni Models 242 upvotes, #3 of 2026-03-18
  4. MiroThinker-1.7 & H1: Towards Heavy-Duty Research Agents via Verification 179 upvotes, #4 of 2026-03-18
  5. Qianfan-OCR: A Unified End-to-End Model for Document Intelligence 145 upvotes, #5 of 2026-03-18
  6. Thinking in Uncertainty: Mitigating Hallucinations in MLRMs with Latent Entropy-Aware Decoding 93 upvotes, #6 of 2026-03-18
  7. Kinema4D: Kinematic 4D World Modeling for Spatiotemporal Embodied Simulation 68 upvotes, #7 of 2026-03-18
  8. WorldCam: Interactive Autoregressive 3D Gaming Worlds with Camera Pose as a Unifying Geometric Representation 58 upvotes, #8 of 2026-03-18
  9. TRUST-SQL: Tool-Integrated Multi-Turn Reinforcement Learning for Text-to-SQL over Unknown Schemas 56 upvotes, #9 of 2026-03-18
  10. Online Experiential Learning for Language Models 55 upvotes, #10 of 2026-03-18
  11. FinToolBench: Evaluating LLM Agents for Real-World Financial Tool Use 43 upvotes, #11 of 2026-03-18
  12. WiT: Waypoint Diffusion Transformers via Trajectory Conflict Navigation 35 upvotes, #12 of 2026-03-18
  13. GradMem: Learning to Write Context into Memory with Test-Time Gradient Descent 33 upvotes, #13 of 2026-03-18
  14. Rethinking UMM Visual Generation: Masked Modeling for Efficient Image-Only Pre-training 31 upvotes, #14 of 2026-03-18
  15. MEMO: Memory-Augmented Model Context Optimization for Robust Multi-Turn Multi-Agent LLM Games 24 upvotes, #15 of 2026-03-18
  16. AgentProcessBench: Diagnosing Step-Level Process Quality in Tool-Using Agents 22 upvotes, #16 of 2026-03-18
  17. Omnilingual MT: Machine Translation for 1,600 Languages 19 upvotes, #17 of 2026-03-18
  18. SWE-Skills-Bench: Do Agent Skills Actually Help in Real-World Software Engineering? 18 upvotes, #18 of 2026-03-18
  19. SegviGen: Repurposing 3D Generative Model for Part Segmentation 18 upvotes, #18 of 2026-03-18
  20. Efficient Reasoning on the Edge 17 upvotes, #20 of 2026-03-18
  21. SparkVSR: Interactive Video Super-Resolution via Sparse Keyframe Propagation 15 upvotes, #21 of 2026-03-18
  22. Semi-Autonomous Formalization of the Vlasov-Maxwell-Landau Equilibrium 14 upvotes, #22 of 2026-03-18
  23. One-Eval: An Agentic System for Automated and Traceable LLM Evaluation 11 upvotes, #23 of 2026-03-18
  24. Recursive Language Models Meet Uncertainty: The Surprising Effectiveness of Self-Reflective Program Search for Long Context 11 upvotes, #23 of 2026-03-18
  25. Reliable Reasoning in SVG-LLMs via Multi-Task Multi-Reward Reinforcement Learning 10 upvotes, #25 of 2026-03-18
  26. M^3: Dense Matching Meets Multi-View Foundation Models for Monocular Gaussian Splatting SLAM 10 upvotes, #25 of 2026-03-18
  27. FlashSampling: Fast and Memory-Efficient Exact Sampling 8 upvotes, #27 of 2026-03-18
  28. MolmoB0T: Large-Scale Simulation Enables Zero-Shot Manipulation 8 upvotes, #27 of 2026-03-18
  29. SK-Adapter: Skeleton-Based Structural Control for Native 3D Generation 6 upvotes, #29 of 2026-03-18
  30. From Passive Observer to Active Critic: Reinforcement Learning Elicits Process Reasoning for Robotic Manipulation 6 upvotes, #29 of 2026-03-18
  31. Residual Stream Duality in Modern Transformer Architectures 3 upvotes, #31 of 2026-03-18
  32. V-Co: A Closer Look at Visual Representation Alignment via Co-Denoising 3 upvotes, #31 of 2026-03-18
  33. Sparking Scientific Creativity via LLM-Driven Interdisciplinary Inspiration 2 upvotes, #33 of 2026-03-18
  34. SuperLocalMemory V3: Information-Geometric Foundations for Zero-LLM Enterprise Agent Memory 2 upvotes, #33 of 2026-03-18
  35. VAREX: A Benchmark for Multi-Modal Structured Extraction from Documents 2 upvotes, #33 of 2026-03-18
  36. CCTU: A Benchmark for Tool Use under Complex Constraints 2 upvotes, #33 of 2026-03-18
  37. I Know What I Don't Know: Latent Posterior Factor Models for Multi-Evidence Probabilistic Reasoning 2 upvotes, #33 of 2026-03-18
  38. Theoretical Foundations of Latent Posterior Factors: Formal Guarantees for Multi-Evidence Reasoning 2 upvotes, #33 of 2026-03-18
  39. ViT-AdaLA: Adapting Vision Transformers with Linear Attention 2 upvotes, #33 of 2026-03-18
  40. Mixture of Style Experts for Diverse Image Stylization 2 upvotes, #33 of 2026-03-18
  41. Anticipatory Planning for Multimodal AI Agents 2 upvotes, #33 of 2026-03-18
  42. Test-Time Strategies for More Efficient and Accurate Agentic RAG 1 upvotes, #42 of 2026-03-18
  43. ECG-Reasoning-Benchmark: A Benchmark for Evaluating Clinical Reasoning Capabilities in ECG Interpretation 1 upvotes, #42 of 2026-03-18
  44. Chain-of-Trajectories: Unlocking the Intrinsic Generative Optimality of Diffusion Models via Graph-Theoretic Planning 1 upvotes, #42 of 2026-03-18
  45. ARISE: Agent Reasoning with Intrinsic Skill Evolution in Hierarchical Reinforcement Learning 1 upvotes, #42 of 2026-03-18
  46. MDM-Prime-v2: Binary Encoding and Index Shuffling Enable Compute-optimal Scaling of Diffusion Language Models 1 upvotes, #42 of 2026-03-18
  47. OneWorld: Taming Scene Generation with 3D Unified Representation Autoencoder 1 upvotes, #42 of 2026-03-18
  48. Polyglot-Lion: Efficient Multilingual ASR for Singapore via Balanced Fine-Tuning of Qwen3-ASR 1 upvotes, #42 of 2026-03-18
  49. Learning Human-Object Interaction for 3D Human Pose Estimation from LiDAR Point Clouds 1 upvotes, #42 of 2026-03-18
  50. BERTology of Molecular Property Prediction 0 upvotes, #50 of 2026-03-18
  51. Measuring Primitive Accumulation: An Information-Theoretic Approach to Capitalist Enclosure in PIK2, Indonesia 0 upvotes, #50 of 2026-03-18
  52. HistoAtlas: A Pan-Cancer Morphology Atlas Linking Histomics to Molecular Programs and Clinical Outcomes 0 upvotes, #50 of 2026-03-18

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.