Daily Papers of 2026-03-06

  1. MOOSE-Star: Unlocking Tractable Training for Scientific Discovery by Breaking the Complexity Barrier 86 upvotes, #1 of 2026-03-06
  2. SkillNet: Create, Evaluate, and Connect AI Skills 79 upvotes, #2 of 2026-03-06
  3. DARE: Aligning LLM Agents with the R Statistical Ecosystem via Distribution-Aware Retrieval 47 upvotes, #3 of 2026-03-06
  4. AgentVista: Evaluating Multimodal Agents in Ultra-Challenging Realistic Visual Scenarios 40 upvotes, #4 of 2026-03-06
  5. RoboPocket: Improve Robot Policies Instantly with Your Phone 31 upvotes, #5 of 2026-03-06
  6. HiFi-Inpaint: Towards High-Fidelity Reference-Based Inpainting for Generating Detail-Preserving Human-Product Images 28 upvotes, #6 of 2026-03-06
  7. Large Multimodal Models as General In-Context Classifiers 22 upvotes, #7 of 2026-03-06
  8. MASQuant: Modality-Aware Smoothing Quantization for Multimodal Large Language Models 20 upvotes, #8 of 2026-03-06
  9. Interactive Benchmarks 18 upvotes, #9 of 2026-03-06
  10. SageBwd: A Trainable Low-bit Attention 17 upvotes, #10 of 2026-03-06
  11. DreamWorld: Unified World Modeling in Video Generation 16 upvotes, #11 of 2026-03-06
  12. Timer-S1: A Billion-Scale Time Series Foundation Model with Serial Scaling 16 upvotes, #11 of 2026-03-06
  13. RealWonder: Real-Time Physical Action-Conditioned Video Generation 11 upvotes, #13 of 2026-03-06
  14. Locality-Attending Vision Transformer 7 upvotes, #14 of 2026-03-06
  15. UltraDexGrasp: Learning Universal Dexterous Grasping for Bimanual Robots with Synthetic Data 7 upvotes, #14 of 2026-03-06
  16. KARL: Knowledge Agents via Reinforcement Learning 6 upvotes, #16 of 2026-03-06
  17. On-Policy Self-Distillation for Reasoning Compression 5 upvotes, #17 of 2026-03-06
  18. Mozi: Governed Autonomy for Drug Discovery LLM Agents 4 upvotes, #18 of 2026-03-06
  19. Towards Multimodal Lifelong Understanding: A Dataset and Agentic Baseline 4 upvotes, #18 of 2026-03-06
  20. Truncated Step-Level Sampling with Process Rewards for Retrieval-Augmented Reasoning 3 upvotes, #20 of 2026-03-06
  21. STMI: Segmentation-Guided Token Modulation with Cross-Modal Hypergraph Interaction for Multi-Modal Object Re-Identification 3 upvotes, #20 of 2026-03-06
  22. Latent Particle World Models: Self-supervised Object-centric Stochastic Dynamics Modeling 3 upvotes, #20 of 2026-03-06
  23. Distribution-Conditioned Transport 3 upvotes, #20 of 2026-03-06
  24. Lightweight Visual Reasoning for Socially-Aware Robots 0 upvotes, #24 of 2026-03-06

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.