Daily Papers of 2025-04-07

  1. Multi-SWE-bench: A Multilingual Benchmark for Issue Resolving 43 upvotes, #1 of 2025-04-07
  2. MegaMath: Pushing the Limits of Open Math Corpora 29 upvotes, #2 of 2025-04-07
  3. Agentic Knowledgeable Self-awareness 27 upvotes, #3 of 2025-04-07
  4. VARGPT-v1.1: Improve Visual Autoregressive Large Unified Model via Iterative Instruction Tuning and Reinforcement Learning 18 upvotes, #4 of 2025-04-07
  5. SynWorld: Virtual Scenario Synthesis for Agentic Action Knowledge Refinement 17 upvotes, #5 of 2025-04-07
  6. TransMamba: Flexibly Switching between Transformer and Mamba 16 upvotes, #6 of 2025-04-07
  7. ShieldAgent: Shielding Agents via Verifiable Safety Policy Reasoning 15 upvotes, #7 of 2025-04-07
  8. APIGen-MT: Agentic Pipeline for Multi-Turn Data Generation via Simulated Agent-Human Interplay 15 upvotes, #7 of 2025-04-07
  9. MME-Unify: A Comprehensive Benchmark for Unified Multimodal Understanding and Generation Models 13 upvotes, #9 of 2025-04-07
  10. HumanDreamer-X: Photorealistic Single-image Human Avatars Reconstruction via Gaussian Restoration 10 upvotes, #10 of 2025-04-07
  11. Comprehensive Relighting: Generalizable and Consistent Monocular Human Relighting and Harmonization 9 upvotes, #11 of 2025-04-07
  12. Slow-Fast Architecture for Video Multi-Modal Large Language Models 8 upvotes, #12 of 2025-04-07
  13. MedSAM2: Segment Anything in 3D Medical Images and Videos 8 upvotes, #12 of 2025-04-07
  14. BEATS: Bias Evaluation and Assessment Test Suite for Large Language Models 6 upvotes, #14 of 2025-04-07
  15. EvMic: Event-based Non-contact sound recovery from effective spatial-temporal modeling 5 upvotes, #15 of 2025-04-07
  16. SPF-Portrait: Towards Pure Portrait Customization with Semantic Pollution-Free Fine-tuning 4 upvotes, #16 of 2025-04-07
  17. Delineate Anything: Resolution-Agnostic Field Boundary Delineation on Satellite Imagery 4 upvotes, #16 of 2025-04-07
  18. Real-is-Sim: Bridging the Sim-to-Real Gap with a Dynamic Digital Twin for Real-World Robot Policy Evaluation 4 upvotes, #16 of 2025-04-07

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.