Daily Papers of 2025-07-10

  1. 4KAgent: Agentic Any Image to 4K Super-Resolution 81 upvotes, #1 of 2025-07-10
  2. Skywork-R1V3 Technical Report 63 upvotes, #2 of 2025-07-10
  3. MIRIX: Multi-Agent Memory System for LLM-Based Agents 55 upvotes, #3 of 2025-07-10
  4. Go to Zero: Towards Zero-shot Motion Generation with Million-scale Data 51 upvotes, #4 of 2025-07-10
  5. Perception-Aware Policy Optimization for Multimodal Reasoning 42 upvotes, #5 of 2025-07-10
  6. Rethinking Verification for LLM Code Generation: From Generation to Testing 28 upvotes, #6 of 2025-07-10
  7. AutoTriton: Automatic Triton Programming with Reinforcement Learning in LLMs 26 upvotes, #7 of 2025-07-10
  8. First Return, Entropy-Eliciting Explore 23 upvotes, #8 of 2025-07-10
  9. A Systematic Analysis of Hybrid Linear Attention 22 upvotes, #9 of 2025-07-10
  10. Towards Solving More Challenging IMO Problems via Decoupled Reasoning and Proving 15 upvotes, #10 of 2025-07-10
  11. A Survey on Vision-Language-Action Models for Autonomous Driving 13 upvotes, #11 of 2025-07-10
  12. Decoder-Hybrid-Decoder Architecture for Efficient Reasoning with Long Generation 9 upvotes, #12 of 2025-07-10
  13. DiffSpectra: Molecular Structure Elucidation from Spectra using Diffusion Models 7 upvotes, #13 of 2025-07-10
  14. PERK: Long-Context Reasoning as Parameter-Efficient Test-Time Learning 6 upvotes, #14 of 2025-07-10
  15. FlexOlmo: Open Language Models for Flexible Data Use 5 upvotes, #15 of 2025-07-10
  16. ModelCitizens: Representing Community Voices in Online Safety 4 upvotes, #16 of 2025-07-10
  17. Evaluating the Critical Risks of Amazon's Nova Premier under the Frontier Model Safety Framework 4 upvotes, #16 of 2025-07-10
  18. Video-RTS: Rethinking Reinforcement Learning and Test-Time Scaling for Efficient and Enhanced Video Reasoning 4 upvotes, #16 of 2025-07-10
  19. SRT-H: A Hierarchical Framework for Autonomous Surgery via Language Conditioned Imitation Learning 3 upvotes, #19 of 2025-07-10
  20. AdamMeme: Adaptively Probe the Reasoning Capacity of Multimodal Large Language Models on Harmfulness 1 upvotes, #20 of 2025-07-10
  21. RabakBench: Scaling Human Annotations to Construct Localized Multilingual Safety Benchmarks for Low-Resource Languages 1 upvotes, #20 of 2025-07-10
  22. Towards Multimodal Understanding via Stable Diffusion as a Task-Aware Feature Extractor 1 upvotes, #20 of 2025-07-10

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.