Daily Papers of 2025-11-18

  1. MiroThinker: Pushing the Performance Boundaries of Open-Source Research Agents via Model, Context, and Interactive Scaling 151 upvotes, #1 of 2025-11-18
  2. Souper-Model: How Simple Arithmetic Unlocks State-of-the-Art LLM Performance 130 upvotes, #2 of 2025-11-18
  3. P1: Mastering Physics Olympiads with Reinforcement Learning 128 upvotes, #3 of 2025-11-18
  4. Uni-MoE-2.0-Omni: Scaling Language-Centric Omnimodal Large Model with Advanced MoE, Training and Data 99 upvotes, #4 of 2025-11-18
  5. Part-X-MLLM: Part-aware 3D Multimodal Large Language Model 70 upvotes, #5 of 2025-11-18
  6. MMaDA-Parallel: Multimodal Large Diffusion Language Models for Thinking-Aware Editing and Generation 64 upvotes, #6 of 2025-11-18
  7. Back to Basics: Let Denoising Generative Models Denoise 55 upvotes, #7 of 2025-11-18
  8. GroupRank: A Groupwise Reranking Paradigm Driven by Reinforcement Learning 52 upvotes, #8 of 2025-11-18
  9. PhysX-Anything: Simulation-Ready Physical 3D Assets from Single Image 49 upvotes, #9 of 2025-11-18
  10. TiViBench: Benchmarking Think-in-Video Reasoning for Video Generative Models 42 upvotes, #10 of 2025-11-18
  11. Evolve the Method, Not the Prompts: Evolutionary Synthesis of Jailbreak Attacks on LLMs 35 upvotes, #11 of 2025-11-18
  12. UFO^3: Weaving the Digital Agent Galaxy 17 upvotes, #12 of 2025-11-18
  13. NORA-1.5: A Vision-Language-Action Model Trained using World Model- and Action-based Preference Rewards 11 upvotes, #13 of 2025-11-18
  14. WebCoach: Self-Evolving Web Agents with Cross-Session Memory Guidance 9 upvotes, #14 of 2025-11-18
  15. OlmoEarth: Stable Latent Image Modeling for Multimodal Earth Observation 9 upvotes, #14 of 2025-11-18
  16. UnSAMv2: Self-Supervised Learning Enables Segment Anything at Any Granularity 9 upvotes, #14 of 2025-11-18
  17. Genomic Next-Token Predictors are In-Context Learners 6 upvotes, #17 of 2025-11-18
  18. Live-SWE-agent: Can Software Engineering Agents Self-Evolve on the Fly? 6 upvotes, #17 of 2025-11-18
  19. Assessing LLMs for Serendipity Discovery in Knowledge Graphs: A Case for Drug Repurposing 5 upvotes, #19 of 2025-11-18
  20. Instella: Fully Open Language Models with Stellar Performance 4 upvotes, #20 of 2025-11-18
  21. MicroVQA++: High-Quality Microscopy Reasoning Dataset with Weakly Supervised Graphs for Multimodal Large Language Model 4 upvotes, #20 of 2025-11-18
  22. Dynamic Reflections: Probing Video Representations with Text Alignment 3 upvotes, #22 of 2025-11-18
  23. Test-Time Spectrum-Aware Latent Steering for Zero-Shot Generalization in Vision-Language Models 3 upvotes, #22 of 2025-11-18
  24. SafeGRPO: Self-Rewarded Multimodal Safety Alignment via Rule-Governed Policy Optimization 2 upvotes, #24 of 2025-11-18
  25. LoCoBench-Agent: An Interactive Benchmark for LLM Agents in Long-Context Software Engineering 2 upvotes, #24 of 2025-11-18
  26. A Decentralized Retrieval Augmented Generation System with Source Reliabilities Secured on Blockchain 1 upvotes, #26 of 2025-11-18
  27. AI-Salesman: Towards Reliable Large Language Model Driven Telemarketing 1 upvotes, #26 of 2025-11-18
  28. OpenUS: A Fully Open-Source Foundation Model for Ultrasound Image Analysis via Self-Adaptive Masked Contrastive Learning 2 upvotes, #28 of 2025-11-18

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.