Daily Papers of 2025-05-16

  1. Beyond 'Aha!': Toward Systematic Meta-Abilities Alignment in Large Reasoning Models 113 upvotes, #1 of 2025-05-16
  2. Parallel Scaling Law for Language Models 72 upvotes, #2 of 2025-05-16
  3. System Prompt Optimization with Meta-Learning 66 upvotes, #3 of 2025-05-16
  4. OpenThinkIMG: Learning to Think with Images via Visual Tool Reinforcement Learning 39 upvotes, #4 of 2025-05-16
  5. WorldPM: Scaling Human Preference Modeling 33 upvotes, #5 of 2025-05-16
  6. The CoT Encyclopedia: Analyzing, Predicting, and Controlling how a Reasoning Model will Think 24 upvotes, #6 of 2025-05-16
  7. EnerVerse-AC: Envisioning Embodied Environments with Action Condition 21 upvotes, #7 of 2025-05-16
  8. J1: Incentivizing Thinking in LLM-as-a-Judge via Reinforcement Learning 20 upvotes, #8 of 2025-05-16
  9. End-to-End Vision Tokenizer Tuning 20 upvotes, #8 of 2025-05-16
  10. EWMBench: Evaluating Scene, Motion, and Semantic Quality in Embodied World Models 18 upvotes, #10 of 2025-05-16
  11. Unilogit: Robust Machine Unlearning for LLMs Using Uniform-Target Self-Distillation 17 upvotes, #11 of 2025-05-16
  12. MLE-Dojo: Interactive Environments for Empowering LLM Agents in Machine Learning Engineering 16 upvotes, #12 of 2025-05-16
  13. Style Customization of Text-to-Vector Generation with Image Diffusion Priors 15 upvotes, #13 of 2025-05-16
  14. PointArena: Probing Multimodal Grounding Through Language-Guided Pointing 11 upvotes, #14 of 2025-05-16
  15. Depth Anything with Any Prior 11 upvotes, #14 of 2025-05-16
  16. ReSurgSAM2: Referring Segment Anything in Surgical Video via Credible Long-term Tracking 9 upvotes, #16 of 2025-05-16
  17. Achieving Tokenizer Flexibility in Language Models through Heuristic Adaptation and Supertoken Learning 9 upvotes, #16 of 2025-05-16
  18. Exploring the Deep Fusion of Large Language Models and Diffusion Transformers for Text-to-Image Synthesis 9 upvotes, #16 of 2025-05-16
  19. QuXAI: Explainers for Hybrid Quantum Machine Learning Models 7 upvotes, #19 of 2025-05-16
  20. AI Agents vs. Agentic AI: A Conceptual Taxonomy, Applications and Challenge 7 upvotes, #19 of 2025-05-16
  21. 3D-Fixup: Advancing Photo Editing with 3D Priors 7 upvotes, #19 of 2025-05-16
  22. AdaptCLIP: Adapting CLIP for Universal Visual Anomaly Detection 6 upvotes, #22 of 2025-05-16
  23. Learning to Detect Multi-class Anomalies with Just One Normal Image Prompt 5 upvotes, #23 of 2025-05-16
  24. Real2Render2Real: Scaling Robot Data Without Dynamics Simulation or Robot Hardware 5 upvotes, #23 of 2025-05-16
  25. Few-Shot Anomaly-Driven Generation for Anomaly Classification and Segmentation 4 upvotes, #25 of 2025-05-16
  26. MetaUAS: Universal Anomaly Segmentation with One-Prompt Meta-Learning 4 upvotes, #25 of 2025-05-16
  27. X-Sim: Cross-Embodiment Learning via Real-to-Sim-to-Real 3 upvotes, #27 of 2025-05-16

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.