Daily Papers of 2025-04-22

  1. Learning to Reason under Off-Policy Guidance 77 upvotes, #1 of 2025-04-22
  2. Eagle 2.5: Boosting Long-Context Post-Training for Frontier Vision-Language Models 65 upvotes, #2 of 2025-04-22
  3. FlowReasoner: Reinforcing Query-Level Meta-Agents 46 upvotes, #3 of 2025-04-22
  4. ToolRL: Reward is All Tool Learning Needs 41 upvotes, #4 of 2025-04-22
  5. OTC: Optimal Tool Calls via Reinforcement Learning 33 upvotes, #5 of 2025-04-22
  6. X-Teaming: Multi-Turn Jailbreaks and Defenses with Adaptive Multi-Agents 30 upvotes, #6 of 2025-04-22
  7. SphereDiff: Tuning-free Omnidirectional Panoramic Image and Video Generation via Spherical Latent Representation 27 upvotes, #7 of 2025-04-22
  8. UFO2: The Desktop AgentOS 27 upvotes, #7 of 2025-04-22
  9. THOUGHTTERMINATOR: Benchmarking, Calibrating, and Mitigating Overthinking in Reasoning Models 24 upvotes, #9 of 2025-04-22
  10. StyleMe3D: Stylization with Disentangled Priors by Multiple Encoders on 3D Gaussians 23 upvotes, #10 of 2025-04-22
  11. Seeing from Another Perspective: Evaluating Multi-View Understanding in MLLMs 22 upvotes, #11 of 2025-04-22
  12. EasyEdit2: An Easy-to-use Steering Framework for Editing Large Language Models 21 upvotes, #12 of 2025-04-22
  13. LeetCodeDataset: A Temporal Dataset for Robust Evaluation and Efficient Training of Code LLMs 19 upvotes, #13 of 2025-04-22
  14. Uni3C: Unifying Precisely 3D-Enhanced Camera and Human Motion Controls for Video Generation 18 upvotes, #14 of 2025-04-22
  15. InfiGUI-R1: Advancing Multimodal GUI Agents from Reactive Actors to Deliberative Reasoners 13 upvotes, #15 of 2025-04-22
  16. LearnAct: Few-Shot Mobile GUI Agent with a Unified Demonstration Benchmark 11 upvotes, #16 of 2025-04-22
  17. DRAGON: Distributional Rewards Optimize Diffusion Generative Models 10 upvotes, #17 of 2025-04-22
  18. An LMM for Efficient Video Understanding via Reinforced Compression of Video Cubes 10 upvotes, #17 of 2025-04-22
  19. LookingGlass: Generative Anamorphoses via Laplacian Pyramid Warping 8 upvotes, #19 of 2025-04-22
  20. TAPIP3D: Tracking Any Point in Persistent 3D Geometry 7 upvotes, #20 of 2025-04-22
  21. NEMOTRON-CROSSTHINK: Scaling Self-Learning beyond Math Reasoning 6 upvotes, #21 of 2025-04-22
  22. RainbowPlus: Enhancing Adversarial Prompt Generation via Evolutionary Quality-Diversity Search 6 upvotes, #21 of 2025-04-22
  23. RF-DETR Object Detection vs YOLOv12 : A Study of Transformer-based and CNN-based Architectures for Single-Class and Multi-Class Greenfruit Detection in Complex Orchard Environments Under Label Ambiguity 4 upvotes, #23 of 2025-04-22
  24. LoftUp: Learning a Coordinate-Based Feature Upsampler for Vision Foundation Models 4 upvotes, #23 of 2025-04-22
  25. PROMPTEVALS: A Dataset of Assertions and Guardrails for Custom Production Large Language Model Pipelines 4 upvotes, #23 of 2025-04-22
  26. CoMotion: Concurrent Multi-person 3D Motion 3 upvotes, #26 of 2025-04-22
  27. SilVar-Med: A Speech-Driven Visual Language Model for Explainable Abnormality Detection in Medical Imaging 2 upvotes, #27 of 2025-04-22
  28. Roll the dice & look before you leap: Going beyond the creative limits of next-token prediction 2 upvotes, #27 of 2025-04-22

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.