Daily Papers of 2025-07-25

  1. Group Sequence Policy Optimization 257 upvotes, #1 of 2025-07-25
  2. nablaNABLA: Neighborhood Adaptive Block-Level Attention 117 upvotes, #2 of 2025-07-25
  3. MUR: Momentum Uncertainty guided Reasoning for Large Language Models 45 upvotes, #3 of 2025-07-25
  4. Captain Cinema: Towards Short Movie Generation 37 upvotes, #4 of 2025-07-25
  5. LAPO: Internalizing Reasoning Efficiency via Length-Adaptive Policy Optimization 34 upvotes, #5 of 2025-07-25
  6. EarthCrafter: Scalable 3D Earth Generation via Dual-Sparse Latent Diffusion 18 upvotes, #6 of 2025-07-25
  7. TTS-VAR: A Test-Time Scaling Framework for Visual Auto-Regressive Generation 17 upvotes, #7 of 2025-07-25
  8. Hierarchical Budget Policy Optimization for Adaptive Reasoning 16 upvotes, #8 of 2025-07-25
  9. GLiNER2: An Efficient Multi-Task Information Extraction System with Schema-Driven Interface 13 upvotes, #9 of 2025-07-25
  10. DriftMoE: A Mixture of Experts Approach to Handle Concept Drifts 10 upvotes, #10 of 2025-07-25
  11. Technical Report of TeleChat2, TeleChat2.5 and T1 9 upvotes, #11 of 2025-07-25
  12. DMOSpeech 2: Reinforcement Learning for Duration Prediction in Metric-Optimized Speech Synthesis 7 upvotes, #12 of 2025-07-25
  13. Discovering and using Spelke segments 7 upvotes, #12 of 2025-07-25
  14. A New Pair of GloVes 7 upvotes, #12 of 2025-07-25
  15. TeEFusion: Blending Text Embeddings to Distill Classifier-Free Guidance 7 upvotes, #12 of 2025-07-25
  16. Agentar-Fin-R1: Enhancing Financial Intelligence through Domain Expertise, Training Efficiency, and Advanced Reasoning 6 upvotes, #16 of 2025-07-25
  17. SegDT: A Diffusion Transformer-Based Segmentation Model for Medical Imaging 4 upvotes, #17 of 2025-07-25
  18. HLFormer: Enhancing Partially Relevant Video Retrieval with Hyperbolic Learning 4 upvotes, #17 of 2025-07-25
  19. Iwin Transformer: Hierarchical Vision Transformer using Interleaved Windows 4 upvotes, #17 of 2025-07-25
  20. Deep Learning-Based Age Estimation and Gender Deep Learning-Based Age Estimation and Gender Classification for Targeted Advertisement 2 upvotes, #20 of 2025-07-25
  21. True Multimodal In-Context Learning Needs Attention to the Visual Context 1 upvotes, #21 of 2025-07-25

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.