Daily Papers of 2025-04-08

  1. SmolVLM: Redefining small and efficient multimodal models 158 upvotes, #1 of 2025-04-08
  2. One-Minute Video Generation with Test-Time Training 92 upvotes, #2 of 2025-04-08
  3. Rethinking Reflection in Pre-Training 72 upvotes, #3 of 2025-04-08
  4. T1: Tool-integrated Self-verification for Test-time Compute Scaling in Small Language Models 38 upvotes, #4 of 2025-04-08
  5. URECA: Unique Region Caption Anything 33 upvotes, #5 of 2025-04-08
  6. Quantization Hurts Reasoning? An Empirical Study on Quantized Reasoning Models 28 upvotes, #6 of 2025-04-08
  7. VAPO: Efficient and Reliable Reinforcement Learning for Advanced Reasoning Tasks 24 upvotes, #7 of 2025-04-08
  8. Concept Lancet: Image Editing with Compositional Representation Transplant 16 upvotes, #8 of 2025-04-08
  9. LiveVQA: Live Visual Knowledge Seeking 13 upvotes, #9 of 2025-04-08
  10. Why Reasoning Matters? A Survey of Advancements in Multimodal Reasoning (v1) 12 upvotes, #10 of 2025-04-08
  11. Are You Getting What You Pay For? Auditing Model Substitution in LLM APIs 12 upvotes, #10 of 2025-04-08
  12. Gaussian Mixture Flow Matching Models 9 upvotes, #12 of 2025-04-08
  13. DiaTool-DPO: Multi-Turn Direct Preference Optimization for Tool-Augmented Large Language Models 6 upvotes, #13 of 2025-04-08
  14. Mamba as a Bridge: Where Vision Foundation Models Meet Vision Language Models for Domain-Generalized Semantic Segmentation 5 upvotes, #14 of 2025-04-08
  15. 3D Scene Understanding Through Local Random Access Sequence Modeling 5 upvotes, #14 of 2025-04-08
  16. Clinical ModernBERT: An efficient and long context encoder for biomedical text 5 upvotes, #14 of 2025-04-08
  17. Distillation and Refinement of Reasoning in Small Language Models for Document Re-ranking 4 upvotes, #17 of 2025-04-08
  18. BOP Challenge 2024 on Model-Based and Model-Free 6D Object Pose Estimation 3 upvotes, #18 of 2025-04-08
  19. JailDAM: Jailbreak Detection with Adaptive Memory for Vision-Language Model 3 upvotes, #18 of 2025-04-08
  20. Sample, Don't Search: Rethinking Test-Time Alignment for Language Models 2 upvotes, #20 of 2025-04-08
  21. Rethinking Multilingual Continual Pretraining: Data Mixing for Adapting LLMs Across Languages and Resources 1 upvotes, #21 of 2025-04-08
  22. GlotEval: A Test Suite for Massively Multilingual Evaluation of Large Language Models 1 upvotes, #21 of 2025-04-08

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.