Daily Papers of 2025-03-20

  1. φ-Decoding: Adaptive Foresight Sampling for Balanced Inference-Time Exploration and Exploitation 46 upvotes, #1 of 2025-03-20
  2. DeepMesh: Auto-Regressive Artist-mesh Creation with Reinforcement Learning 43 upvotes, #2 of 2025-03-20
  3. TULIP: Towards Unified Language-Image Pretraining 43 upvotes, #2 of 2025-03-20
  4. Cube: A Roblox View of 3D Intelligence 26 upvotes, #4 of 2025-03-20
  5. GKG-LLM: A Unified Framework for Generalized Knowledge Graph Construction 24 upvotes, #5 of 2025-03-20
  6. Temporal Regularization Makes Your Video Generator Stronger 21 upvotes, #6 of 2025-03-20
  7. MetaLadder: Ascending Mathematical Solution Quality via Analogical-Problem Reasoning Transfer 20 upvotes, #7 of 2025-03-20
  8. VERIFY: A Benchmark of Visual Explanation and Reasoning for Investigating Multimodal Reasoning Fidelity 19 upvotes, #8 of 2025-03-20
  9. Efficient Personalization of Quantized Diffusion Model without Backpropagation 19 upvotes, #8 of 2025-03-20
  10. LEGION: Learning to Ground and Explain for Synthetic Image Detection 19 upvotes, #8 of 2025-03-20
  11. Optimizing Decomposition for Optimal Claim Verification 18 upvotes, #11 of 2025-03-20
  12. STEVE: AStep Verification Pipeline for Computer-use Agent Training 13 upvotes, #12 of 2025-03-20
  13. SkyLadder: Better and Faster Pretraining via Context Window Scheduling 11 upvotes, #13 of 2025-03-20
  14. MusicInfuser: Making Video Diffusion Listen and Dance 9 upvotes, #14 of 2025-03-20
  15. Decompositional Neural Scene Reconstruction with Generative Diffusion Prior 9 upvotes, #14 of 2025-03-20
  16. ViSpeak: Visual Instruction Feedback in Streaming Videos 8 upvotes, #16 of 2025-03-20
  17. SWEET-RL: Training Multi-Turn LLM Agents on Collaborative Reasoning Tasks 8 upvotes, #16 of 2025-03-20
  18. Unlock Pose Diversity: Accurate and Efficient Implicit Keypoint-based Spatiotemporal Diffusion for Audio-driven Talking Portrait 7 upvotes, #18 of 2025-03-20
  19. LLM-FE: Automated Feature Engineering for Tabular Data with LLMs as Evolutionary Optimizers 7 upvotes, #18 of 2025-03-20
  20. Mitigating Visual Forgetting via Take-along Visual Conditioning for Multi-modal Long CoT Reasoning 6 upvotes, #20 of 2025-03-20
  21. ELTEX: A Framework for Domain-Driven Synthetic Data Generation 5 upvotes, #21 of 2025-03-20
  22. CURIE: Evaluating LLMs On Multitask Scientific Long Context Understanding and Reasoning 4 upvotes, #22 of 2025-03-20
  23. LLM-Mediated Guidance of MARL Systems 3 upvotes, #23 of 2025-03-20

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.