Daily Papers of 2025-11-13

1. Lumine: An Open Recipe for Building Generalist Agents in 3D Open Worlds 172 upvotes, #1 of 2025-11-13
2. TiDAR: Think in Diffusion, Talk in Autoregression 95 upvotes, #2 of 2025-11-13
3. MADD: Multi-Agent Drug Discovery Orchestra 54 upvotes, #3 of 2025-11-13
4. Time-to-Move: Training-Free Motion Controlled Video Generation via Dual-Clock Denoising 50 upvotes, #4 of 2025-11-13
5. Motif 2 12.7B technical report 38 upvotes, #5 of 2025-11-13
6. LoopTool: Closing the Data-Training Loop for Robust LLM Tool Calls 15 upvotes, #6 of 2025-11-13
7. WMPO: World Model-based Policy Optimization for Vision-Language-Action Models 15 upvotes, #6 of 2025-11-13
8. WebVIA: A Web-based Vision-Language Agentic Framework for Interactive and Verifiable UI-to-Code Generation 12 upvotes, #8 of 2025-11-13
9. MathSE: Improving Multimodal Mathematical Reasoning via Self-Evolving Iterative Reflection and Reward-Guided Fine-Tuning 11 upvotes, #9 of 2025-11-13
10. Adapting Web Agents with Synthetic Supervision 5 upvotes, #10 of 2025-11-13
11. Toward the Frontiers of Reliable Diffusion Sampling via Adversarial Sinkhorn Attention Guidance 5 upvotes, #10 of 2025-11-13
12. Agentic Refactoring: An Empirical Study of AI Coding Agents 4 upvotes, #12 of 2025-11-13
13. Stemming Hallucination in Language Models Using a Licensing Oracle 1 upvotes, #13 of 2025-11-13

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.