Daily Papers of 2025-07-24

1. Yume: An Interactive World Generation Model 77 upvotes, #1 of 2025-07-24
2. Pixels, Patterns, but No Poetry: To See The World like Humans 62 upvotes, #2 of 2025-07-24
3. DesignLab: Designing Slides Through Iterative Detection and Correction 47 upvotes, #3 of 2025-07-24
4. Can One Domain Help Others? A Data-Centric Study on Multi-Domain Reasoning via Reinforcement Learning 33 upvotes, #4 of 2025-07-24
5. Ultra3D: Efficient and High-Fidelity 3D Generation with Part Attention 30 upvotes, #5 of 2025-07-24
6. RAVine: Reality-Aligned Evaluation for Agentic Search 28 upvotes, #6 of 2025-07-24
7. Re:Form -- Reducing Human Priors in Scalable Formal Software Verification with RL in LLMs: A Preliminary Study on Dafny 17 upvotes, #7 of 2025-07-24
8. Promptomatix: An Automatic Prompt Optimization Framework for Large Language Models 16 upvotes, #8 of 2025-07-24
9. Elevating 3D Models: High-Quality Texture and Geometry Refinement from a Low-Quality Model 14 upvotes, #9 of 2025-07-24
10. PUSA V1.0: Surpassing Wan-I2V with $500 Training Cost by Vectorized Timestep Adaptation 9 upvotes, #10 of 2025-07-24
11. Finding Dori: Memorization in Text-to-Image Diffusion Models Is Less Local Than Assumed 6 upvotes, #11 of 2025-07-24

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.