Daily Papers of 2025-08-22

1. Intern-S1: A Scientific Multimodal Foundation Model 242 upvotes, #1 of 2025-08-22
2. Deep Think with Confidence 74 upvotes, #2 of 2025-08-22
3. Mobile-Agent-v3: Foundamental Agents for GUI Automation 55 upvotes, #3 of 2025-08-22
4. LiveMCP-101: Stress Testing and Diagnosing MCP-enabled Agents on Challenging Queries 42 upvotes, #4 of 2025-08-22
5. Waver: Wave Your Way to Lifelike Video Generation 33 upvotes, #5 of 2025-08-22
6. aiXiv: A Next-Generation Open Access Ecosystem for Scientific Discovery Generated by AI Scientists 18 upvotes, #6 of 2025-08-22
7. A Survey on Large Language Model Benchmarks 18 upvotes, #6 of 2025-08-22
8. SceneGen: Single-Image 3D Scene Generation in One Feedforward Pass 18 upvotes, #6 of 2025-08-22
9. ATLAS: Decoupling Skeletal and Shape Parameters for Expressive Parametric Human Modeling 12 upvotes, #9 of 2025-08-22
10. Visual Autoregressive Modeling for Instruction-Guided Image Editing 8 upvotes, #10 of 2025-08-22
11. Snap-Snap: Taking Two Images to Reconstruct 3D Human Gaussians in Milliseconds 7 upvotes, #11 of 2025-08-22
12. "Does the cafe entrance look accessible? Where is the door?" Towards Geospatial AI Agents for Visual Inquiries 7 upvotes, #11 of 2025-08-22
13. LLaSO: A Foundational Framework for Reproducible Research in Large Language and Speech Model 4 upvotes, #13 of 2025-08-22
14. INTIMA: A Benchmark for Human-AI Companionship Behavior 3 upvotes, #14 of 2025-08-22
15. Fin-PRM: A Domain-Specialized Process Reward Model for Financial Reasoning in Large Language Models 3 upvotes, #14 of 2025-08-22
16. When and What: Diffusion-Grounded VideoLLM with Entity Aware Segmentation for Long Video Understanding 3 upvotes, #14 of 2025-08-22

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.