 |
ML Newsnew | past | best | rss | submit | about |
|
Stories from May 17, 2025 (UTC)
|
| 1. | LLMs are more persuasive than incentivized human persuaders (arxiv.org) |
| 140 points by flornt on May 17, 2025 | hide | past | pdf | 116 comments | |
| 2. | Understanding Transformers via N-gram Statistics (arxiv.org) |
| 139 points by pona-a on May 17, 2025 | hide | past | pdf | 16 comments | |
| 3. | Steepest Descent Density Control for Compact 3D Gaussian Splatting (arxiv.org) |
| 30 points by PaulHoule on May 17, 2025 | hide | past | pdf | discuss | |
| 4. | DeepSeek-V3: Scaling Challenges and Reflections on Hardware for AI Architectures (arxiv.org) |
| 4 points by nsoonhui on May 17, 2025 | hide | past | pdf | discuss | |
| 5. | Analyzing, Predicting, and Controlling How a Reasoning Model Will Think (arxiv.org) |
| 3 points by simonpure on May 17, 2025 | hide | past | pdf | discuss | |
| 6. | Open Problems in Mechanistic Interpretability (arxiv.org) |
| 1 point by nill0 on May 17, 2025 | hide | past | pdf | discuss | |