 |
ML Newsnew | past | best | rss | submit | about |
|
Stories from February 8, 2025 (UTC)
|
| 1. | Value-Based Deep RL Scales Predictably (arxiv.org) |
| 68 points by bearseascape on Feb 8, 2025 | hide | past | pdf | 3 comments | |
| 2. | Bolt: Bootstrap long chain-of-thought in LLMs without distillation [pdf] (arxiv.org) |
| 15 points by TaurenHunter on Feb 8, 2025 | hide | past | pdf | 5 comments | |
| 3. | Demystifying Long Chain-of-Thought Reasoning in LLMs (arxiv.org) |
| 11 points by Anon84 on Feb 8, 2025 | hide | past | pdf | discuss | |
| 4. | STP: Self-Play LLM Theorem Provers with Iterative Conjecturing and Proving (arxiv.org) |
| 3 points by heydenberk on Feb 8, 2025 | hide | past | pdf | discuss | |
| 5. | Test-time scaling new approach: extra test-time compute improves LLM reasoning (arxiv.org) |
| 2 points by TaurenHunter on Feb 8, 2025 | hide | past | pdf | discuss | |
| 6. | CoCoNUT: Structural Code Understanding does not fall out of a tree (arxiv.org) |
| 2 points by PaulHoule on Feb 8, 2025 | hide | past | pdf | discuss | |