 |
ML Newsnew | past | best | rss | submit | about |
|
Stories from December 1, 2024 (UTC)
|
| 1. | Procedural knowledge in pretraining drives reasoning in large language models (arxiv.org) |
| 248 points by reqo on Dec 1, 2024 | hide | past | pdf | 101 comments | |
| 2. | DynaSaur: Large Language Agents Beyond Predefined Actions (arxiv.org) |
| 128 points by surprisetalk on Dec 1, 2024 | hide | past | pdf | 31 comments | |
| 3. | The Curse of Recursion: Training on generated data makes models forget (2023) (arxiv.org) |
| 122 points by surprisetalk on Dec 1, 2024 | hide | past | pdf | 107 comments | |
| 4. | Streaming Deep Reinforcement Learning Works (arxiv.org) |
| 2 points by surprisetalk on Dec 1, 2024 | hide | past | pdf | discuss | |
| 5. | DrugAgent: AI-Aided Drug Discovery Programming Through LLM Multi-Agent Collab (arxiv.org) |
| 2 points by surprisetalk on Dec 1, 2024 | hide | past | pdf | discuss | |
| 6. | Challenges and Applications of Large Language Models (arxiv.org) |
| 1 point by t55 on Dec 1, 2024 | hide | past | pdf | discuss | |