 |
ML Newsnew | past | best | rss | submit | about |
|
Stories from November 3, 2025 (UTC)
|
| 1. | Kimi Linear: An Expressive, Efficient Attention Architecture (arxiv.org) |
| 6 points by birriel 335 days ago | hide | past | pdf | discuss | |
| 2. | Deep sequence models tend to memorize geometrically (arxiv.org) |
| 3 points by jonbaer 334 days ago | hide | past | pdf | discuss | |
| 3. | Streaming DiLoCo: Towards a Distributed Free Lunch (arxiv.org) |
| 2 points by nathan-barry 334 days ago | hide | past | pdf | discuss | |
| 4. | Defeating the Training-Inference Mismatch via FP16 (arxiv.org) |
| 1 point by billyzs 335 days ago | hide | past | pdf | discuss | |