 |
ML Newsnew | past | best | rss | submit | about |
|
Stories from May 21, 2026 (UTC)
|
| 1. | Multi-Stream LLMs: new paper on parallelizing/separating prompts, thinking, I/O (arxiv.org) |
| 156 points by atomicthumbs 135 days ago | hide | past | pdf | 16 comments | |
| 2. | DashAttention: Differentiable and Adaptable Sparse Hierarchical Attention (arxiv.org) |
| 9 points by cmogni1 135 days ago | hide | past | pdf | discuss | |
| 3. | Lecture Notes on Statistical Physics and Neural Networks (arxiv.org) |
| 3 points by Anon84 135 days ago | hide | past | pdf | discuss | |
| 4. | PULSELoCo: 17x less trainer-to-trainer bandwidth in distributed RL post-training (arxiv.org) |
| 3 points by synapz_org 136 days ago | hide | past | pdf | discuss | |