 |
ML Newsnew | past | best | rss | submit | about |
|
Stories from March 25, 2025 (UTC)
|
| 1. | Optimizing ML training with metagradient descent (arxiv.org) |
| 83 points by ladberg on Mar 25, 2025 | hide | past | pdf | 13 comments | |
| 2. | Scaling a 300B Mixture-of-Experts LING LLM Without Premium GPUs (arxiv.org) |
| 2 points by PaulHoule on Mar 25, 2025 | hide | past | pdf | discuss | |
| 3. | Graph Masked Language Models (arxiv.org) |
| 1 point by PaulHoule on Mar 25, 2025 | hide | past | pdf | discuss | |
| 4. | Communication-Efficient Language Model Training Scales Reliably and Robustly (arxiv.org) |
| 1 point by PaulHoule on Mar 25, 2025 | hide | past | pdf | discuss | |
| 5. | SQLCritic: Correcting Text-to-SQL Generation via Clause-Wise Critic (arxiv.org) |
| 1 point by PaulHoule on Mar 25, 2025 | hide | past | pdf | discuss | |