 |
ML Newsnew | past | best | rss | submit | about |
|
Stories from March 24, 2025 (UTC)
|
| 1. | Every Flop Counts: Scaling a 300B LLM Without Premium GPUs (arxiv.org) |
| 117 points by bretpiatt on Mar 24, 2025 | hide | past | pdf | 9 comments | |
| 2. | Can Large Vision Language Models Read Maps Like a Human? (arxiv.org) |
| 9 points by thinkingemote on Mar 24, 2025 | hide | past | pdf | 1 comment | |
| 3. | Accurate INT8 Training Through Dynamic Block-Level Fallback (arxiv.org) |
| 3 points by PaulHoule on Mar 24, 2025 | hide | past | pdf | discuss | |
| 4. | Bold: Boolean Logic Deep Learning (arxiv.org) |
| 2 points by cubefox on Mar 24, 2025 | hide | past | pdf | 1 comment | |
| 5. | EvoBPE: Evolutionary Protein Sequence Tokenization (arxiv.org) |
| 1 point by PaulHoule on Mar 24, 2025 | hide | past | pdf | discuss | |
| 6. | Sentence-Level Reward Model Can Better Aligning LLM from Human Preference (arxiv.org) |
| 1 point by PaulHoule on Mar 24, 2025 | hide | past | pdf | discuss | |
| 7. | Self-Optimization of Hopfield Networks: The Creativity of Unsupervised Learning (arxiv.org) |
| 1 point by pizza on Mar 24, 2025 | hide | past | pdf | discuss | |