 |
ML Newsnew | past | best | rss | submit | about |
|
Stories from October 17, 2025 (UTC)
|
| 1. | Every Language Model Has a Forgery-Resistant Signature (arxiv.org) |
| 7 points by mattfinlayson 352 days ago | hide | past | pdf | 2 comments | |
| 2. | Unsupervised, Human-Inspired Long-Term Memory Architecture for Edge-Based LLMs (arxiv.org) |
| 2 points by PaulHoule 352 days ago | hide | past | pdf | discuss | |
| 3. | Sample-Efficient Online Learning in LM Agents via Hindsight Trajectory Rewriting (arxiv.org) |
| 2 points by djhu9 352 days ago | hide | past | pdf | discuss | |
| 4. | LLMs Achieve Gold Medal Performance at the IOAA (arxiv.org) |
| 1 point by throwaway29303 352 days ago | hide | past | pdf | 1 comment | |
| 5. | It's 2025 – Narrative Learning is the new baseline to beat for explainable ML (arxiv.org) |
| 1 point by solresol 352 days ago | hide | past | pdf | discuss | |
| 6. | Baby Dragon Hatchling (arxiv.org) |
| 1 point by jacobgorm 352 days ago | hide | past | pdf | 1 comment | |
| 7. | The Art of Scaling Reinforcement Learning Compute for LLMs [Meta] (arxiv.org) |
| 1 point by wavelander 352 days ago | hide | past | pdf | discuss | |