 |
ML Newsnew | past | best | rss | submit | about |
|
Stories from January 19, 2026 (UTC)
|
| 1. | The unreasonable effectiveness of pattern matching (arxiv.org) |
| 7 points by headalgorithm 257 days ago | hide | past | pdf | 1 comment | |
| 2. | Do You Trust Me? Cognitive-Affective Signatures of Trustworthiness in LLMs (arxiv.org) |
| 4 points by 7777777phil 258 days ago | hide | past | pdf | discuss | |
| 3. | Too Helpful to Be Safe: User-Mediated Attacks on Planning and Web-Use Agents (arxiv.org) |
| 4 points by 7777777phil 258 days ago | hide | past | pdf | discuss | |
| 4. | DiffusionBlocks: Block-Wise Neural Network Training (arxiv.org) |
| 3 points by E-Reverance 257 days ago | hide | past | pdf | 5 comments | |
| 5. | Prompt Repetition Improves Non-Reasoning LLMs (arxiv.org) |
| 3 points by Tomte 258 days ago | hide | past | pdf | discuss | |
| 6. | The Assistant Axis: Situating/Stabilizing the Default Persona of Language Models (arxiv.org) |
| 1 point by lawrenceyan 257 days ago | hide | past | pdf | discuss | |