 |
ML Newsnew | past | best | rss | submit | about |
|
Stories from December 12, 2025 (UTC)
|
| 1. | Training LLMs for honesty via confessions (arxiv.org) |
| 70 points by arabello 296 days ago | hide | past | pdf | 58 comments | |
| 2. | Weird Generalization and Inductive Backdoors: New Ways to Corrupt LLMs (arxiv.org) |
| 7 points by joegibbs 296 days ago | hide | past | pdf | 2 comments | |
| 3. | How Well Do LLMs Understand Tunisian Arabic? (arxiv.org) |
| 3 points by PaulHoule 296 days ago | hide | past | pdf | discuss | |
| 4. | AI based hacking compared to humans (arxiv.org) |
| 2 points by mriguy 296 days ago | hide | past | pdf | discuss | |
| 5. | Framework for Preventing Unauthorized Zero-Shot Image-to-Image Generation (arxiv.org) |
| 2 points by PaulHoule 296 days ago | hide | past | pdf | discuss | |
| 6. | Can You Learn to See Without Images? Procedural Warm-Up for Vision Transformers (arxiv.org) |
| 2 points by andy12_ 296 days ago | hide | past | pdf | 1 comment | |
| 7. | Beyond Data Filtering: Knowledge Localization for Capability Removal in LLMs (arxiv.org) |
| 2 points by yorwba 296 days ago | hide | past | pdf | discuss | |