 |
ML Newsnew | past | best | rss | submit | about |
|
Stories from January 12, 2024 (UTC)
|
| 1. | Sleeper Agents: Training Deceptive LLMs That Persist Through Safety Training (arxiv.org) |
| 143 points by mfiguiere on Jan 12, 2024 | hide | past | pdf | 17 comments | |
| 2. | Meta: Multi-Source Test Time Adaptation (arxiv.org) |
| 3 points by PaulHoule on Jan 12, 2024 | hide | past | pdf | 1 comment | |
| 3. | Direct Preference Optimization: Your Language Model Is a Reward Model (arxiv.org) |
| 1 point by rahimnathwani on Jan 12, 2024 | hide | past | pdf | 2 comments | |
| 4. | Modeling Beats and Downbeats with a Time-Frequency Transformer (arxiv.org) |
| 1 point by teleforce on Jan 12, 2024 | hide | past | pdf | discuss | |