|
|
Stories from November 4, 2024 (UTC)
|
| 1. |
An embarrassingly simple approach to recover unlearned knowledge for LLMs (arxiv.org) |
|
259 points by PaulHoule on Nov 4, 2024 | hide | past | pdf | 121 comments
|
| 2. |
URAvatar: Universal Relightable Gaussian Codec Avatars (arxiv.org) |
|
2 points by sandwichsphinx on Nov 4, 2024 | hide | past | pdf | discuss
|
| 3. |
An End-to-End Model with Adaptive Filtering for Retrieval-Augmented Generation (arxiv.org) |
|
2 points by foweltschmerz on Nov 4, 2024 | hide | past | pdf | discuss
|
| 4. |
VibeCheck: Discover and Quantify Qualitative Differences in LLMs (arxiv.org) |
|
1 point by PaulHoule on Nov 4, 2024 | hide | past | pdf | discuss
|
| 5. |
Interpretable Online Log Analysis Using LLMs with Prompt Strategies (arxiv.org) |
|
1 point by krunck on Nov 4, 2024 | hide | past | pdf | discuss
|
| 6. |
MarsCode Agent: AI-Native Automated Bug Fixing (arxiv.org) |
|
1 point by zshanhui on Nov 4, 2024 | hide | past | pdf | discuss
|
| 7. |
Alice's Adventures in a Differentiable Wonderland (PDF) (arxiv.org) |
|
1 point by yarapavan on Nov 4, 2024 | hide | past | pdf | discuss
|
| 8. |
Personalization of Large Language Models: A Survey (arxiv.org) |
|
1 point by sandwichsphinx on Nov 4, 2024 | hide | past | pdf | discuss
|
| 9. |
The Persistence of Neural Collapse Despite Low-Rank Bias (arxiv.org) |
|
1 point by Wheatman on Nov 4, 2024 | hide | past | pdf | 1 comment
|
| 10. |
Mastering the Craft of Data Synthesis for CodeLLMs (arxiv.org) |
|
1 point by sandwichsphinx on Nov 4, 2024 | hide | past | pdf | discuss
|
| 11. |
Thinking LLMs: General Instruction Following with Thought Generation (arxiv.org) |
|
1 point by timbilt on Nov 4, 2024 | hide | past | pdf | discuss
|
|