|
|
|
Stories from January 13, 2025 (UTC)
|
| 1. |
Titans: Learning to Memorize at Test Time (arxiv.org) |
|
115 points by birriel on Jan 13, 2025 | hide | past | pdf | 15 comments
|
|
| 2. |
VideoRAG: Retrieval-Augmented Generation over Video Corpus (arxiv.org) |
|
4 points by t55 on Jan 13, 2025 | hide | past | pdf | discuss
|
|
| 3. |
Frontier Models are Capable of In-context Scheming (arxiv.org) |
|
2 points by wslh on Jan 13, 2025 | hide | past | pdf | discuss
|
|
| 4. |
A Framework for Training and Deploying Language Models at the Edge Computers (arxiv.org) |
|
1 point by PaulHoule on Jan 13, 2025 | hide | past | pdf | discuss
|
|
| 5. |
Data Poisoning in LLMs: Jailbreak-Tuning and Scaling Laws (arxiv.org) |
|
1 point by pera on Jan 13, 2025 | hide | past | pdf | discuss
|
|
| 6. |
Quantifying Positional Biases in Text Embedding Models (arxiv.org) |
|
1 point by PaulHoule on Jan 13, 2025 | hide | past | pdf | discuss
|
|
| 7. |
State Space Models Are Strong Text Rerankers (arxiv.org) |
|
1 point by PaulHoule on Jan 13, 2025 | hide | past | pdf | discuss
|
|
| 8. |
Towards Backdoor Stealthiness in Model Parameter Space (arxiv.org) |
|
1 point by belter on Jan 13, 2025 | hide | past | pdf | discuss
|
|
| 9. |
LLM forecasters rapidly approaching human-level performance (arxiv.org) |
|
1 point by drcwpl on Jan 13, 2025 | hide | past | pdf | 1 comment
|
|
| 10. |
Question Answering is a Format; When is it Useful? (arxiv.org) |
|
1 point by jbarrow on Jan 13, 2025 | hide | past | pdf | discuss
|
|
|
|
