|
|
|
Stories from September 22, 2025 (UTC)
|
| 1. |
We Politely Insist: Your LLM Must Learn the Persian Art of Taarof (arxiv.org) |
|
181 points by chosenbeard on Sep 22, 2025 | hide | past | pdf | 122 comments
|
|
| 2. |
Paper2Agent: Stanford Reimagining Research Papers as Interactive AI Agents (arxiv.org) |
|
152 points by Gaishan on Sep 22, 2025 | hide | past | pdf | 44 comments
|
|
| 3. |
Tech Report: Winning CRS from Team Atlanta (DARPA AIxCC) (arxiv.org) |
|
23 points by tsgates on Sep 22, 2025 | hide | past | pdf | discuss
|
|
| 4. |
Jet-Nemotron: Efficient Language Model with Post Neural Architecture Search (arxiv.org) |
|
17 points by jonbaer on Sep 22, 2025 | hide | past | pdf | discuss
|
|
| 5. |
Wan-Animate: Unified Character Animation, Replacement with Holistic Replication (arxiv.org) |
|
2 points by walterbell on Sep 22, 2025 | hide | past | pdf | discuss
|
|
| 6. |
Unsupervised Instance Segmentation with Superpixels (arxiv.org) |
|
2 points by PaulHoule on Sep 22, 2025 | hide | past | pdf | discuss
|
|
| 7. |
The Illusion of Diminishing Returns: Measuring Long Horizon Execution in LLMs (arxiv.org) |
|
2 points by speckx on Sep 22, 2025 | hide | past | pdf | discuss
|
|
| 8. |
Apertus: Democratizing Open and Compliant LLMs for Global Language Environments (arxiv.org) |
|
2 points by elashri on Sep 22, 2025 | hide | past | pdf | discuss
|
|
| 9. |
TLinFormer, a Path to Exact, Full Context-Aware Linear Attention (arxiv.org) |
|
2 points by P_qRs on Sep 22, 2025 | hide | past | pdf | discuss
|
|
| 10. |
Culturally transmitted color categories in LLMs reflect efficient compression (arxiv.org) |
|
1 point by PaulHoule on Sep 22, 2025 | hide | past | pdf | discuss
|
|
| 11. |
Mindstorms in Natural Language-Based Societies of Mind (arxiv.org) |
|
1 point by carlsborg on Sep 22, 2025 | hide | past | pdf | discuss
|
|
|
|
