 |
ML Newsnew | past | best | rss | submit | about |
|
Stories from July 16, 2025 (UTC)
|
| 1. | Chain of thought monitorability: A new and fragile opportunity for AI safety (arxiv.org) |
| 134 points by mfiguiere on Jul 16, 2025 | hide | past | pdf | 64 comments | |
| 2. | How Many Instruction Can LLMs Follow at Once? (arxiv.org) |
| 11 points by djdistyl on Jul 16, 2025 | hide | past | pdf | discuss | |
| 3. | A LoD of Gaussians: Ultra-Large Scale Reconstruction with External Memory (arxiv.org) |
| 2 points by PaulHoule on Jul 16, 2025 | hide | past | pdf | discuss | |
| 4. | Assessing RAG and HyDE on 1B vs. 4B-Parameter Gemma LLMs for Personal Assistants (arxiv.org) |
| 1 point by PaulHoule on Jul 16, 2025 | hide | past | pdf | discuss | |
| 5. | TinyTroupe: An LLM-Powered Multiagent Persona Simulation Toolkit (arxiv.org) |
| 1 point by ajcp on Jul 16, 2025 | hide | past | pdf | discuss | |
| 6. | Mixture-of-Recursions (arxiv.org) |
| 1 point by mfiguiere on Jul 16, 2025 | hide | past | pdf | discuss | |
| 7. | GenAI-Powered Inference (arxiv.org) |
| 1 point by JackeJR on Jul 16, 2025 | hide | past | pdf | 1 comment | |