 |
ML Newsnew | past | best | rss | submit | about |
|
Stories from December 29, 2025 (UTC)
|
| 1. | Deep sequence models tend to memorize geometrically; it is unclear why (arxiv.org) |
| 3 points by tzury 278 days ago | hide | past | pdf | discuss | |
| 2. | Optimal Software Pipelining and Warp Specialization for Tensor Core GPUs (arxiv.org) |
| 2 points by matt_d 278 days ago | hide | past | pdf | discuss | |
| 3. | Propose, Solve, Verify: Self-Play Through Formal Verification (arxiv.org) |
| 2 points by imakwana 278 days ago | hide | past | pdf | discuss | |
| 4. | LLMs, LoRA, and Slerp Shape Representational Geometry of Embeddings (arxiv.org) |
| 1 point by PaulHoule 278 days ago | hide | past | pdf | discuss | |
| 5. | Generative Caching for Structurally Similar Prompts and Responses (arxiv.org) |
| 1 point by PaulHoule 278 days ago | hide | past | pdf | discuss | |
| 6. | Position: Privacy Is Not Just Memorization (arxiv.org) |
| 1 point by PaulHoule 278 days ago | hide | past | pdf | discuss | |