ML Newsnew | past | best | rss | submit about
Stories from October 6, 2025 (UTC)
Go back a day, month, or year. Go forward a day.
1. Expected Attention: KV Cache Compression by Estimating Attention (arxiv.org)
20 points by sonabinu 362 days ago | hide | past | pdf | 3 comments
2. Fine-Tuning Small Language Models with Low-Rank Adapters to Mimic User Behaviors (arxiv.org)
3 points by PaulHoule 362 days ago | hide | past | pdf | discuss
3. Pretraining Large Language Models with NVFP4 (arxiv.org)
2 points by matt_d 362 days ago | hide | past | pdf | discuss
4. Video models are zero-shot learners and reasoners (arxiv.org)
2 points by wertyk 362 days ago | hide | past | pdf | discuss
5. Code-to-Metric Regression: Predicting Numeric Outcomes of Code Executions (arxiv.org)
2 points by chabad360 362 days ago | hide | past | pdf | discuss
6. An Efficient Vision-Language-Action Model for Combat Tasks in 3D Action RPGs (arxiv.org)
1 point by mikhael 362 days ago | hide | past | pdf | discuss
7. The threat of analytic flexibility in using LLMs to simulate human data (arxiv.org)
1 point by PaulHoule 362 days ago | hide | past | pdf | discuss
8. The Dragon Hatchling: The Missing Link Between the Transformer and the Brain (arxiv.org)
1 point by flux3125 362 days ago | hide | past | pdf | discuss
About | RSS | RSS (all) | HN arXiv