ML Newsnew | past | best | rss | submit about
Stories from November 13, 2025 (UTC)
Go back a day, month, or year. Go forward a day.
1. Whisper leak: a side-channel attack on large language models (arxiv.org)
3 points by neapolisbeach 325 days ago | hide | past | pdf | discuss
2. Can we bootstrap AI Safety despite being unable to even define it? (arxiv.org)
2 points by cryptohell 325 days ago | hide | past | pdf | 2 comments
3. Probing Knowledge Holes in Unlearned LLMs (arxiv.org)
2 points by PaulHoule 325 days ago | hide | past | pdf | discuss
4. Pictographic Character Reconstruction with Bézier Curves (arxiv.org)
2 points by PaulHoule 325 days ago | hide | past | pdf | discuss
5. LeJEPA: Provable and Scalable Self-Supervised Learning Without the Heuristics (arxiv.org)
2 points by samstevens 325 days ago | hide | past | pdf | discuss
6. Continuous Autoregressive Language Models (arxiv.org)
2 points by badmonster 325 days ago | hide | past | pdf | discuss
7. Source-Optimal Training Is Transfer-Suboptimal (arxiv.org)
1 point by ceh123 325 days ago | hide | past | pdf | 1 comment
8. Automated Contiguous Layer Pruning for Large Language Models (arxiv.org)
1 point by PaulHoule 325 days ago | hide | past | pdf | discuss
9. Hadsf: Aspect Aware Semantic Control for Explainable Recommendation (arxiv.org)
1 point by PaulHoule 325 days ago | hide | past | pdf | discuss
10. How far are we from scaling up next-pixel prediction? (arxiv.org)
1 point by Hard_Space 325 days ago | hide | past | pdf | discuss
About | RSS | RSS (all) | HN arXiv