ML Newsnew | past | best | rss | submit about
Stories from March 31, 2025 (UTC)
Go back a day, month, or year. Go forward a day.
1. Proof or Bluff? Evaluating LLMs on 2025 USA Math Olympiad (arxiv.org)
13 points by mfiguiere on Mar 31, 2025 | hide | past | pdf | 2 comments
2. Large Language Models Can Verbatim Reproduce Long Malicious Sequences (arxiv.org)
3 points by wslh on Mar 31, 2025 | hide | past | pdf | discuss
3. A Framework for Evaluating Emerging Cyberattack Capabilities of AI [pdf] (arxiv.org)
3 points by _tk_ on Mar 31, 2025 | hide | past | pdf | discuss
4. AttentionRAG: Attention-Guided Context Pruning in Retrieval-Augmented Generation (arxiv.org)
2 points by PaulHoule on Mar 31, 2025 | hide | past | pdf | discuss
5. Cerebras Wafer-Scale Integration vs. Nvidia GPU-Based Systems for AI (arxiv.org)
2 points by PaulHoule on Mar 31, 2025 | hide | past | pdf | discuss
6. Graph neural networks extrapolate out-of-distribution for shortest paths (arxiv.org)
2 points by calebkaiser on Mar 31, 2025 | hide | past | pdf | discuss
7. Relax: Composable Abstractions for End-to-End Dynamic Machine Learning (arxiv.org)
2 points by djhu9 on Mar 31, 2025 | hide | past | pdf | discuss
8. Quantum advantage for learning shallow NNs with natural data distributions (arxiv.org)
1 point by westurner on Mar 31, 2025 | hide | past | pdf | 2 comments
About | RSS | RSS (all) | HN arXiv