ML Newsnew | past | best | rss | submit about
Stories from May 15, 2026 (UTC)
Go back a day, month, or year. Go forward a day.
1. ExploitGym: Can AI agents turn bugs into exploits? (arxiv.org)
3 points by p_stuart82 142 days ago | hide | past | pdf | discuss
2. Demystifying the Silence of Correctness Bugs in PyTorch Compiler (arxiv.org)
3 points by matt_d 142 days ago | hide | past | pdf | discuss
3. Negation Neglect: When models fail to learn negations in training (arxiv.org)
3 points by Timofeibu 142 days ago | hide | past | pdf | discuss
4. Known by Their Actions: Fingerprinting LLM Browser Agents via UI Traces (arxiv.org)
3 points by sbulaev 142 days ago | hide | past | pdf | 1 comment
5. AI co-mathematician: Accelerating mathematicians with agentic AI (arxiv.org)
3 points by aoki 143 days ago | hide | past | pdf | discuss
6. AI Agents Modulate Their Language When Framed as Being Watched (arxiv.org)
2 points by vinicius-covas 142 days ago | hide | past | pdf | discuss
7. Qwen-Image-2.0 Technical Report (arxiv.org)
2 points by gmays 142 days ago | hide | past | pdf | discuss
8. Systematically Auditing AI Agent Benchmarks with BenchJack (arxiv.org)
1 point by matt_d 143 days ago | hide | past | pdf | discuss
About | RSS | RSS (all) | HN arXiv