ML Newsnew | past | best | rss | submit about
Stories from July 7, 2025 (UTC)
Go back a day, month, or year. Go forward a day.
1. Mercury: Ultra-fast language models based on diffusion (arxiv.org)
576 points by PaulHoule on Jul 7, 2025 | hide | past | pdf | 242 comments
2. Query Agnostic Adversarial Triggers for Reasoning Models (arxiv.org)
5 points by layer8 on Jul 7, 2025 | hide | past | pdf | discuss
3. Because We Have LLMs, We Can and Should Pursue Agentic Interpretability (arxiv.org)
4 points by favoboa on Jul 7, 2025 | hide | past | pdf | discuss
4. AsyncFlow: An Asynchronous Streaming RL Framework for LLM Post-Training (arxiv.org)
4 points by robertnishihara on Jul 7, 2025 | hide | past | pdf | discuss
5. Sequential Diagnosis with Language Models (arxiv.org)
4 points by herrherr on Jul 7, 2025 | hide | past | pdf | discuss
6. Frustratingly Simple Retrieval for Challenging, Reasoning-Intensive Benchmarks (arxiv.org)
2 points by amirkabbara on Jul 7, 2025 | hide | past | pdf | discuss
7. Segmentation and Representation Trade-Offs in Chemistry-Aware RAG (arxiv.org)
2 points by PaulHoule on Jul 7, 2025 | hide | past | pdf | discuss
About | RSS | RSS (all) | HN arXiv