ML Newsnew | past | best | rss | submit about
Stories from October 22, 2025 (UTC)
Go back a day, month, or year. Go forward a day.
1. The Dragon Hatchling: The missing link between the transformer and brain models (arxiv.org)
134 points by thatxliner 347 days ago | hide | past | pdf | 99 comments
2. The Free Transformer (arxiv.org)
6 points by aaraujo002 346 days ago | hide | past | pdf | discuss
3. A Novel Spinor-Based Embedding Model for Transformers (arxiv.org)
4 points by haxiomic 346 days ago | hide | past | pdf | discuss
4. Scaling Reinforcement Learning for Trillion-Scale Thinking Model (arxiv.org)
4 points by omarsar 347 days ago | hide | past | pdf | discuss
5. Large Language Models Inference Engines Based on Spiking Neural Networks (arxiv.org)
3 points by PaulHoule 347 days ago | hide | past | pdf | discuss
6. Poisoning Attacks on LLMs Require a Near-Constant Number of Poison Samples (arxiv.org)
2 points by ievans 346 days ago | hide | past | pdf | discuss
7. A tiny spectral PMF estimator for large discrete supports (arxiv.org)
2 points by alexshtf 347 days ago | hide | past | pdf | discuss
8. Can We Trust Functionally Correct Patches Generated by Code Agents? (arxiv.org)
1 point by bikenaga 347 days ago | hide | past | pdf | discuss
9. Grasp Any Region: Precise, Contextual Pixel Understanding for Multimodal LLMs (arxiv.org)
1 point by badmonster 347 days ago | hide | past | pdf | discuss
10. Query Decomposition for RAG (arxiv.org)
1 point by salkahfi 347 days ago | hide | past | pdf | discuss
11. Thinking Sparks: Emergent Attention Heads in Reasoning Models (arxiv.org)
1 point by diwank 347 days ago | hide | past | pdf | discuss
About | RSS | RSS (all) | HN arXiv