about
Stories from November 4, 2026 (UTC)
Go back a day, month, or year. Go forward a day.
1. Multi-Token Prediction Done Right (arxiv.org)
13 points by matt_d 13 days ago | hide | past | pdf | 4 comments
2. LLMs tested on historical prediction markets, NONE outperformed the market (arxiv.org)
4 points by dataMike 13 days ago | hide | past | pdf | 2 comments
3. Length Is Cheap, Competition Is Not: Attention Predicts Context Rot in Retrieval (arxiv.org)
3 points by liusci 13 days ago | hide | past | pdf | discuss
4. You don't need long context (arxiv.org)
3 points by craigmart 13 days ago | hide | past | pdf | discuss
5. Foundations of Large Language Models (arxiv.org)
2 points by manojbajaj95 13 days ago | hide | past | pdf | discuss
6. Hinted Scaling Laws (arxiv.org)
2 points by matt_d 14 days ago | hide | past | pdf | discuss
7. EdgeDAE: Acceleration of Diffusion Action Experts for Real-Time Physical AI (arxiv.org)
1 point by teleforce 13 days ago | hide | past | pdf | discuss
8. Automated grounding verification of AI statements about chest radiographs (arxiv.org)
1 point by mrkn1 13 days ago | hide | past | pdf | discuss
9. SpecPilot: Autonomous Algorithm Discovery and Systems Optimization for SpecDec (arxiv.org)
1 point by matt_d 13 days ago | hide | past | pdf | discuss