about
Stories from October 6, 2026 (UTC)
Go back a day, month, or year. Go forward a day.
1. UniEvo-VL: Self-Distillation Training for Multimodal Model Self-Improvement (arxiv.org)
18 points by gmays 42 days ago | hide | past | pdf | 3 comments
2. Language Models That Play Chess (2700 Elo) and Explain Their Moves (arxiv.org)
5 points by buzzy_hacker 43 days ago | hide | past | pdf | discuss
3. What stops a small language model from driving a database agent (arxiv.org)
2 points by abdullahk0634 42 days ago | hide | past | pdf | 1 comment
4. Measuring the Experimental Research Taste of AI Systems Against Human Experts (arxiv.org)
2 points by Betelbuddy 42 days ago | hide | past | pdf | discuss
5. MaLiang-Harness: Programmable Image and Video Generation (arxiv.org)
2 points by alok-g 42 days ago | hide | past | pdf | discuss
6. Base Models Can Reason by Taking a Cue from Training Data (arxiv.org)
2 points by sbulaev 42 days ago | hide | past | pdf | discuss
7. Passing the Test You Trained On: Re-Evaluating Prompt-Injection Detectors (arxiv.org)
2 points by sbulaev 43 days ago | hide | past | pdf | discuss
8. Improving Agents by Bootstrapping Experientially-Learned Environmental Knowledge (arxiv.org)
2 points by azhenley 43 days ago | hide | past | pdf | discuss
9. Gradients Leakage in Split Language Models (arxiv.org)
1 point by hevalon 42 days ago | hide | past | pdf | discuss