Retrospective Harness Optimization: Improving LLM Agents via Self-Preference over Trajectory Rollouts Paper • 2606.05922 • Published 6 days ago • 47
AURA: Action-Gated Memory for Robot Policies at Constant VRAM Paper • 2606.02775 • Published 9 days ago • 3
On the Scaling of PEFT: Towards Million Personal Models of Trillion Parameters Paper • 2606.02437 • Published 10 days ago • 224
Data-Gouv-ML/effectifs-de-nantes-universite-le-personnel Viewer • Updated 10 days ago • 4.49k • 62 • 1
Forecasting Scientific Progress with Artificial Intelligence Paper • 2605.22681 • Published 21 days ago • 43
EvalVerse: Pipeline-Aware and Expert-Calibrated Benchmarking for Professional Cinematic Video Generation Paper • 2605.23271 • Published 20 days ago • 79