Surfer-H Meets Holo1: Cost-Efficient Web Agent Powered by Open Weights Paper • 2506.02865 • Published Jun 3 • 33
Confidence Is All You Need: Few-Shot RL Fine-Tuning of Language Models Paper • 2506.06395 • Published Jun 5 • 132
Will It Still Be True Tomorrow? Multilingual Evergreen Question Classification to Improve Trustworthy QA Paper • 2505.21115 • Published May 27 • 139
cadrille: Multi-modal CAD Reconstruction with Online Reinforcement Learning Paper • 2505.22914 • Published May 28 • 36
When Less is Enough: Adaptive Token Reduction for Efficient Image Representation Paper • 2503.16660 • Published Mar 20 • 72