On the Generalization of SFT: A Reinforcement Learning Perspective with Reward Rectification Paper • 2508.05629 • Published 26 days ago • 168
REINA: Regularized Entropy Information-Based Loss for Efficient Simultaneous Speech Translation Paper • 2508.04946 • Published 27 days ago • 1
StrandDesigner: Towards Practical Strand Generation with Sketch Guidance Paper • 2508.01650 • Published about 1 month ago • 6
Phi-Ground Tech Report: Advancing Perception in GUI Grounding Paper • 2507.23779 • Published Jul 31 • 44
LayerCake: Token-Aware Contrastive Decoding within Large Language Model Layers Paper • 2507.04404 • Published Jul 6 • 21