Submitted by akhaliq 59 Direct Nash Optimization: Teaching Language Models to Self-Improve with General Preferences · 6 authors 1
Submitted by akhaliq 27 No "Zero-Shot" Without Exponential Data: Pretraining Concept Frequency Determines Multimodal Model Performance · 8 authors 1
Submitted by akhaliq 23 CantTalkAboutThis: Aligning Language Models to Stay on Topic in Dialogues · 4 authors 5
Submitted by akhaliq 23 AutoWebGLM: Bootstrap And Reinforce A Large Language Model-based Web Navigating Agent · 11 authors 3
Submitted by akhaliq 14 RL for Consistency Models: Faster Reward Guided Text-to-Image Generation · 5 authors 3
Submitted by akhaliq 11 Chinese Tiny LLM: Pretraining a Chinese-Centric Large Language Model · 16 authors 2
Submitted by akhaliq 5 Sigma: Siamese Mamba Network for Multi-Modal Semantic Segmentation · 7 authors 1