AI Research Papers Daily

Direct Nash Optimization: Teaching Language Models to Self-Improve with General Preferences

Stream of Search (SoS): Learning to Search in Language

No "Zero-Shot" Without Exponential Data: Pretraining Concept Frequency Determines Multimodal Model Performance

AutoWebGLM: Bootstrap And Reinforce A Large Language Model-based Web Navigating Agent

CantTalkAboutThis: Aligning Language Models to Stay on Topic in Dialogues

Social Skill Training with Large Language Models

RL for Consistency Models: Faster Reward Guided Text-to-Image Generation

Chinese Tiny LLM: Pretraining a Chinese-Centric Large Language Model

Robust Gaussian Splatting

Sigma: Siamese Mamba Network for Multi-Modal Semantic Segmentation