Lu Wang

NExT-OMNI: Towards Any-to-Any Omnimodal Foundation Models with Discrete Flow Matching

Learning Ordinal Probabilistic Reward from Preferences

GUI-R1: A Generalist R1-Style Vision-Language Action Model For GUI Agents

All in RLVR on Non-Verifiable Domains

Combination Generalization of Capability-Specific Neurons in LLMs

Entropy Scheduling in Reinforcement Learning for Large Language Models

BDQ: Bidirectional Diagonal Quantization for LLMs

Effective Interaction between Quantization and Low-Rank Decomposition based on LLMs

VCM: Vision Concept Modeling with Adaptive Vision Token Compression via Instruction Fine-Tuning

Scaling Law with Learning Rate Annealing