Jingyao Li

DreamOmni2: Multimodal Instruction-based Editing and Generation

Answer-Consistent Chain-of-thought Reinforcement Learning For Multi-modal Large Langauge Models

Elevating Large Language Models with Module-of-Thought

Understanding the Mixture-of-Experts with Nadaraya-Watson Kernel

MGM-Omni: Scaling Omni LLMs to Personalized Long-Horizon Speech

DynamicBench: Evaluating Real-Time Report Generation in Large Language Models

End-to-End QA Construction Pipeline for Continual Pre-training of Large Language Models

Multi-Scale Group Relative Policy Optimization for Large Language Models

IndustryGPT: A Large Language Model for Industrial Domain-Specific Question Answering

DLoFT: Gradient-Decoupled Fine-Tuning for Generalizable Long Chain-of-Thought Reasoning

DAPE V2: Process Attention Score as Feature Map for Length Extrapolation