Li Xiangtian

Li Xiangtian

he/him

Researcher focusing on Large Language Model Post-training, Reinforcement Learning, Multi-agent Systems, and Multimodal AI. Previously worked on Embodied AI.

Multimodal Large Language Model Chain-of-Thought

发布时间：

Overview

This project explores Chain-of-Thought reasoning methods for multimodal large language models (MLLMs), enhancing their reasoning capabilities when processing both visual and textual information.

Key Features

  • CoT Reasoning: Implementing and improving Chain-of-Thought reasoning for MLLMs
  • Multimodal Integration: Combining vision and language understanding
  • Reasoning Enhancement: Better step-by-step reasoning in complex multimodal tasks
  • Evaluation Framework: Comprehensive evaluation of reasoning capabilities

Technologies

  • PyTorch
  • Multimodal Large Language Models
  • Chain-of-Thought Reasoning
  • Vision-Language Models