Research

Multimodal Large Language Models

• Multimodal Understanding & Reasoning
• Multi-Image Understanding
• Multi-Turn Multimodal Interaction
• Multimodal Reinforcement Learning
• Reasoning Segmentation

Vision-Language-Action & Embodied AI

• Vision-Language-Action Models
• Robot Learning
• Multimodal Robot Manipulation
• Embodied Reasoning

Visual Recognition & Understanding

• Semantic Segmentation
• Open-Vocabulary Recognition
• Anomaly Detection
• Super-Resolution

Learning & Adaptation

• Domain Generalization
• Parameter-Efficient Fine-Tuning
• Knowledge Distillation
• Self-Play Learning
• Reinforcement Learning

Efficient Deep Learning

• Efficient Model Training & Inference
• Distributed Training
• Memory-Efficient Deep Learning
• Model Adaptation & Optimization