Ming Tang

4 papers Southern University of Science and Technology

• FOCUS: Unified Vision-Language Modeling for Interactive Editing Driven by Referential Segmentation
• PhysVLM-AVR: Active Visual Reasoning for Multimodal Large Language Models in Physical Environments
• SCOUT: Teaching Pre-trained Language Models to Enhance Reasoning via Flow Chain-of-Thought
• Tackling Biased Evaluators in Dueling Bandits