Jun Xiao

6 papers Zhejiang University

• Counterfactual Evolution of Multimodal Datasets via Visual Programming
• EOC-Bench: Can MLLMs Identify, Recall, and Forecast Objects in an Egocentric World?
• Janus-Pro-R1: Advancing Collaborative Visual Comprehension and Generation via Reinforcement Learning
• Let LRMs Break Free from Overthinking via Self-Braking Tuning
• Mind the Gap: Bridging Thought Leap for Improved Chain-of-Thought Tuning
• SegGraph: Leveraging Graphs of SAM Segments for Few-Shot 3D Part Segmentation