Xiangyu Zhao

6 papers Shanghai Jiao Tong University

• Data Efficient Adaptation in Large Language Models via Continuous Low-Rank Fine-Tuning
• Envisioning Beyond the Pixels: Benchmarking Reasoning-Informed Visual Editing
• Envisioning Beyond the Pixels: Benchmarking Reasoning-Informed Visual Editing
• GeoRanker: Distance-Aware Ranking for Worldwide Image Geolocalization
• Process vs. Outcome Reward: Which is Better for Agentic RAG Reinforcement Learning
• UniTraj: Learning a Universal Trajectory Foundation Model from Billion-Scale Worldwide Traces