Xindi Wu

Visual Compositional Tuning

Actions as Language: Fine-Tuning VLMs into VLAs Without Catastrophic Forgetting

DD-Ranking: Rethinking the Evaluation of Dataset Distillation

Where is Motion From? Scalable Motion Attribution for Video Generation Models

Beyond Objects: Contextual Synthetic Data Generation for Fine-Grained Classification

SWE-bench Multimodal: Do AI Systems Generalize to Visual Software Domains?