Xiu Su

6

Papers

58

Total Citations

Papers (6)

VideoEspresso: A Large-Scale Chain-of-Thought Dataset for Fine-Grained Video Reasoning via Core Frame Selection

L-MTP: Leap Multi-Token Prediction Beyond Adjacent Context for Large Language Models

Perturbating, Tuning, and Collaborating: Harnessing Vision Foundation Models for Single Domain Generalization on Medical Imaging

CounterPC: Counterfactual Feature Realignment for Unsupervised Domain Adaptation on Point Clouds

Seeing Beyond Noise: Joint Graph Structure Evaluation and Denoising for Multimodal Recommendation

Detecting Any instruction-to-answer interaction relationship:Universal Instruction-to-Answer Navigator for Med-VQA