Weitai Kang

5

Papers

40

Total Citations

Papers (5)

SegVG: Transferring Object Bounding Box to Segmentation for Visual Grounding

Token Transformation Matters: Towards Faithful Post-hoc Explanation for Vision Transformer

InfantAgent-Next: A Multimodal Generalist Agent for Automated Computer Interaction

Robin3D: Improving 3D Large Language Model via Robust Instruction Tuning

On the Faithfulness of Vision Transformer Explanations