Author

Weitai Kang

Observed name: Kang, Weitai

Institution: University of Illinois Chicago

Observed institutions: Illinois Institute of Technology, University of Illinois Chicago

ORCID: 0009-0007-6484-0665

Observed ORCID: 0009-0007-6484-0665

OpenAlex ID: A5113395507

Robin3D Improving 3D Large Language Model via Robust Instruction Tuning

2025 · Weitai Kang, Haifeng Huang, et al. · IEEE/CVF International Conference on Computer Vision (ICCV) · 25

PDF

On the Faithfulness of Vision Transformer Explanations

2024 · Junyi Wu, Weitai Kang, et al. · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · 23

PDF

Interpolating Video-LLMs: Toward Longer-sequence LMMs in a Training-free Manner

2024 · Shang, Yuzhang, Xu, Bingxin, et al. · arXiv (Cornell University) · 18

PDF

SegVG: Transferring Object Bounding Box to Segmentation for Visual Grounding

2024 · Weitai Kang, Gaowen Liu, et al. · Lecture notes in computer science · 17

PDF

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

2024 · Junyi Wu, Bin Duan, et al. · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · 17

PDF

Intent3D: 3D Object Detection in RGB-D Scans Based on Human Intention

2024 · Kang, Weitai, Qu, Mengxue, et al. · arXiv (Cornell University) · 14

PDF

Visual Grounding with Attention-Driven Constraint Balancing

2025 · Weitai Kang, Luowei Zhou, et al. · ACM International Conference on Multimedia (ACM MM) · 10

PDF

ACTRESS: Active Retraining for Semi-supervised Visual Grounding

2024 · Kang, Weitai, Qu, Mengxue, et al. · arXiv (Cornell University) · 9

PDF

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

2025 · Bin Lei, Weitai Kang, et al. · neural information processing systems · 6