Weitai Kang
6 papers · 2024–2026 · 4 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓
🌍
Conference Polyglot · Bronze
🌉
Interdisciplinary Bridge · Bronze
🗺️
Taxonomy Completionist
(17)
Top co-authors
Research topics
Computer Vision
(5)
Artificial Intelligence
(4)
Deep Learning
(4)
Core AI · Artificial Intelligence
(4)
Machine Learning
(3)
Analysis
(3)
Architectures
(3)
Core AI · Computer Vision
(2)
Learning Types · Machine Learning
(2)
Optimization & Theory · Machine Learning
(2)
Core Methods
(1)
Learning Types · Deep Learning
(1)
Optimization & Theory · Deep Learning
(1)
Processing
(1)
Techniques
(1)
Keywords
visual grounding
(4)
vision transformer
(2)
model interpretability
(2)
attention visualization
(2)
3d vision
(1)
referring expression
(1)
object localization
(1)
intention understanding
(1)
feature attribution
(1)
instruction tuning
(1)
saliency mapping
(1)
3d object detection
(1)
vision-language model
(1)
multimodal large language model
(1)
bounding box prediction
(1)
attention weight
(1)
post-hoc explanation
(1)
encoder-decoder architecture
(1)
explanation faithfulness
(1)
faithfulness evaluation
(1)
Papers
VGent: Visual Grounding via Modular Design for Disentangling Reasoning and Prediction
CVPR 2026
Intent3D: 3D Object Detection in RGB-D Scans Based on Human Intention
ICLR 2025
Robin3D: Improving 3D Large Language Model via Robust Instruction Tuning
ICCV 2025
On the Faithfulness of Vision Transformer Explanations
CVPR 2024
SegVG: Transferring Object Bounding Box to Segmentation for Visual Grounding
ECCV 2024
Token Transformation Matters: Towards Faithful Post-hoc Explanation for Vision Transformer
CVPR 2024