Caixin Kang
7 papers · 2022–2026 · 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
(16)
🔥
Unstoppable · Bronze
❓
The Questioner
Venues
Top co-authors
Research topics
Artificial Intelligence
(5)
Core AI · Artificial Intelligence
(5)
Computer Vision
(3)
Machine Learning
(2)
Analysis
(2)
Deep Learning
(1)
Application Areas
(1)
Applications
(1)
Core AI · Computer Vision
(1)
Domain-Specific
(1)
Learning Types · Machine Learning
(1)
Learning Types · Deep Learning
(1)
Optimization & Theory
(1)
Keywords
vision-language model
(2)
multimodal large language model
(2)
adversarial attack
(2)
multimodal learning
(1)
autonomous driving
(1)
corruption robustness
(1)
distribution shift
(1)
3d object detection
(1)
neural radiance field
(1)
image classifier
(1)
jailbreak attack
(1)
video question answering
(1)
causal chain
(1)
cross-modal attention
(1)
lidar-camera fusion
(1)
safety mechanism
(1)
spatio-temporal reasoning
(1)
viewpoint robustness
(1)
visual-textual alignment
(1)
adversarial viewpoint
(1)
Papers
CaST-Bench: Benchmarking Causal Chain-Grounded Spatio-Temporal Reasoning for Video Question Answering
CVPR 2026
Multi-speaker Attention Alignment for Multimodal Social Interaction
CVPR 2026
AdvDreamer Unveils: Are Vision-Language Models Truly Ready for Real-World 3D Variations?
ICCV 2025
Jailbreaking Multimodal Large Language Models via Shuffle Inconsistency
ICCV 2025
DIFFender: Diffusion-Based Adversarial Defense against Patch Attacks
ECCV 2024
Benchmarking Robustness of 3D Object Detection to Common Corruptions
CVPR 2023
ViewFool: Evaluating the Robustness of Visual Recognition to Adversarial Viewpoints
NeurIPS 2022