Tianyang Han
5 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
(13)
🐣
Hot Topic Early Bird
Top co-authors
Research topics
Artificial Intelligence
(3)
Deep Learning
(3)
Core AI
(3)
Learning Types · Deep Learning
(3)
Machine Learning
(2)
Computer Vision
(1)
Natural Language Processing
(1)
Application Areas
(1)
Generation · Natural Language Processing
(1)
Generation · Computer Vision
(1)
Learning Types · Machine Learning
(1)
Models
(1)
Optimization & Theory
(1)
Keywords
multimodal large language model
(2)
multimodal learning
(2)
transfer learning
(1)
model robustness
(1)
instruction tuning
(1)
harmful content
(1)
safety alignment
(1)
diffusion model
(1)
adversarial defense
(1)
spurious correlation
(1)
vision-language model
(1)
harmful content detection
(1)
data synthesis
(1)
image customization
(1)
harm detection
(1)
personalized dialogue
(1)
visual instruction
(1)
visibility-aware attention
(1)
identity consistency
(1)
benchmark evaluation
(1)
Papers
PositionIC: Unified Position and Identity Consistency for Image Customization
CVPR 2026
Personalized Visual Instruction Tuning
ICLR 2025
MLLM-Protector: Ensuring MLLM’s Safety without Hurting Performance
EMNLP 2024
Strengthening Multimodal Large Language Model with Bootstrapped Preference Optimization
ECCV 2024
The Instinctive Bias: Spurious Images lead to Illusion in MLLMs
EMNLP 2024