馃捇 Selected Publications
My complete publication record is available on Google Scholar. Each highlighted paper below includes a visual overview and direct links to its resources.
Do Unified Multimodal Models Think in One Space? A Lens Through Cross-Branch Steering
An intervention-based study of whether multimodal understanding and generation share a transferable semantic space.
Why Multimodal In-Context Learning Lags Behind? Unveiling the Inner Mechanisms and Bottlenecks
A mechanistic study of how multimodal in-context learning routes visual and textual evidence鈥攁nd where that reasoning pipeline falls short.
Paper coming soon 路 Code coming soon
AdaShield: Safeguarding Multimodal LLMs from Structure-based Attack via Adaptive Shield Prompting
Adaptive prompt shielding for defending multimodal language models against structure-based jailbreak attacks.
Discover and Align Taxonomic Context Priors for Open-world Semi-Supervised Learning
Learning taxonomic context priors to discover and align known and novel classes in open-world semi-supervised learning.
Out-of-Distributed Semantic Pruning for Robust Semi-Supervised Learning
A semantic-pruning approach that improves the reliability of semi-supervised learning under distribution shift.
AnyTalk: Multi-modal Driven Multi-domain Talking Head Generation
A multimodal framework for controllable talking-head generation across diverse identities and domains.