5 papers
Shedding the Facades, Connecting the Domains: Detecting Shifting Multimodal Hate Video with Test-Time Adaptation
Jiao Li, Jian Lang, Xikai Tang +6
Hate Video Detection (HVD) is crucial for online ecosystems. Existing methods assume identical distributions between training (source) and inference (target) data. However, hateful…
Nip Rumors in the Bud: Retrieval-Guided Topic-Level Adaptation for Test-Time Fake News Video Detection
Jian Lang, Rongpei Hong, Ting Zhong +2
Fake News Video Detection (FNVD) is critical for social stability. Existing methods typically assume consistent news topic distribution between training and test phases, failing to…
TAMEing Long Contexts in Personalization: Towards Training-Free and State-Aware MLLM Personalized Assistant
Rongpei Hong, Jian Lang, Ting Zhong +2
Multimodal Large Language Model (MLLM) Personalization is a critical research problem that facilitates personalized dialogues with MLLMs targeting specific entities (known as perso…
From Shallow Humor to Metaphor: Towards Label-Free Harmful Meme Detection via LMM Agent Self-Improvement
Jian Lang, Rongpei Hong, Ting Zhong +3
The proliferation of harmful memes on online media poses significant risks to public health and stability. Existing detection methods heavily rely on large-scale labeled data for t…
Modality-Balanced Collaborative Distillation for Multi-Modal Domain Generalization
Xiaohan Wang, Zhangtao Cheng, Ting Zhong +2
Weight Averaging (WA) has emerged as a powerful technique for enhancing generalization by promoting convergence to a flat loss landscape, which correlates with stronger out-of-dist…