7 papers
DynaForcing: Overcoming Dynamic Collapse in Self-Forcing Distillation for Streaming Avatar Generation
Yubo Huang, Sirui Zhao, Xinchen Yao +5
Audio-driven avatar generation requires realistic lip-sync, expressive motion, and real-time streaming. Recent work achieves the latter via self-forcing with Distribution Matching…
ActFER: Agentic Facial Expression Recognition via Active Tool-Augmented Visual Reasoning
Shifeng Liu, Zhengye Zhang, Sirui Zhao +7
Recent advances in Multimodal Large Language Models (MLLMs) have created new opportunities for facial expression recognition (FER), moving it beyond pure label prediction toward re…
Benchmarking Large Language Models for Conversational Question Answering in Multi-instructional Documents
Shiwei Wu, Chen Zhang, Yan Gao +4
Instructional documents are rich sources of knowledge for completing various tasks, yet their unique challenges in conversational question answering (CQA) have not been thoroughly…
Leveraging Entity Information for Cross-Modality Correlation Learning: The Entity-Guided Multimodal Summarization
Yanghai Zhang, Ye Liu, Shiwei Wu +4
The rapid increase in multimedia data has spurred advancements in Multimodal Summarization with Multimodal Output (MSMO), which aims to produce a multimodal summary that integrates…
From a Social Cognitive Perspective: Context-aware Visual Social Relationship Recognition
Shiwei Wu, Chao Zhang, Joya Chen +4
People's social relationships are often manifested through their surroundings, with certain objects or interactions acting as symbols for specific relationships, e.g., wedding ring…
NoteLLM-2: Multimodal Large Representation Models for Recommendation
Chao Zhang, Haoxin Zhang, Shiwei Wu +6
Large Language Models (LLMs) have demonstrated exceptional proficiency in text understanding and embedding tasks. However, their potential in multimodal representation, particularl…