Papers by Mingjian Yang

1 papers
CaM-HG: Causal-Enhanced MoE and Hypergraphs Network for Incomplete Multimodal Emotion Recognition in Conversations (2026.findings-acl)

Copied to clipboard

Challenge: Existing methods that focus on statistical reconstruction often fail to bridge these gaps, effectively leaving semantic holes.
Approach: They propose a Causal-Enhanced Mixture-of-Experts and Hypergraph Network to bridge missing features . they use experts to synthesize missing features that are realistic and causally consistent .
Outcome: The proposed model synthesizes missing features that are realistic and causally consistent . it surpasses benchmarks on IEMOCAP, CMU-MOSI, and CMU MOSEI by 1.43% and 1.25% .

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations