collaborators

6 papers

eess.AS2026

The WER Trap: Shattering the Illusion of Unified Tokens in Speech Language Models

Xiangyu Zhang, Yuxin Li, Haoyang Zhang +5

The pursuit of a "unified" discrete token for both speech understanding and generation has led the Speech Language Model (SLM) community to heavily rely on Word Error Rate (WER) --…

cs.LG2026

Learning Invariant Modality Representation for Robust Multimodal Learning from a Causal Inference Perspective

Sijie Mai, Shiqin Han

Multimodal affective computing aims to predict humans' sentiment, emotion, intention, and opinion using language, acoustic, and visual modalities. However, current models often lea…

cs.LG2026

Addressing Missing and Noisy Modalities in One Solution: Unified Modality-Quality Framework for Low-quality Multimodal Data

Sijie Mai, Shiqin Han, Haifeng Hu

Multimodal data encountered in real-world scenarios are typically of low quality, with noisy modalities and missing modalities being typical forms that severely hinder model perfor…

cs.CV2026

CaReFlow: Cyclic Adaptive Rectified Flow for Multimodal Fusion

Sijie Mai, Shiqin Han

Modality gap significantly restricts the effectiveness of multimodal fusion. Previous methods often use techniques such as diffusion models and adversarial learning to reduce the m…

cs.CL2026

Uncertainty-Aware Collaborative System of Large and Small Models for Multimodal Sentiment Analysis

Shiqin Han, Manning Gao, Menghua Jiang +3

Multimodal Large Language Models (MLLMs) have notably enhanced the performance of Multimodal Sentiment Analysis (MSA), yet their massive parameter scale leads to excessive resource…

cs.CV2026

GRCF: Two-Stage Groupwise Ranking and Calibration Framework for Multimodal Sentiment Analysis

Manning Gao, Leheng Zhang, Shiqin Han +3

Most Multimodal Sentiment Analysis research has focused on point-wise regression. While straightforward, this approach is sensitive to label noise and neglects whether one sample i…