I am currently pursuing my PhD in the Institute for Intelligent Collaborative Computing at UESTC (电子科技大学).

I was guided by Tao He and worked closely with Dongyang Zhang, and Guiduo Duan at Ubiquitous Intelligence and Trusted Services Key Laboratory of Sichuan Province. I am currently doing an internship at the VIVO BlueImage Laboratory and am being guided by Qingnan Fan.

My research interest includes Multimodal perception, MLLM Post-training, Affective computing. The future research direction will focus on Unified Multimodal Models (UMM) and Omni-modal models. I have published 15+ papers

🔥 News

• 2026.04: 🧱 Begin my research internship at VIVO.
• 2026.02: 🎉 Two paper are accepted by CVPR 2026!
• 2026.01: 🎉 One paper is accepted by ACL 2026!
• 2026.01: 🎉 Two paper are accepted by ICASSP 2026!
• 2025.11: 🎉 Two paper are accepted by AAAI 2026!
• 2025.03: 🎉 One paper is accepted by CVPR 2025!
• 2024.02: 🎉 One paper is accepted by COLING 2024!
• 2023.05: 🎉 One paper is accepted by ICANN 2023!

📝 Publications

† indicates the corresponding author

🧡 Affective Computing

AAAI 2026

TiCAL:Typicality-Based Consistency-Aware Learning for Multimodal Emotion Recognition
Wen Yin, Siyu Zhan, Cencen Liu, XIN Hu, Guiduo Duan, Xiurui Xie, Yuan-Fang Li, Tao He

• We propose TiCAL, a novel framework that performs dynamic multi-stage fusion by leveraging inter-modal consistency and unimodal typicality, mimicking human-like emotion perception.
• TiCAL assess unimodal emotional pseudo-labels and its typicality, then defined the modal consistency quantification matrix, enabling robust MER.

CVPR 2025

Knowledge-Aligned Counterfactual-Enhancement Diffusion Perception for Unsupervised Cross-Domain Visual Emotion Recognition
Wen Yin, Yong Wang , Guiduo Duan, Dongyang Zhang, Xin Hu, Yuan-Fang Li, Tao He

• We introduce Unsupervised Cross-Domain Visual Emotion Recognition (UCDVER).
• we propose a Knowledge-aligned Counterfactual enhancement Diffusion Perception (KCDP) framework to learn domain-agnostic knowledge across diverse emotion domains.

• ACL Finding 2026 CaM-HG: Causal-Enhanced MoE and Hypergraphs Network for Incomplete Multimodal Emotion Recognition in Conversations, Mingjian Yang, Yong Wang, Peng Liu, Wen Yin†.

• ICASSP 2026 DGSDNet: Dual-Graph Spectral Diffusion Network for Incomplete Multimodal Emotion Recognition in Conversations, Mingjian Yang, Yong Wang, Peng Liu, Wen Yin†.
• COLING 2024 SynPrompt: Syntax-aware Enhanced Prompt Engineering for Aspect-based Sentiment Analysis, Wen Yin, Cencen Liu, Yi Xu, Ahmad Raza Wahla, Huang Yiting, Dezhang Zheng.
• ICANN 2023 Prompt-oriented Fine-tuning Dual Bert for Aspect-Based Sentiment Analysis, Wen Yin, Yi Xu, Cencen Liu, Dezhang Zheng, Qi Wang, Chuanjie Liu

✨ Multimodal Perception and MLLM

• AAAI 2026 CaT-Diff: Cascaded Text-enhanced Diffusion Model for Time-Series Imputation, Changjian Xu, Yong Wang, Ruizheng Huang, Zhicheng Zhang, Wen Yin, Kexin Li .

Others

• ICASSP 2026 Toward Cross-Dataset Clothes-Changing Re-Identification via Efficient Decoupled Adaptive Matching, Wen Yin, Qiuran Li, …, Tao He.
• CVPR 2026 Can We Build Scene Graphs, Not Classify Them? FlowSG: Progressive Image-Conditioned Scene Graph Generation with Flow Matching, XIN Hu, Ke Qin, Wen Yin, …Tao He.
• CVPR Finding 2026 AlignVAR: Towards Globally Consistent Visual Autoregression for Image Super-Resolution, Cencen Liu, Dongyang Zhang, Wen Yin, Jielei Wang, Guangchun Luo.
• Neurocomputing SRMamba-T: Exploring the hybrid Mamba-Transformer network for Single Image Super-Resolution, Cencen Liu, Dongyang Zhang, Guoming Lu, Wen Yin, Jielei Wang, Guangchun Luo.
• ITNLP 2023 Structure-aware Table-to-Text Generation with Prefix-tuning, Cencen Liu, Yi Xu, Wen Yin, Dezhang Zheng.
• CISDS 2023 Increasing the Transferability of Adversarial Attack by Depthwise Separation Convolution, Xida Cao, Wen Yin, Guang Kou, Jia Chen.

📖 Educations

• 2017.09 - 2021.06, Undergraduate, Henan University of Economics and Law, Zhengzhou.
• 2021.09 - 2024.06, Master, University of Electronic Science and Technology of China, Chengdu.
• 2024.09 - now, Phd, University of Electronic Science and Technology of China, Chengdu.

💼 Internships

BlueImage Lab, VivoResearch Intern, focusing on Unified Multimodal Model (UMM)Supervisor: Qingnan Fan

2026.04 - Present

Personality Perception Department, Megvii TechnologyResearch Intern, focusing on MLLM and Post-training.

2025.09 - 2026.03

🎖 Honors and Awards

• 2025.11 Yanbao Special Scholarship
• 2025.10 Academic Scholarship
• 2024.01 Silver Star Scholarship
• 2023.10 Academic Scholarship
• 2022.12 Second prize of the National University Computer Ability Challenge
• 2021.05 Huang Tingfang Scholarship