Core Research
Multimodal Emotion Understanding
Modeling emotion from speech, vision, and text with depth-aware representations.
Hi, I'm
Zhishuo
Ph.D. candidate in Computer Science, focusing on multimodal learning, affective computing, and robust speech understanding.
NowCurrently at PolyU · Hong Kong from Sep 2026
About
I am a Ph.D. candidate in Computer Science at Sichuan University. My research focuses on multimodal learning, affective computing, and robust speech understanding, with particular interests in multimodal sentiment analysis, cross-modal contrastive optimization, noise-resilient speech recognition, and emotion-aware agent workflows. I care about research that remains interpretable and generalizes under real-world conditions.
Research Focus
Systems
LLM + MoE Systems
Task-adaptive routing and efficient expert collaboration for better generalization.
Impact
Applied AI Products
Bridging research and deployment through reliable workflows and automation.
Selected Projects
work in progress
Research:
HEME
Hierarchical emotion modeling with adaptive multi-level mixture-of-experts.
Platform:
Emotion Agent Stack
End-to-end pipeline for multimodal emotion analysis and conversational AI.
Workflow:
AV-RISE
Hierarchical cross-modal denoising for robust audio-visual speech representation under noisy real-world conditions.
Tooling:
Paper-to-Product Toolkit
Toolchain for transforming research prototypes into reproducible demos.
News
from the notebook- 2026🌉 In September 2026, I’ll be in Hong Kong for a new chapter of joint Ph.D. training at PolyU and SCU—connecting my research across Chengdu and Hong Kong.
- 2025🎉 Our paper "AV-RISE: Hierarchical Cross-Modal Denoising for Learning Robust Audio-Visual Speech Representation" is accepted at ACM MM 2025.
- 2024📖 Published "WinNet: Make Only One Convolutional Layer Effective for Time Series Forecasting" in ICIC 2025.
- 2024🎉 Our paper "AMG-AVSR: Adaptive Modality Guidance for Audio-Visual Speech Recognition via Progressive Feature Enhancement" is accepted at ACML 2024.