activity
20242026
most citedSZTU-CMU at MER2024: Improving Emotion-LLaMA with Conv-Attention for Multimodal Emotion Recognition

8 citations · 8 across the 5 of their papers we have counts for

collaborators

9 papers

cs.CV2026

Preference Score Distillation: Leveraging 2D Rewards to Align Text-to-3D Generation with Human Preference

Jiaqi Leng, Shuyuan Tu, Haidong Cao +4

Human preference alignment presents a critical yet underexplored challenge for diffusion models in text-to-3D generation. Existing solutions typically require task-specific fine-tu…

cs.CV2026

Emotion-LLaMAv2 and MMEVerse: A New Framework and Benchmark for Multimodal Emotion Understanding

Xiaojiang Peng, Jingyi Chen, Zebang Cheng +11

Understanding human emotions from multimodal signals poses a significant challenge in affective computing and human-robot interaction. While multimodal large language models (MLLMs…

cs.CV2026

ArcFlow: Unleashing 2-Step Text-to-Image Generation via High-Precision Non-Linear Flow Distillation

Zihan Yang, Shuyuan Tu, Licheng Zhang +3

Diffusion models have achieved remarkable generation quality, but they suffer from significant inference cost due to their reliance on multiple sequential denoising steps, motivati…

cs.CV2025

FlashPortrait: 6x Faster Infinite Portrait Animation with Adaptive Latent Prediction

Shuyuan Tu, Yueming Pan, Yinming Huang +6

Current diffusion-based acceleration methods for long-portrait animation struggle to ensure identity (ID) consistency. This paper presents FlashPortrait, an end-to-end video diffus…

cs.CV2025

StableAvatar: Infinite-Length Audio-Driven Avatar Video Generation

Shuyuan Tu, Yueming Pan, Yinming Huang +6

Current diffusion models for audio-driven avatar video generation struggle to synthesize long videos with natural audio synchronization and identity consistency. This paper present…

cs.CV2025

PersonaAnimator: Personalized Motion Transfer from Unconstrained Videos

Ziyun Qian, Runyu Xiao, Shuyuan Tu +7

Recent advances in motion generation show remarkable progress. However, several limitations remain: (1) Existing pose-guided character motion transfer methods merely replicate moti…