Publications

Towards Reliable Human Evaluations in Gesture Generation: Insights from a Community-Driven State-of-the-Art Benchmark

CVPR, 2026

Rajmund Nagy, Hendric Voss, Thanh Hoang-Minh, Mihail Tsakov, Teodor Nikolov, Zeyi Zhang, Tenglong Ao, Sicheng Yang, Shaoli Huang, Yongkang Cheng, M Hamza Mughal, Rishabh Dabral, Kiran Chhatre, Christian Theobalt, Libin Liu, Stefan Kopp, Rachel McDonnell, Michael Neff, Taras Kucherenko, Youngwoo Yoon, Gustav Eje Henter. (2026). "Towards Reliable Human Evaluations in Gesture Generation: Insights from a Community-Driven State-of-the-Art Benchmark." CVPR.

Egocentric Co-Pilot: Web-Native Smart-Glasses Agents for Assistive Egocentric AI

WWW, 2026

Sicheng Yang, Yukai Huang, Weitong Cai, Shitong Sun, Fengyi Fang, You He, Yiqiao Xie, Jiankang Deng, Hang Zhang, Jifei Song, Zhensong Zhang. (2026). "Egocentric Co-Pilot: Web-Native Smart-Glasses Agents for Assistive Egocentric AI." WWW.

CoordSpeaker: Exploiting Gesture Captioning for Coordinated Caption-Empowered Co-Speech Gesture Generation

CVPR, 2026

Fengyi Fang, Sicheng Yang, Wenming Yang. (2026). "CoordSpeaker: Exploiting Gesture Captioning for Coordinated Caption-Empowered Co-Speech Gesture Generation." CVPR.

Optimizing Multimodal LLMs for Egocentric Video Understanding: A Solution for the HD-EPIC VQA Challenge

Arxiv (CVPR 2025 EgoVis Workshop), 2026

Sicheng Yang*, Yukai Huang*, Shitong Sun, Weitong Cai, Jiankang Deng, Jifei Song, Zhensong Zhang. (2026). "Optimizing Multimodal LLMs for Egocentric Video Understanding: A Solution for the HD-EPIC VQA Challenge." Arxiv.

Plug-and-Play Clarifier: A Zero-Shot Multimodal Framework for Egocentric Intent Disambiguation

AAAI, 2026

Sicheng Yang, Yukai Huang, Weitong Cai, Shitong Sun, You He, Jiankang Deng, Hang Zhang, Jifei Song, Zhensong Zhang. (2026). "Plug-and-Play Clarifier: A Zero-Shot Multimodal Framework for Egocentric Intent Disambiguation." AAAI.

AutoMR: A Universal Time Series Motion Recognition Pipeline

Arxiv, 2025

Likun Zhang, Sicheng Yang, Zhuo Wang, Haining Liang, Junxiao Shen. (2025). "AutoMR: A Universal Time Series Motion Recognition Pipeline." Arxiv.

Duo Streamers: A Streaming Gesture Recognition Framework

Arxiv, 2025

Boxuan Zhu, Sicheng Yang, Zhuo Wang, Haining Liang, Junxiao Shen. (2025). "Duo Streamers: A Streaming Gesture Recognition Framework." Arxiv.

MambaTalk: Efficient Holistic Gesture Synthesis with Selective State Space Models

NeurIPS, 2024

Zunnan Xu, Yukang Lin, Haonan Han, Sicheng Yang, Ronghui Li, Yachao Zhang, Xiu Li. (2024). "MambaTalk: Efficient Holistic Gesture Synthesis with Selective State Space Models." NeurIPS, 20055-20080, doi: 10.52202/079017-0633.

Co-Speech Gesture Video Generation via Motion-Decoupled Diffusion Model

CVPR, 2024

Xu He, Qiaochu Huang, Zhensong Zhang, ZhiweiLin, Zhiyong Wu, Sicheng Yang, Minglei Li, Zhiyi Chen, Songcen Xu, Xiaofei Wu. (2024). "Co-Speech Gesture Video Generation via Motion-Decoupled Diffusion Model." CVPR, 2263-2273, doi: 10.1109/CVPR52733.2024.00220.

Conversational Co-Speech Gesture Generation via Modeling Dialog Intention, Emotion and Context with Diffusion Models

ICASSP, 2024

Haiwei Xue, Sicheng Yang, Zhensong Zhang, Zhiyong Wu, Minglei Li, Zonghong Dai, Helen Meng. (2024). "Conversational Co-Speech Gesture Generation via Modeling Dialog Intention, Emotion and Context with Diffusion Models." ICASSP, 8296-8300, doi: 10.1109/ICASSP48485.2024.10448208.

Freetalker: Controllable Speech and Text-Driven Gesture Generation Based on Diffusion Models for Enhanced Speaker Naturalness

ICASSP, 2024

Sicheng Yang, Zunnan Xu, Haiwei Xue, Yongkang Cheng, Shaoli Huang, Mingming Gong, Zhiyong Wu. (2024). "Freetalker: Controllable Speech and Text-Driven Gesture Generation Based on Diffusion Models for Enhanced Speaker Naturalness." ICASSP, 7945-7949, doi: 10.1109/ICASSP48485.2024.10447978.

Chain of Generation: Multi-Modal Gesture Synthesis via Cascaded Conditional Control

AAAI, 2024

Zunnan Xu, Yachao Zhang, Sicheng Yang, Ronghui Li, Xiu Li. (2024). "Chain of Generation: Multi-Modal Gesture Synthesis via Cascaded Conditional Control." AAAI, 6387-6395, doi: 10.1609/aaai.v38i6.28458.

The DiffuseStyleGesture+ entry to the GENEA Challenge 2023

ICMI (Reproducibility Award), 2023

Sicheng Yang*, Haiwei Xue*, Zhensong Zhang, Minglei Li, Zhiyong Wu, Xiaofei Wu, Songcen Xu, Zonghong Dai. (2023). "The DiffuseStyleGesture+ entry to the GENEA Challenge 2023." ICMI, 779–785, doi: 10.1145/3577190.3616114.

UnifiedGesture: A Unified Gesture Synthesis Model for Multiple Skeletons

ACM MM (Oral), 2023

Sicheng Yang*, Zilin Wang*, Zhiyong Wu, Minglei Li, Zhensong Zhang, Qiaochu Huang, Lei Hao, Songcen Xu, Xiaofei Wu, Changpeng Yang, Zonghong Dai. (2023). "UnifiedGesture: A Unified Gesture Synthesis Model for Multiple Skeletons." ACM MM, 1033–1044, doi: 10.1145/3581783.3612503.

DiffuseStyleGesture: Stylized Audio-Driven Co-Speech Gesture Generation with Diffusion Models

IJCAI (The 4th Outstanding Science and Technology Academic Papers of Shenzhen Association for Science and Technology, 2024), 2023

Sicheng Yang, Zhiyong Wu, Minglei Li, Zhensong Zhang, Lei Hao, Weihong Bao, Ming Cheng, Long Xiao. (2023). "DiffuseStyleGesture: Stylized Audio-Driven Co-Speech Gesture Generation with Diffusion Models." IJCAI, 5860--5868, doi: 10.24963/ijcai.2023/650.

QPGesture: Quantization-Based and Phase-Guided Motion Matching for Natural Speech-Driven Gesture Generation

CVPR (Highlight), 2023

Sicheng Yang, Zhiyong Wu, Minglei Li, Zhensong Zhang, Lei Hao, Weihong Bao, Haolin Zhuang. (2023). "QPGesture: Quantization-Based and Phase-Guided Motion Matching for Natural Speech-Driven Gesture Generation." CVPR, 2321-2330, doi: 10.1109/CVPR52729.2023.00230.

Wavsyncswap: End-To-End Portrait-Customized Audio-Driven Talking Face Generation

ICASSP, 2023

Weihong Bao, Liyang Chen, Chaoyong Zhou, Sicheng Yang, Zhiyong Wu. (2023). "Wavsyncswap: End-To-End Portrait-Customized Audio-Driven Talking Face Generation." ICASSP, 1-5, doi: 10.1109/ICASSP49357.2023.10094807.

GTN-Bailando: Genre Consistent Long-Term 3D Dance Generation based on Pre-trained Genre Token Network

ICASSP, 2023

Haolin Zhuang, Shun Lei, Long Xiao, Weiqin Li, Liyang Chen, Sicheng Yang, Zhiyong Wu, Shiyin Kang, Helen Meng. (2023). "GTN-Bailando: Genre Consistent Long-Term 3D Dance Generation based on Pre-trained Genre Token Network." ICASSP, 1-5, doi: 10.1109/ICASSP49357.2023.10095203.

Innovative Thinking Training in Light Control Circuit Open Experiment

Laboratory Science, 2023

Gao Xuanyi, Yang Sicheng, Liu Yongxin. (2023). "Innovative Thinking Training in Light Control Circuit Open Experiment." Laboratory Science, 26(01):107-110, doi: 10.3969/j.issn.1672-4305.2023.01.025.

The ReprGesture entry to the GENEA Challenge 2022

ICMI, 2022

Sicheng Yang, Zhiyong Wu, Minglei Li, Mengchen Zhao, Jiuxin Lin, Liyang Chen, Weihong Bao. (2022). "The ReprGesture entry to the GENEA Challenge 2022." ICMI, 758–763, doi: 10.1145/3536221.3558066.

Speech Representation Disentanglement with Adversarial Mutual Information Learning for One-shot Voice Conversion

Interspeech, 2022

SiCheng Yang*, Methawee Tantrawenith*, Haolin Zhuang*, Zhiyong Wu, Aolan Sun, Jianzong Wang, Ning Cheng, Huaizhen Tang, Xintao Zhao, Jie Wang, Helen Meng. (2022). "Speech Representation Disentanglement with Adversarial Mutual Information Learning for One-shot Voice Conversion." Interspeech, 2553-2557, doi: 10.21437/Interspeech.2022-571.

An Automatic Analysis and Evaluation System Used for Teaching Quality in MOOC Environment

DTPI, 2021

Sicheng Yang, Yaping Dai, Simin Li, Kaixin Zhao. (2021). "An Automatic Analysis and Evaluation System Used for Teaching Quality in MOOC Environment." DTPI, 38-41, doi: 10.1109/DTPI52967.2021.9540117.