Publications

Preprint MemoGen: Can Past Experience Improve Future Text-to-Image Generation? ArXiv
Wenshuo Chen*, Kuimou Yu*, Bowen Tian*, Jianfei Song*, Shaofeng Liang, Haozhe Jia, Kan Cheng, Haosen Li, Kaishen Yuan, Lei Wang, Jiemin Wu, Songning Lai, Yutao Yue.

Preprint Before the Body Moves: Learning Anticipatory Joint Intent for Language-Conditioned Humanoid Control Project ArXiv Code
Haozhe Jia, Honglei Jin, Yuan Zhang, Youcheng Fan*, Shaofeng Liang*, Lei Wang, Shuxu Jin, Kuimou Yu, Zinuo Zhang, Jianfei Song, Wenshuo Chen†, Yutao Yue†.

Preprint An Edge-Cloud Framework for Language-Driven Whole-Body Control of Humanoid Robots Project ArXiv Code
Haozhe Jia, Jianfei Song, Yuan Zhang, Honglei Jin, Youcheng Fan, Wenshuo Chen, Wei Zhang, Yutao Yue.

Preprint POLARIS: Projection-Orthogonal Least Squares for Robust and Adaptive Inversion in Diffusion Models Project ArXiv Code
Wenshuo Chen, Haosen Li, Shaofeng Liang, Lei Wang, Haozhe Jia, Kaishen Yuan, Jieming Wu, Bowen Tian, Yutao Yue.

ECCV Dynamic-V2C: Editable and Continual Vision-to-Concept Bottleneck Models via Influence Functions Project
Songning Lai, Shaofeng Liang, Jiayu Yang, Ninghui Feng, Yuxuan Fan, Wenshuo Chen†.
The 19th European Conference on Computer Vision (ECCV 2026).

ECCV SFM: Taming State Space Models for Text-to-Motion via Spatial-Frequency Modeling
Shang Gao*, Haicheng Liao*, Wenshuo Chen*, Yumu Xie, Jiaxun Zhang, Bin Rao, Chengyue Wang, Yanchen Guan, Zhiyong Cui, Shiqi Ou, Yutao Yue, Zhenning Li.
The 19th European Conference on Computer Vision (ECCV 2026).

ACM MM BNI Free-T2M: Frequency-Aware Coarse-to-Fine Text-to-Motion Generation ArXiv Code
Wenshuo Chen*, Haozhe Jia*, Songning Lai, Lei Wang, Pengyu Yin, Shaofeng Liang, Yuqi Lin, Hongru Xiao, Lijie Hu, Yutao Yue.
ACM Multimedia Brave New Ideas Track (ACM MM BNI 2026). Selected as a Poster paper.

ACM MM BNI Oral Delta Score Matters! Spatial Adaptive Multi Guidance in Diffusion Models ArXiv
Haosen Li*, Wenshuo Chen*, Lei Wang, Shaofeng Liang, Bowen Tian, Songning Lai, Yutao Yue.
ACM Multimedia Workshop on Big Neural and Imaging Models (ACM MM BNI 2026). Selected as an Oral paper.

ACM MM BNI Oracle Noise: Faster Semantic Spherical Alignment for Interpretable Latent Optimization ArXiv
Haosen Li*, Wenshuo Chen*†, Lei Wang, Shaofeng Liang, Haozhe Jia, Yutao Yue†.
ACM Multimedia Workshop on Big Neural and Imaging Models (ACM MM BNI 2026).

ICML Learning to Think in Physics: Breaking Shortcut Learning in Scientific Diffusion via Representation Alignment ArXiv
Haozhe Jia*, Pengyu Yin*, Wenshuo Chen*, Shaofeng Liang, Lei Wang, Bowen Tian, Xiucheng Wang, Nanqian Jia, Yutao Yue.
The Forty-Third International Conference on Machine Learning (ICML 2026).

ICML AnyEdit++: Adaptive Long-Form Knowledge Editing via Bayesian Surprise ArXiv
Bowen Tian, Caixue He, Jiemin Wu, Jingying Wang, Wenshuo Chen, Zexi Li, Yutao Yue.
The Forty-Third International Conference on Machine Learning (ICML 2026).

ICLR CoEmoGen: Towards Semantically-Coherent and Scalable Emotional Image Content Generation ArXiv Code
Kaishen Yuan*, Yuting Zhang*, Shang Gao, Yijie Zhu, Wenshuo Chen, Yutao Yue.
The Fourteenth International Conference on Learning Representations (ICLR 2026).

ACM MM ANT: Adaptive Neural Temporal-Aware Text-to-Motion Model ArXiv Code
Wenshuo Chen*, Kuimou Yu*, Haozhe Jia*, Kaishen Yuan, Zexu Huang, Bowen Tian, Songning Lai, Hongru Xiao, Erhang Zhang, Lei Wang, Yutao Yue.
The 33rd ACM International Conference on Multimedia (ACM MM 2025).

ACM MM BNI Oral Physics-Informed Representation Alignment for Sparse Radio-Map Reconstruction ArXiv Code
Haozhe Jia*, Wenshuo Chen*, Zhihui Huang*, Hongru Xiao, Nanqian Jia, Keming Wu, Songning Lai, Yutao Yue.
ACM Multimedia Workshop on Big Neural and Imaging Models (ACM MM BNI 2025). Selected as an Oral paper.

ICML DCTdiff: Intriguing Properties of Image Generative Modeling in the DCT Space ArXiv Code
Mang Ning, Mingxiao Li, Jianlin Su, Haozhe Jia, Lanmiao Liu, Martin Benes, Wenshuo Chen, Albert Ali Salah, Itir Onal Ertugrul.
The Forty-Second International Conference on Machine Learning (ICML 2025).

ACM MM Text2Weight: Bridging Natural Language and Neural Network Weight Spaces ArXiv Code
Bowen Tian*, Wenshuo Chen*, Zexi Li, Songning Lai, Jiemin Wu, Yutao Yue.
The 33rd ACM International Conference on Multimedia (ACM MM 2025).

ACM MM SATO: Stable Text-to-Motion Framework Project ArXiv Code
Wenshuo Chen*, Hongru Xiao*, Erhang Zhang*, Lijie Hu, Lei Wang, Mengyuan Liu, Chen Chen.
The 32nd ACM International Conference on Multimedia (ACM MM 2024).

NeurIPS Towards Multi-dimensional Explanation Alignment for Medical Classification ArXiv
Lijie Hu*, Songning Lai*, Wenshuo Chen*, Hongru Xiao, Hongbin Lin, Lu Yu, Jingfeng Zhang, Di Wang.
The Thirty-Eighth Annual Conference on Neural Information Processing Systems (NeurIPS 2024).