Jixuan Ying

Jixuan Ying

Tsinghua undergraduate and SenseTime research intern working on interleaved multimodal reasoning and efficient visual architectures.

Publications

You can also find my articles on my Google Scholar profile.

Conference Papers

InterSketch: Interleaved Visual–Textual Chain-of-Thought with Tool-Generated Sketches and Reinforcement Learning

Under review at International Conference on Machine Learning (ICML), 2025

An interleaved multimodal reasoning framework that leverages tool-generated sketches to support long-horizon visual-text Chain-of-Thought reasoning.

Recommended citation: Z. Ning, W. Tong, X. Kong, S. Ma, Z. Shang, J. Ni, T. Hu, Y. X. Chng, Jixuan Ying, Z. Wu, J. Yang, W. Liu, H. Deng, L. Lu. "InterSketch: Interleaved Visual–Textual Chain-of-Thought with Tool-Generated Sketches and Reinforcement Learning." ICML 2026, under review.

Linear Differential Vision Transformer: Learning Visual Contrasts via Pairwise Differentials

Accepted at Neural Information Processing Systems (NeurIPS), 2025

A linear-complexity vision transformer based on visual contrast attention, designed to improve local difference perception with minimal overhead.

Recommended citation: Y. Pu*, Jixuan Ying*, T. Ye, D. Han, Z. Wang, Q. Li, X. Shao, X. Wang, G. Huang, X. Li. "Linear Differential Vision Transformer: Learning Visual Contrasts via Pairwise Differentials." NeurIPS 2025.

Follow-Your-Click: Open-domain Regional Image Animation via Motion Prompts

Accepted at AAAI Conference on Artificial Intelligence (AAAI), 2025

An interactive regional image animation method that generates open-domain animations for arbitrary regions via motion prompts and mouse clicks.

Recommended citation: Yue Ma*, Y. He*, H. Wang, A. Wang, L. Shen, C. Qi, Jixuan Ying, C. Cai, Z. Li, H.-Y. Shum, W. Liu, Q. Chen. "Follow-Your-Click: Open-domain Regional Image Animation via Motion Prompts." AAAI 2025.

Journal Articles

InfoPro: Locally Supervised Deep Learning by Maximizing Information Propagation

Published in International Journal of Computer Vision (IJCV), 2025

A locally supervised deep learning framework that improves information flow, feature expression, generalization, and training efficiency.

Recommended citation: Y. Wang*, Z. Ni*, Y. Pu, C. Zhou, Jixuan Ying, S. Song, G. Huang. "InfoPro: Locally Supervised Deep Learning by Maximizing Information Propagation." IJCV 2025.
Download Paper