Yuchu Jiang

Master's student at Southeast University and PALM Lab

yuchu-jiang.png

Nanjing, China

I am Yuchu Jiang, a Master’s student at Southeast University’s PALM Lab, advised by Prof. Xu Yang. My research interests are broad, with a primary focus on inference acceleration, diffusion large language models, and post-training techniques. I enjoy developing elegant works and continually exploring new knowledge.

Outside of my academic work, I have a strong interest in neuroscience, particularly in understanding how the brain processes information and how neural systems function at the biological level. Classical music is another significant part of my life, with a particular focus on symphonies and piano works from the Romantic, Impressionist, and Atonal music periods.

News

May 01, 2026
Rethinking LLM Ensembling from the Perspective of Mixture Models was accepted by ICML 2026 as a Spotlight presentation.
Jan 01, 2026
d2Cache: Accelerating Diffusion-Based LLMs via Dual Adaptive Caching was accepted by ICLR 2026.
Jul 01, 2025
Two papers (including one demo track) were accepted by ACM MM 2025.
May 15, 2025
I won 1st place in the image detection and localization track in the IJCAI 2025 Deepfake Detection and Localization Challenge.
May 01, 2025
Fast Large Language Model Collaborative Decoding via Speculation was accepted by ICML 2025.
Feb 01, 2025
My first paper on multimodal in-context learning, Mimic In-Context Learning for Multimodal Tasks, was accepted by CVPR 2025.
Aug 01, 2024
Start my research career under the supervision of Prof. Xu Yang.

Selected Publications

  1. Rethinking LLM Ensembling from the Perspective of Mixture Models
    Jiale Fu*, Yuchu Jiang*, Peijun Wu, Chonghan Liu, Joey Tianyi Zhou, and Xu Yang
    In International Conference on Machine Learning, 2026
  1. d^2Cache: Accelerating Diffusion-Based LLMs via Dual Adaptive Caching
    Yuchu Jiang, Yue Cai, Xiangzhong Luo, Jiale Fu, Jiarui Wang, Chonghan Liu, and Xu Yang
    In International Conference on Learning Representations, 2026
  1. Fast Large Language Model Collaborative Decoding via Speculation
    Jiale Fu*, Yuchu Jiang*, Junkai Chen, Jiaming Fan, Xin Geng, and Xu Yang
    In International Conference on Machine Learning, 2025
  1. Mimic In-Context Learning for Multimodal Tasks
    Yuchu Jiang, Jiale Fu, Chenduo Hao, Xinting Hu, Yingzhe Peng, Xin Geng, and Xu Yang
    In IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2025