Jiachen Jiang

Biography

I am advised by Prof. Zhihui Zhu. My research interests include:

• Structured representations in deep networks. How information is organized at the last layer (ICML 2024), across depth (ICLR 2025), across modalities (NeurIPS 2025), and within in-context learning (ICLR 2026 Workshop, MLSP 2026).
• LLM-driven scientific discovery. LLMs as in-context search operators, via compact context construction (ICML 2026) and principled search with provable guarantees (arXiv 2026).
• Low-level vision. Unified, adaptive models for image restoration and other low-level vision tasks (NeurIPS 2026).

I am currently on the job market and actively seeking industry positions. If you are aware of any relevant opportunities or have recommendations, I would love to hear from you.

Education

• The Ohio State University (OSU) Columbus, OH
  Doctor of Philosophy in Computer Science and Engineering 2023 – Present
• University of Michigan (UMich) Ann Arbor, MI
  Master of Science in Electrical & Computer Engineering 2020 – 2023
• Beihang University (BUAA) Beijing, China
  Bachelor of Science in Electrical Engineering 2016 – 2020

Experience

• Research Intern May 2026 – Aug. 2026
  @ Microsoft, Redmond, WA
• Research Intern Jun. 2024 – Sep. 2024
  @ Microsoft, Redmond, WA
• Research Assistant Aug. 2023 – Present
  @ The Ohio State University, Columbus, OH

Selected Publications

(★ indicates first-author work)

1. Learning Where and What to Restore for Composite Image Restoration
   Jiachen Jiang, Tianyu Ding, Ke Zhang, Jinxin Zhou, Tianyi Chen, Ilya Zharkov, Zhihui Zhu, Luming Liang
   Neural Information Processing Systems (NeurIPS), 2026 AC rate = 25.7%
   pdf arXiv project page
2. DeltaEvolve: Accelerating Scientific Discovery through Momentum-Driven Evolution
   Jiachen Jiang, Tianyu Ding, Zhihui Zhu
   International Conference on Machine Learning (ICML), 2026 AC rate = 26.6%
   pdf arXiv
3. Improving Visual Discriminability of CLIP for Training-Free Open-Vocabulary Semantic Segmentation
   Jinxin Zhou, Jiachen Jiang, Zhihui Zhu
   Transactions on Machine Learning Research (TMLR), 2026
   pdf arXiv
4. From Emergence to Control: Probing and Modulating Self-Reflection in Language Models
   Xudong Zhu, Jiachen Jiang, Mohammad Mahdi Khalili, Zhihui Zhu
   Transactions on Machine Learning Research (TMLR), 2026
   pdf arXiv
5. Understanding Task Vectors in In-Context Learning: Emergence, Functionality, and Limitations
   Yuxin Dong, Jiachen Jiang, Zhihui Zhu, Xia Ning
   International Conference on Learning Representations (ICLR), 2026 AC rate = 27.4%
   pdf arXiv
6. Learning to Adapt: In-Context Learning Beyond Stationarity
   Zhen Qin, Jiachen Jiang, Zhihui Zhu
   International Conference on Learning Representations (ICLR), 2026 AC rate = 27.4%
   pdf arXiv
7. From Compression to Expression: A Layerwise Analysis of In-Context Learning
   Jiachen Jiang, Yuxin Dong, Jinxin Zhou, Zhihui Zhu
   International Conference on Learning Representations (ICLR) DeLTa Workshop, 2026
   pdf arXiv project page
8. On the Convergence of Gradient Descent on Learning Transformers with Residual Connections
   Zhen Qin, Jinxin Zhou, Jiachen Jiang, Zhihui Zhu
   IEEE Signal Processing Letters (SPL), 2026
   pdf arXiv IEEE
9. ProCrop: Learning Aesthetic Image Cropping from Professional Compositions
   Ke Zhang, Tianyu Ding, Jiachen Jiang, Tianyi Chen, Ilya Zharkov, Vishal M. Patel, Luming Liang
   AAAI Conference on Artificial Intelligence (AAAI), 2026 AC rate = 17.6%
   pdf arXiv project page
10. In-Context Learning for Non-Stationary MIMO Equalization
    Jiachen Jiang, Zhen Qin, Zhihui Zhu
    IEEE International Workshop on Machine Learning for Signal Processing (MLSP), 2026
    pdf arXiv
11. Analyzing Fine-Grained Alignment and Enhancing Vision Understanding in Multimodal Language Models
    Jiachen Jiang, Jinxin Zhou, Bo Peng, Xia Ning, Zhihui Zhu
    Neural Information Processing Systems (NeurIPS), 2025 AC rate = 24.5%
    pdf arXiv
12. Can Reasoning LLMs Eliminate Conformity in Multi-Agent Systems? Best Paper Award
    Alina Liu, Christopher Hill, Jiachen Jiang, Zhihui Zhu
    IEEE International Conference on Data Mining Workshops (ICDMW), 2025
    pdf
13. Tracing Representation Progression: Analyzing and Enhancing Layer-Wise Similarity
    Jiachen Jiang, Jinxin Zhou, Zhihui Zhu
    International Conference on Learning Representations (ICLR), 2025 AC rate = 32%
    pdf arXiv
14. Are All Layers Created Equal: A Neural Collapse Perspective
    Jinxin Zhou, Jiachen Jiang, Zhihui Zhu
    Conference on Parsimony and Learning (CPAL), 2025
    pdf
15. Generalized Neural Collapse for a Large Number of Classes
    Jiachen Jiang, Jinxin Zhou, Peng Wang, Qing Qu, Dustin Mixon, Chong You, Zhihui Zhu
    International Conference on Machine Learning (ICML), 2024 AC rate = 27.5%
    pdf arXiv
16. DREAM: Diffusion Rectification and Estimation-Adaptive Models
    Jinxin Zhou, Tianyu Ding, Tianyi Chen, Jiachen Jiang, Ilya Zharkov, Zhihui Zhu, Luming Liang
    Computer Vision and Pattern Recognition (CVPR), 2024 AC rate = 23.6%
    pdf code arXiv project page

Selected Preprints

1. SMCEvolve: Principled Scientific Discovery via Sequential Monte Carlo Evolution
   Jiachen Jiang, Huminhao Zhu, Zhihui Zhu
   arXiv preprint, 2026
   pdf arXiv
2. The Efficiency Spectrum of Large Language Models: An Algorithmic Survey
   Tianyu Ding, Tianyi Chen, Haidong Zhu, Jiachen Jiang, Yiqi Zhong, Jinxin Zhou, Guangzhi Wang, Zhihui Zhu, Ilya Zharkov, Luming Liang
   arXiv preprint, 2023
   pdf arXiv

Visitors