Image
Jianyang Gu
Postdoc @ The Ohio State University
Visiting Postdoc @ MIT
Email: gu.1220[at]osu.edu

About Me

I am currently a postdoctoral scholar in the Dept. of Computer Science and Engineering at The Ohio State University and a visiting postdoctoral scholar at MIT CSAIL. I'm affliated with Imageomics Institute and am fortunate to work with Dr. Wei-Lun Chao, Dr. Yu Su, Dr. Tanya Berger-Wolf, and Dr. Sara Beery.

I obtained my Ph.D. in 2024 from College of Control Science and Engineering, Zhejiang University, Hangzhou, China. I was supervised by Dr. Wei Jiang. Previously, I received my B.Eng. in Zhejiang University in 2019. During Sep. 2022 - Oct. 2023, I was a visiting scholar at HPC AI Lab, National University of Singapore, under the supervision of Dr. Yang You.

Research Interest

My research advances machine learning for scientific discovery through:

  1. learning and exposing concepts from scientific observations. Why science? Science is complex, with observations containing rich concepts and relationships. Science is also structured, providing a rigorous environment to expose limitations of existing machine learning approaches. My research develops methods to produce scientifically meaningful representations, reveal visual evidence underlying predictions, and enrich training to improve fine-grained scientific understanding.
  2. investigating how concepts in data shape model learning and behavior. Insights from models and representations can be fed back into data construction and learning to foster more interpretable, robust, and generalizable models. My data-centric research identifies the information that makes training data effective and develop methods to make models use visual evidence effectively during reasoning.
I envision concepts as a human-centered computational interface between data and models. Scientists can derive observation-grounded relationships between concepts and use the produced insights to guide further data and model development, forming a reinforcing cycle between scientific understanding and machine learning.

News

  • [Oct 2026] I will serve in the program committee of NAIRR Annual Meeting 2027.
  • [Oct 2026] Two papers accepted to WACV 2027.
  • [Oct 2026] Invited talk at ABC NextGen Seminar about intervention reconstruction as an essential interpretability component.
  • [Oct 2026] Invited talk at Boston University about concept-centric data representation.
  • [Sept 2026] Four papers accepted to NeurIPS 2026 (one E&D Track).
  • [Aug 2026] Two papers accepted to EMNLP 2026 (one Findings).
  • [Aug 2026] We organized FloraPalooza 2026 to advance AI for plant biodiversity.
  • [Aug 2026] I will serve as an Area Chair for ICLR 2027.
  • [Jul 2026] Invited talk at ESIP Semantic Technologies Committee.
  • [Jun 2026] Three papers accepted to ECCV 2026.
  • [May 2026] We are organizing the Designing for Discovery workshop at Evolution 2026.
  • [May 2026] We are organizing the CV4Ecology workshop at ECCV 2026.
  • [Apr 2026] We organized the AI Spy Event at COSI Science Festival 2026.
  • [Apr 2026] One paper accepted to ICML 2026.
  • [Apr 2026] BioCLIP 2 featured by NVIDIA (blog 1 / blog 2).
  • [Mar 2026] I will serve as an Area Chair for NeurIPS 2026.
  • [Mar 2026] We are organizing the Designing for Discovery workshop at the first Imageomics conference.
  • [Mar 2026] I will serve as a Panelist at NSF ACCESS Regional Workshop.
  • [Feb 2026] I will serve as a Panelist at NAIRR Annual Meeting.
  • [Feb 2026] Invited talk and lecture at University of Arizona and Texas A&M University about scalable and interpretable AI for science.
  • [Feb 2026] Two papers accepted to CVPR 2026.
  • [Feb 2026] Talk at Imageomics seminar about BioCLIP 2 and BioCAP.
  • [Jan 2026] One paper accepted to ICLR 2026.
  • [Nov 2025] One paper accepted to WACV 2026.
  • [Sept 2025] One paper accepted to NeurIPS 2025 as spotlight.
  • [Aug 2025] I will serve as an Area Chair for ICLR 2026.
  • [Aug 2025] Guest lecture at Australian National University about BioCLIP 2 and fine-grained classification.
  • [Jul 2025] We are organizing the Imageomics workshop at NeurIPS 2025.

Selected Publications

A full publication list is available in my google scholar page.
(* denotes equal contribution)

Concept Learning and Extraction from Scientific Observations
Image

BioCAP: Exploiting Synthetic Captions Beyond Labels in Biological Foundation Models

Integrate instance-level synthetic captions in multimodal alignment and demonstrate rich understanding of biological semantics.

Ziheng Zhang, Xinyue Ma, Arpita Chowdhury, Elizabeth G Campolongo, Matthew J Thompson, Net Zhang, Samuel Stevens, Hilmar Lapp, Tanya Berger-Wolf, Yu Su, Wei-Lun Chao, and Jianyang Gu.

ICLR 2026 PDF Code Webpage
Image

AVION: Aerial Vision–Language Instruction from Offline Teacher to Prompt-Tuned Network

A knowledge distillation framework tailored for remote sensing adaptation of vision-language models with minimal additional trainable parameters.

Yu Hu*, Jianyang Gu*, Hao Liu, Yue Cao, Jozsef Hamari, Zheng Liu, and Mohsen Zardadi.

CVPR 2026 PDF Code
Image

BioCLIP 2: Emergent Properties from Scaling Hierarchical Contrastive Learning

Extend species classification training to emergent properties of inter-species ecological alignment and intra-species variation separation.

Jianyang Gu, Samuel Stevens, Elizabeth G Campolongo, Matthew J Thompson, Net Zhang, Jiaman Wu, Andrei Kopanev, Zheda Mai, Alexander E White, James Balhoff, Wasila Dahdul, Daniel Rubenstein, Hilmar Lapp, Tanya Berger-Wolf, Wei-Lun Chao, and Yu Su.

NeurIPS 2025 Spotlight PDF Code Webpage
Image

Finer-CAM: Spotting the Difference Reveals Finer Details for Visual Explanation

Compare the target class with similar classes for more fine-grained and discriminative explanation.

Ziheng Zhang*, Jianyang Gu*, Arpita Chowdhury, Zheda Mai, David Carlyn, Tanya Berger-Wolf, Yu Su, and Wei-Lun Chao.

CVPR 2025 PDF Code Demo

Static Segmentation by Tracking: A Frustratingly Label-Efficient Approach to Fine-Grained Segmentation.

Zhenyang Feng, Zihe Wang, Jianyang Gu, Saul Ibaven Bueno, Tomasz Frelek, Advikaa Ramesh, Jingyan Bai, Lemeng Wang, Zanming Huang, Jinsu Yoo, Tai-Yu Pan, Arpita Chowdhury, Michelle Ramirez, Elizabeth G. Campolongo, Matthew J. Thompson, Christopher G. Lawrence, Sydne Record, Neil Rosser, Anuj Karpatne, Daniel Rubenstein, Hilmar Lapp, Charles V. Stewart, Tanya Berger-Wolf, Yu Su, and Wei-Lun Chao.

CVPR 2025 CV4Animals Oral PDF Code

Prompt-CAM: Making Vision Transformers Interpretable for Fine-Grained Analysis.

Arpita Chowdhury, Dipanjyoti Paul, Zheda Mai, Jianyang Gu, Ziheng Zhang, Kazi Sajeed Mehrab, Elizabeth G Campolongo, Daniel Rubenstein, Charles V Stewart, Anuj Karpatne, Tanya Berger-Wolf, Yu Su, and Wei-Lun Chao.

CVPR 2025 PDF Code
Concept Influence and Use in Data-Centric Machine Learning
Image

Mind the Tail: Data Selection Through Sparse Concepts

Alternating concept composition and studying their influence on downstream behavior.

Ziheng Zhang, Neha Hulkund, Colin Lee, Zheda Mai, Hui Shen, Ying Ding, Tanya Berger-Wolf, Sara Beery, Wei-Lun Chao, and Jianyang Gu.

arXiv PDF Code Webpage
Image

Leveraging Latent Visual Reasoning in Silence

Strengthen the use of visual evidence through attention enforcement.

Dongyao Zhu, Zhen Wang, Xi Xiao, Han Jiang, Saeed Vahidian, Wei-Lun Chao, Tanya Berger-Wolf, Yu Su, and Jianyang Gu.

NeurIPS 2026 PDF Code
Image

HierAmp: Coarse-to-Fine Autoregressive Amplification for Generative Dataset Distillation

Enhance the attention over object-related hierarchical semantics in the vision autoregressive model.

Lin Zhao*, Xinru Jiang*, Xi Xiao, Qihui Fan, Lei Lu, Yanzhi Wang, Xue Lin, Octavia Camps, Pu Zhao, and Jianyang Gu.

CVPR 2026 PDF Code
Image

Efficient Dataset Distillation via Minimax Diffusion

Efficiently distill ImageNet and generate representative and diverse images, yielding state-of-the-art validation performance.

Jianyang Gu, Saeed Vahidian, Vyacheslav Kungurtsev, Haonan Wang, Wei Jiang, Yang You and Yiran Chen.

CVPR 2024 PDF Code

Structural Assessment for Understanding and Guiding Dataset Distillation in Discrete Token Space.

Yue Cao, Jianyang Gu, Vyacheslav Kungurtsev, Yu Hu, Jozsef Hamari, Zheng Liu, and Mohsen Zardadi.

ECCV 2026 PDF

CONCORD: Concept-Informed Diffusion for Dataset Distillation.

Jianyang Gu, Haonan Wang, Ruoxi Jia, Saeed Vahidian, Vyacheslav Kungurtsev, Wei Jiang, and Yiran Chen.

WACV 2026 PDF Code

Summarizing Stream Data for Memory-Restricted Online Continual Learning.

Jianyang Gu, Kai Wang, Wei Jiang, and Yang You.

AAAI 2024 PDF Code

DREAM: Efficient Dataset Distillation by Representative Matching.

Yanqing Liu*, Jianyang Gu*, Kai Wang, Zheng Zhu, Wei Jiang, and Yang You.

ICCV 2023 PDF Code

InfoBatch: Lossless Training Speed Up by Unbiased Dynamic Data Pruning.

Ziheng Qin*, Kai Wang*, Zangwei Zheng, Jianyang Gu, Xiangyu Peng, Zhaopan Xu, Daquan Zhou, Lei Shang, Baigui Sun, Xuansong Xie, and Yang You.

ICLR 2024 Oral PDF Code

Experience

  • OPPO Research Intern

    Nov. 2021 - Jun. 2022. Focused on domain generalizable person re-identification and video action recognition.

  • Alibaba Research Intern

    Jun. 2020 - Apr. 2021. Focused on unsupervised domain adaptive person re-identification. Awarded as the annual outstanding research intern in 2020.

  • Yitu Tech. CI Intern

    May. 2018 - Sept. 2018. Helped build up the continuous integration pipeline of products.

Competitions & Awards

  • NeurIPS Scholar Award

    2025.

  • OSU PDA Travel Award

    2025.

  • OSU CSE Research Staff Award

    2025.

  • AAAI Scholarship

    2024.

  • ActivityNet Temporal Action Localization Challenge

    Third Place. CVPR Workshop 2022.

  • SoccerNet Challenge

    Third Place. CVPR Workshop 2022.

  • AICity Challenge

    First Place. CVPR Workshop 2021.

  • National AI Challenge

    Second Prize. 2020.

  • Visual Domain Adaptation Challenge

    First Place. ECCV Workshop 2020.

  • Robocup Montreal

    First Place. 2018.

Academic Service

Other Information

  • President, Student AI Association of Zhejiang University, Aug. 2020 - Jun. 2021

  • Part of my photography works.

Contact Me

You are welcome to contact me via Email.

Written by Jianyang Gu & CodeX