Publications

2026

  1. Agentified Agent Assessment Improves Standardization Across Heterogeneous Scenarios
    Xiaoyuan Liu, Jianhong Tu, Yuqi Chen, Siyuan Xie, Sihan Ren, Tianneng Shi, Gal Gantar, Peter J. Gilbert, Nick Hynes, Mauro Staver, Warren He, David Marn, Andrew Low, Xi Zhang, Daniel Miao, Evan Sandoval, Donghyun Lee, Chenguang Wang, Wenbo Guo, and Dawn Song
    2026
    Under review
  2. Agents’ Last Exam
    Yiyou Sun, Jianhong Tu, Kyle Montgomery, Vincent Siu, Chenguang Wang, Dawn Song, and others
    2026
    Under review
  3. FaultLoc: Evaluating AI Coding Agents for Fault Localization from Crash to Cause
    Jianhong Tu, Shubham Gaur, Rathik Murtinty, Zhun Wang, Tianneng Shi, Dawn Song, and Chenguang Wang
    2026
    Under review
  4. CyberCycle: A Scalable Real-World Benchmark for AI Agents’ End-to-End Cybersecurity Capabilities
    Tianneng Shi, Robin Rheem, Dongwei Jiang, Francisco De La Riega, Mona Wang, Zhun Wang, Jingzhi Jiang, Alexander Cheung, Sean Tai, Jonah Cha, Jianhong Tu, Gabriel Han, Chenguang Wang, Wenbo Guo, Jingxuan He, and Dawn Song
    In Proceedings of the International Conference on Machine Learning, 2026
  5. FICO: Evaluating Vision-Language Models under Visual Fidelity and Compression at Scale
    Jianhong Tu, Kyle Montgomery, Nicholas Crispino, Chenguang Wang, and Dawn Song
    In Proceedings of the Annual Meeting of the Association for Computational Linguistics, 2026

2025

  1. 2025jianhongmlan.png
    MLAN: Language-Based Instruction Tuning Preserves and Transfers Knowledge in Multimodal Language Models
    Jianhong Tu, Zhuohao Ni, Nicholas Crispino, Zihao Yu, Michael Bendersky, Beliz Gunel, Ruoxi Jia, Xin Liu, Lingjuan Lyu, Dawn Song, and Chenguang Wang
    In Proceedings of the 3rd Workshop on Towards Knowledgeable Foundation Models (KnowFM), Aug 2025
    PDF
  2. 2025kylecontextscaling.png
    Predicting Task Performance with Context-aware Scaling Laws
    Kyle Montgomery, David Park, Jianhong Tu, Michael Bendersky, Beliz Gunel, Dawn Song, and Chenguang Wang
    In Proceedings of the 3rd Workshop on Towards Knowledgeable Foundation Models (KnowFM), Aug 2025
    PDF
  3. 2025yuancompmmeval.png
    A Comprehensive Survey of Evaluating Multimodal Foundation Models: Hierarchical Perspective and Extensive Applications
    Ye Yuan, Junyu Luo, Guancheng Wan, Jinsheng Huang, Chengwu Liu, Junwei Yang, Yifang Qin, Zhiping Xiao, Qingqing Long, Meng Xiao, Yiqiao Jin, Jianhong Tu, Yuqi Chen, Wei Ju, Zhongwei Wan, Yusheng Zhao, Xiao Luo, Yiwei Fu, Yizhou Sun, Wei Wang, Chenguang Wang, and Ming Zhang
    May 2025
    Under review at ARR
    PDF

2024

  1. 2024hengentau.jpg
    ⭐ Failure in a population: Tauopathy disrupts homeostatic set-points in emergent dynamics despite stability in the constituent neurons
    James N. McGregor, Clayton A. Farris, Sahara Ensley, Aidan Schneider, Leandro J. Fosque, Chao Wang, Elizabeth I. Tilden, Yuqi Liu, Jianhong Tu, Halla Elmore, Keenan D. Ronayne, Ralf Wessel, Eva L. Dyer, Kiran Bhaskaran-Nair, David M. Holtzman, and Keith B. Hengen
    Neuron, May 2024
    Cover Paper
  2. 2024jianhongtavpool.png
    Instruction-aware Visual Feature Extraction for Multimodal Large Language Model
    Jianhong Tu, Erdong Chen, and Shuhan Zhang
    Dec 2024
    Preprint
    PDF
  3. 2024jianhongsubset.png
    Diversity-based Data Subset Selection with Deep Reinforcement Learning
    Jianhong Tu and Anxu Wang
    Dec 2024
    Preprint
    PDF