Publications

2026

  1. arXiv
    OpenSafeIntent: Evaluating Intent-Calibrated Safe Completion Across Dual-Use Prompt Sets
    Rheeya Uppaal,Seungwoo Lyu,Selina Sung, and Junjie Hu
    [Website]
  2. COLM
    When Safety Fails Before the Answer: Benchmarking Harmful Behavior Detection in Reasoning Chains
    Ishita Kakkar,Enze Zhang,Rheeya Uppaal, and Junjie Hu
  3. arXiv
    Mmgr: Multi-modal generative reasoning
    Zefan Cai,Haoyi Qiu,Tianyi Ma,Haozhe Zhao,Gengze Zhou,Kung-Hsiang Huang,Parisa Kordjamshidi,Minjia Zhang,Wen Xiao,Jiuxiang Gu, and others
  4. arXiv
    RiskCueBench: Benchmarking Anticipatory Reasoning from Early Risk Cues in Video-Language Models
    Sha Luo,Yogesh Prabhu,Timothy Ossowski,Kaiping Chen, and Junjie Hu
  5. arXiv
    SITA: Learning Speaker-Invariant and Tone-Aware Speech Representations for Low-Resource Tonal Languages
    Tianyi Xu,Xuan Ouyang,Binwei Yao,Shoua Xiong,Sara Misurelli,Maichou Lor, and Junjie Hu
  6. arXiv
    DEBATE: A large-scale benchmark for evaluating opinion dynamics in role-playing LLM agents
    Yun-Shiuan Chuang,Ruixuan Tu,Chengtao Dai,You Li,Smit Vasani,Binwei Yao,Michael Henry Tessler,Sijia Yang,Dhavan Shah,Robert Hawkins, and others
  7. arXiv
    Shattered Compositionality: Counterintuitive Learning Dynamics of Transformers for Arithmetic
    Xingyu Zhao,Darsh Sharma,Rheeya Uppaal, and Yiqiao Zhong
  8. CVPR
    PETAR: Localized Findings Generation with Mask-Aware Vision-Language Modeling for PET Automated Reporting
    Danyal Maqbool,Changhee Lee,Zachary Huemann,Samuel D Church,Matthew E Larson,Scott B Perlman,Tomas A Romero,Joshua D Warner,Meghan Lubner,Xin Tie, and others
  9. CVPR
    Octomed: Data recipes for state-of-the-art multimodal medical reasoning
    Timothy Ossowski,Sheng Zhang,Qianchu Liu,Guanghui Qin,Reuben Tan,Tristan Naumann,Junjie Hu, and Hoifung Poon
  10. CVPR
    Visualtoolagent (vista): A reinforcement learning framework for visual tool selection
    Zeyi Huang,Yuyang Ji,Anirudh Sundara Rajan,Zefan Cai,Wen Xiao,Haohan Wang,Junjie Hu, and Yong Jae Lee
  11. EACL
    Journey before destination: On the importance of visual faithfulness in slow thinking
    Rheeya Uppaal,Phu Mon Htut,Min Bai,Nikolaos Pappas,Zheng Qi, and Sandesh Swamy
    [Website]
  12. TMLR
    From preferences to prejudice: The role of alignment tuning in shaping social bias in video diffusion models
    Zefan Cai,Haoyi Qiu,Haozhe Zhao,Ke Wan,Jiachen Li,Jiuxiang Gu,Wen Xiao,Nanyun Peng, and Junjie Hu

2025

  1. arXiv
    Peacemaker or troublemaker: How sycophancy shapes multi-agent debate
    Binwei Yao,Chao Shang,Wanyu Du,Jianfeng He,Ruixue Lian,Yi Zhang,Hang Su,Sandesh Swamy, and Yanjun Qi
  2. COLM
    PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling
    Zefan Cai,Yichi Zhang,Bofei Gao,Tianyu Liu,Keming Lu,Wayne Xiong,Yue Dong,Junjie Hu, and Wen Xiao
    In The Second Conference of Language Modeling 2025
    [Code]
  3. EMNLP
    V-SEAM: Visual Semantic Editing and Attention Modulating for Causal Interpretability of Vision-Language Models
    Qidong Wang,Junjie Hu, and Ming Jiang
    In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing (EMNLP) 2025
    [Code]
  4. EMNLP
    Probing LLM World Models: Enhancing Guesstimation with Wisdom of Crowds Decoding
    Yun-Shiuan Chuang,Nikunj Harlalka,Sameer Narendran,Alexander Cheung,Sizhe Gao,Siddharth Suresh,Junjie Hu, and Timothy T Rogers
    In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing (EMNLP) 2025
  5. ICLR
    Model Editing as a Robust and Denoised variant of DPO: A Case Study on Toxicity
    Rheeya Uppaal,Apratim Dey,Yiting He,Yiqiao Zhong, and Junjie Hu
    In The Thirteenth International Conference on Learning Representations 2025
    [Code] [Checkpoints] [Website]
  6. ICLR
    No Preference Left Behind: Group Distributional Preference Optimization
    Binwei Yao,Zefan Cai,Yun-Shiuan Chuang,Shanglin Yang,Ming Jiang,Diyi Yang, and Junjie Hu
    In The Thirteenth International Conference on Learning Representations 2025
    [Code]
  7. ICML
    MA-LoT: Multi-Agent Lean-based Long Chain-of-Thought Reasoning enhances Formal Theorem Proving
    Ruida Wang,Rui Pan,Yuxin Li,Jipeng Zhang,Yizhen Jia,Shizhe Diao,Renjie Pi,Junjie Hu, and Tong Zhang
    In The Forty-Second International Conference on Machine Learning 2025
    [Code]
  8. NeurIPS
    R-KV: Redundancy-aware KV Cache Compression for Training-Free Reasoning Models Acceleration
    Zefan Cai,Wen Xiao,Hanshi Sun,Cheng Luo,Yikai Zhang,Ke Wan,Yucheng Li,Yeyang Zhou,Li-Wen Chang,Jiuxiang Gu,Zhen Dong,Anima Anandkumar,Abedelkadir Asi, and Junjie Hu
    In Proceedings of the Thirty-ninth Annual Conference on Neural Information Processing Systems (NeurIPS) 2025
    [Code] [Website]
  9. TMLR
    COMMA: A Communicative Multimodal Multi-Agent Benchmark
    Timothy Ossowski,Danyal Maqbool,Jixuan Chen,Zefan Cai,Tyler J. Bradshaw, and Junjie Hu
    Transactions on Machine Learning Research 2025
    [Code]
  10. arXiv
    Scaling Up Audio-Synchronized Visual Animation: An Efficient Training Paradigm
    Lin Zhang,Zefan Cai,Yufan Zhou,Shentong Mo,Jinhong Lin,Cheng-En Wu,Yibing Wei,Yijing Zhang,Ruiyi Zhang,Wen Xiao, and others
    arXiv preprint arXiv:2508.03955 2025
  11. arXiv
    MENTOR: Efficient Multimodal-Conditioned Tuning for Autoregressive Vision Generation Models
    Haozhe Zhao,Zefan Cai,Shuzheng Si,Liang Chen,Jiuxiang Gu,Wen Xiao, and Junjie Hu
    arXiv preprint arXiv:2507.09574 2025
    [Code] [Website]
  12. arXiv
    Headinfer: Memory-efficient llm inference by head-wise offloading
    Cheng Luo,Zefan Cai,Hanshi Sun,Jinqi Xiao,Bo Yuan,Wen Xiao,Junjie Hu,Jiawei Zhao,Beidi Chen, and Anima Anandkumar
    arXiv preprint arXiv:2502.12574 2025
    [Code]
  13. arXiv
    VisualToolAgent (VisTA): A Reinforcement Learning Framework for Visual Tool Selection
    Zeyi Huang,Yuyang Ji,Anirudh Sundara Rajan,Zefan Cai,Wen Xiao,Junjie Hu, and Yong Jae Lee
    arXiv preprint arXiv:2505.20289 2025
    [Code] [Website]

2024

  1. ACL
    OLIVE: Object Level In-Context Visual Embeddings
    Timothy Ossowski and Junjie Hu
    In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics 2024
    [Code]
  2. ACL
    Data Augmentation using LLMs: Data Perspectives, Learning Paradigms and Challenges
    Bosheng Ding,Chengwei Qin,Ruochen Zhao,Tianze Luo,Xinze Li,Guizhen Chen,Wenhan Xia,Junjie Hu,Anh Tuan Luu, and Shafiq Joty
    In Findings of the 62nd Annual Meeting of the Association for Computational Linguistics 2024
  3. COLM
    How Well Do LLMs Identify Cultural Unity in Diversity?
    Jialin Li,Junli Wang,Junjie Hu, and Ming Jiang
    In The first Conference of Language Modeling 2024
    [Code]
  4. CSCW
    MetaWriter: Exploring the Potential and Perils of AI Writing Support in Scientific Peer Review
    Lu Sun,Stone Tao,Junjie Hu, and Steven Dow
    In Proceedings of The 26th ACM Conference on Computer-Supported Cooperative Work and Social Computing 2024
  5. CVPR
    Lookahead Exploration with Neural Radiance Representation for Continuous Vision-Language Navigation
    Zihan Wang,Xiangyang Li,Jiahao Yang,Yeqi Liu,Junjie Hu,Ming Jiang, and Shuqiang Jiang
    In The IEEE/CVF Conference on Computer Vision and Pattern Recognition 2024
    [Code]
  6. CogSci
    Evaluating LLM Agent Group Dynamics against Human Group Dynamics: A Case Study on Wisdom of Partisan Crowds
    Yun-Shiuan Chuang,Siddharth Suresh,Nikunj Harlalka,Agam Goyal,Robert Hawkins,Sijia Yang,Dhavan Shah,Junjie Hu, and Timothy T Rogers
    In The Annual Conference of the Cognitive Science Society (CogSci). 2024
  7. EACL
    Learning Label Hierarchy with Supervised Contrastive Learning
    Ruixue Lian,William A. Sethares, and Junjie Hu
    In Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics 2024
    [Code]
  8. EMNLP
    Beyond Demographics: Aligning Role-playing LLM-based Agents Using Human Belief Networks
    Yun-Shiuan Chuang,Zach Studdiford,Krirk Nirunwiroj,Agam Goyal,Vincent V. Frigo,Sijia Yang,Dhavan V. Shah,Junjie Hu, and Timothy T. Rogers
    In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing (EMNLP Findings) 2024
  9. EMNLP
    Benchmarking Machine Translation with Cultural Awareness
    Binwei Yao,Ming Jiang,Diyi Yang, and Junjie Hu
    In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing (EMNLP Findings) 2024
    [Code]
  10. ICML
    Chatbot Meets Pipeline: Augment Large Language Model with Definite Finite Automaton
    Yiyou Sun,Junjie Hu,Wei Cheng, and Haifeng Chen
    In International Conference on Machine Learning (ICML) 2024
  11. NAACL
    How does Multi-Task Training Affect Transformer In-Context Capabilities? Investigations with Function Classes
    Harmon Bhasin,Timothy Ossowski,Yiqiao Zhong, and Junjie Hu
    In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics 2024
    [Code]
  12. NAACL
    Simulating Opinion Dynamics with Networks of LLM-based Agents
    Yun-Shiuan Chuang,Agam Goyal,Nikunj Harlalka,Siddharth Suresh,Robert Hawkins,Sijia Yang,Dhavan Shah,Junjie Hu, and Timothy T Rogers
    In Findings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics 2024
  13. NeurIPS
    Mitigating Fine-tuning based Jailbreak Attack with Backdoor Enhanced Safety Alignment
    Jiongxiao Wang,Jiazhao Li,Yiquan Li,Xiangyu Qi,Junjie Hu,Yixuan Li,Patrick McDaniel,Muhao Chen,Bo Li, and Chaowei Xiao
    In Proceedings of the Thirty-eighth Annual Conference on Neural Information Processing Systems (NeurIPS) 2024
    [Code] [Website]
  14. arXiv
    Large Language Models Are Active Critics in NLG Evaluation
    Shuying Xu,Junjie Hu, and Ming Jiang
    arXiv preprint arXiv:2410.10724 2024
  15. RepL4NLP
    How Useful is Continued Pre-Training for Generative Unsupervised Domain Adaptation?
    Rheeya Uppaal,Yixuan Li, and Junjie Hu
    In Proceedings of the 9th Workshop on Representation Learning for NLP (RepL4NLP-2024)
    [Code]
  16. arXiv
    Prompting Large Vision-Language Models for Compositional Reasoning
    Timothy Ossowski,Ming Jiang, and Junjie Hu
    arXiv preprint arXiv:2401.11337 2024
    [Code]

2023

  1. ACL
    Single Sequence Prediction over Reasoning Graphs for Multi-hop QA
    Gowtham Ramesh,Makesh Narsimhan Sreedhar, and Junjie Hu
    In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics 2023
  2. ACL
    Is Fine-tuning Needed? Pre-trained Language Models Are Near Perfect for Out-of-Domain Detection
    Rheeya Uppaal,Junjie Hu, and Yixuan Li
    In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics 2023
    [Code]
  3. ACL
    Local Byte Fusion for Neural Machine Translation
    Makesh Narsimhan Sreedhar,Xiangpeng Wan,Yu Cheng, and Junjie Hu
    In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics 2023
    [Code]
  4. ACL
    Multimodal Prompt Retrieval for Generative Visual Question Answering
    Timothy Ossowski and Junjie Hu
    In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (ACL Findings) 2023
    [Code]
  5. NeurIPS
    Evolving Domain Adaptation of Pretrained Language Models for Text Classification
    Yun-Shiuan Chuang,Yi Wu,Dhruv Gupta,Rheeya Uppaal,Ananya Kumar,Luhang Sun,Makesh Narsimhan Sreedhar,Sijia Yang,Timothy T Rogers, and Junjie Hu
    In NeurIPS Workshop on Distribution Shifts, 37th Conference on Neural Information Processing Systems. 2023