research

our papers organized by topic, preprints first, then published work. The same papers listed by year are on the publications page.

Click a topic to expand its papers.

Large Language Models

Data Selection, Curriculum & Synthetic Data
  1. Efficient Reinforcement Finetuning via Adaptive Curriculum Learning
    Taiwei Shi, Yiyang Wu, Linxin Song, and 2 more authors
    arXiv preprint arXiv:2504.05520, 2025
  2. GenQA: Generating Millions of Instructions from a Handful of Prompts
    Jiuhai Chen, Rifaa Qadri, Yuxin Wen, and 4 more authors
    arXiv preprint arXiv:2406.10323, 2024
  3. UniGen: A Unified Framework for Textual Dataset Generation Using Large Language Models
    Siyuan Wu, Yue Huang, Chujie Gao, and 8 more authors
    arXiv preprint arXiv:2406.18966, 2024
  1. CIKM
    Generative Models for Synthetic Data: Transforming Data Mining in the GenAI Era
    Dawei Li, Yue Huang, Ming Li, and 3 more authors
    In The 34th ACM International Conference on Information and Knowledge Management (CIKM), 2025
  2. Mosaic IT: Enhancing Instruction Tuning with Data Mosaics
    Ming Li, Pei Chen, Chenguang Wang, and 5 more authors
    In The 63rd Annual Meeting of the Association for Computational Linguistics (ACL) Findings, 2025
  3. DataGen: Unified Synthetic Dataset Generation via Large Language Models
    Yue Huang, Siyuan Wu, Chujie Gao, and 8 more authors
    In The Thirteenth International Conference on Learning Representations (ICLR), 2025
  4. RuleR: Improving LLM Controllability by Rule-based Data Recycling
    Ming Li, Han Chen, Chenguang Wang, and 3 more authors
    In Annual Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics (NAACL), 2025
  5. ACL
    superfiltering.png
    Superfiltering: Weak-to-Strong Data Filtering for Fast Instruction-Tuning
    Ming Li, Yong Zhang, Shwai He, and 5 more authors
    In Annual Meeting of the Association for Computational Linguistics (ACL), 2024
  6. Can LLMs Speak For Diverse People? Tuning LLMs via Debate to Generate Controllable Controversial Statements
    Ming Li, Jiuhai Chen, Lichang Chen, and 1 more author
    In Annual Meeting of the Association for Computational Linguistics (ACL) Findings, 2024
  7. Selective Reflection-Tuning: Student-Selected Data Recycling for LLM Instruction-Tuning
    Ming Li, Lichang Chen, Jiuhai Chen, and 3 more authors
    In Annual Meeting of the Association for Computational Linguistics (ACL) Findings, 2024
  8. From Quantity to Quality: Boosting LLM Performance with Self-Guided Data Selection for Instruction Tuning
    Ming Li, Yong Zhang, Zhitao Li, and 6 more authors
    In Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL), 2024
  9. Alpagasus: Training a Better Alpaca Model with Fewer Data
    Lichang Chen, Shiyang Li, Jun Yan, and 8 more authors
    In International Conference on Learning Representations (ICLR), 2024
  10. Efficient Reinforcement Finetuning via Adaptive Curriculum Learning
    Taiwei Shi, Yiyang Wu, Linxin Song, and 2 more authors
    Transactions on Machine Learning Research (TMLR), 2026
Post-training & Reasoning
  1. Thinking Hard, Not Smart: Reasoning Models Fail to Ration Test-Time Compute Across Questions
    Chenrui Fan, Yize Cheng, Ming Li, and 3 more authors
    arXiv preprint arXiv:2608.07968, 2026
  2. Weak-to-Strong On-Policy Distillation
    Fangxu Yu, Weijia Xu, Michael Xu, and 2 more authors
    arXiv preprint arXiv:2607.26246, 2026
  3. A Survey on Knowledge Distillation of Large Language Models
    Xiaohan Xu, Ming Li, Chongyang Tao, and 6 more authors
    arXiv preprint arXiv:2402.13116, 2024
  4. What Makes Reasoning Models Different? Follow the Reasoning Leader for Efficient Decoding
    Ming Li, Zhengyuan Yang, Xiyao Wang, and 4 more authors
    arXiv preprint arXiv:2506.06998, 2025
  1. Routing Entropy: A Hidden Self-Verifier for Free in Mixture-of-Experts LLMs
    Zhongyang Li, Ziyue Li, and Tianyi Zhou
    In Third Conference on Language Modeling (COLM), 2026
  2. ACL
    repo-mingliiii_gradient_unified.png
    How Instruction and Reasoning Data shape Post-Training: Data Quality through the Lens of Layer-wise Gradients
    Ming Li, Yanhong Li, Ziyue Li, and 1 more author
    In Annual Meeting of the Association for Computational Linguistics (ACL), 2026
  3. ACL
    repo-zxiangx_lc-r1.png
    Optimizing Length Compression in Large Reasoning Models
    Zhengxiang Cheng, Dongping Chen, Mingyang Fu, and 1 more author
    In Annual Meeting of the Association for Computational Linguistics (ACL), 2026
  4. Routing Manifold Alignment Improves Generalization of Mixture-of-Experts LLMs
    Zhongyang Li, Ziyue Li, and Tianyi Zhou
    In The Fourteenth International Conference on Learning Representations (ICLR), 2026
  5. Don’t Think Longer, Think Wisely: Optimizing Thinking Dynamics for Large Reasoning Models
    Sohyun An, Ruochen Wang, Tianyi Zhou, and 1 more author
    In The Thirty-ninth Annual Conference on Neural Information Processing Systems (NeurIPS), 2025
  6. Understanding the Thinking Process of Reasoning Models: A Perspective from Schoenfeld’s Episode Theory
    Ming Li, Nan Zhang, Chenrui Fan, and 6 more authors
    In The 2025 Conference on Empirical Methods in Natural Language Processing (EMNLP), 2025
  7. Wait, We Don’t Need to" Wait"! Removing Thinking Tokens Improves Reasoning Efficiency
    Chenlong Wang, Yuanning Feng, Dongping Chen, and 3 more authors
    In The 2025 Conference on Empirical Methods in Natural Language Processing (EMNLP) Findings, 2025
  8. Missing Premise exacerbates Overthinking: Are Reasoning Models losing Critical Thinking Skill?
    Chenrui Fan, Ming Li, Lichao Sun, and 1 more author
    In Conference on Language Modeling (COLM), 2025
  9. ACL
    layergrad.png
    What Happened in LLMs Layers when Trained for Fast vs. Slow Thinking: A Gradient PerspectiveOral
    Ming Li, Yanhong Li, and Tianyi Zhou
    In The 63rd Annual Meeting of the Association for Computational Linguistics (ACL), 2025
  10. Multi-Objective Linguistic Control of Large Language Models
    Dang Nguyen, Jiuhai Chen, and Tianyi Zhou
    In Annual Meeting of the Association for Computational Linguistics (ACL) Findings, 2024
  11. Cognitive Episodes in LLM Reasoning Traces Enable Interpretable Human Item Difficulty Prediction
    Chenguang Wang, Ming Li, Xinyue Zeng, and 4 more authors
    Transactions on Machine Learning Research (TMLR), 2026
Human–AI Alignment & Reward Hacking
  1. Representing Visual Evidence for Item Difficulty Prediction: Visual Textualization and Image-Native Modeling
    Han Chen, Ming Li, Hong Jiao, and 1 more author
    arXiv preprint arXiv:2608.04554, 2026
  2. Can LLMs Really Understand Item Difficulty Levels? Implications for Automated Item Generation Using LLMs
    Xinyi Wang, Hong Jiao, Ming Li, and 4 more authors
    arXiv preprint arXiv:2607.28634, 2026
  3. LLMs Struggle to Measure What Distinguishes Students of Different Proficiency Levels: A Study of Item Discrimination in Reading Comprehension Assessment
    Han Chen, Ming Li, Chenguang Wang, and 4 more authors
    arXiv preprint arXiv:2606.18709, 2026
  4. Automated Alignment of Math Items to Content Standards in Large-Scale Assessments Using Language Models
    Qingshu Xu, Hong Jiao, Tianyi Zhou, and 4 more authors
    arXiv preprint arXiv:2510.05129, 2025
  5. Controllable Pareto Trade-off between Fairness and Accuracy
    Yongkang Du, Jieyu Zhao, Yijun Yang, and 1 more author
    arXiv preprint arXiv:2509.13651, 2025
  6. Preprint
    Human Modeling Meets AI Metacognition: Toward Coupled Cognitive Alignment for Interactive Agents
    Yaochen Wang, Ming Li, Xirui Li, and 1 more author
    Position paper, under review, 2026
  1. ACL
    thinkarm.png
    Schoenfeld’s Anatomy of Mathematical Reasoning by Language ModelsOral · SAC Highlight
    Ming Li, Chenrui Fan, Yize Cheng, and 2 more authors
    In Annual Meeting of the Association for Computational Linguistics (ACL), 2026
  2. Can LLMs Estimate Student Struggles? Human-AI Difficulty Alignment with Proficiency Simulation for Item Difficulty Prediction
    Ming Li, Han Chen, Yunze Xiao, and 3 more authors
    In Annual Meeting of the Association for Computational Linguistics (ACL) Findings, 2026
  3. AI, Take the Wheel: What Drives Delegation and Trust in Human–Computer Cooperative Question Answering?
    Maharshi Gor, Yoo Yeon Sung, Yu Hou, and 4 more authors
    In Annual Meeting of the Association for Computational Linguistics (ACL) Findings, 2026
  4. ACL
    arxiv-2409.11704.png
    From Lists to Emojis: How format bias affects model alignment
    Xuanchang Zhang, Wei Xiong, Lichang Chen, and 3 more authors
    In The 63rd Annual Meeting of the Association for Computational Linguistics (ACL), 2025
  5. Do great minds think alike? Investigating Human-AI Complementarity for Question Answering
    Maharshi Gor, Hal Daumé III, Tianyi Zhou, and 1 more author
    In The 2024 Conference on Empirical Methods in Natural Language Processing (EMNLP), 2024
  6. ODIN: Disentangled Reward Mitigates Hacking in RLHF
    Lichang Chen, Chen Zhu, Davit Soselia, and 6 more authors
    In International Conference on Machine Learning (ICML), 2024
  7. One Model for All: Multi-Objective Controllable Language Models
    Qiang He, Yucheng Yang, Tianyi Zhou, and 3 more authors
    Transactions on Machine Learning Research, 2026
Generalization, Memorization & Architecture
  1. Skip a Layer or Loop It? Test-Time Depth Adaptation of Pretrained LLMs
    Ziyue Li, Yang Li, and Tianyi Zhou
    arXiv preprint arXiv:2507.07996, 2025
  2. The 4th Dimension for Scaling Model Size
    Ruike Zhu, Hanwen Zhang, Tianyu Shi, and 3 more authors
    arXiv preprint arXiv:2506.18233, 2025
  3. Preprint
    Doing More with Less: Monitoring Generalization During Pretraining via Virtual MoE
    Ziyue Li and Tianyi Zhou
    Under review, 2026
  1. Skip a Layer or Loop It? Learning Program-of-Layers in LLMsOral
    Ziyue Li, Yang Li, and Tianyi Zhou
    In Forty-third International Conference on Machine Learning (ICML), 2026
  2. Grokking in LLM Pretraining? Monitor Memorization-to-Generalization without Test
    Ziyue Li, Chenrui Fan, and Tianyi Zhou
    In The Fourteenth International Conference on Learning Representations (ICLR), 2026
  3. Your Mixture-of-Experts LLM Is Secretly an Embedding Model For FreeOral
    Ziyue Li and Tianyi Zhou
    In The Thirteenth International Conference on Learning Representations (ICLR), 2025
  4. Sparser Mixture-of-Adapters with Cross-Layer Generalization
    Ziyue Li and Tianyi Zhou
    In Annual Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics (NAACL), 2025
  5. ACL
    arxiv-2402.18458.png
    Meta-Task Prompting Elicits Embedding from Large Language Models
    Yibin Lei, Di Wu, Tianyi Zhou, and 4 more authors
    In Annual Meeting of the Association for Computational Linguistics (ACL), 2024
  6. Bias Also Matters: Bias Attribution for Deep Neural Network Explanation
    Tianyi Zhou, Shengjie Wang, and Jeff A. Bilmes
    In International Conference on Machine Learning (ICML), Long Beach, CA, 2019
  7. Extracting Local Reasoning Chains of Deep Neural Networks
    Haiyan Zhao, Tianyi Zhou, Guodong Long, and 2 more authors
    Transactions on Machine Learning Research, 2022
Prompting & Test-time Optimization
  1. When is Your LLM Steerable?
    Chenrui Fan, Yize Cheng, Ming Li, and 2 more authors
    arXiv preprint arXiv:2606.11599, 2026
  2. When Do You Need Chain-of-Thought Prompting for ChatGPT?
    Jiuhai Chen, Lichang Chen, Heng Huang, and 1 more author
    arXiv preprint arXiv:2304.03262, 2023
  1. C3PO: Critical-Layer, Core-Expert, Collaborative Pathway Optimization for Test-Time Expert Re-Mixing
    Zhongyang Li, Ziyue Li, and Tianyi Zhou
    In Conference on Language Modeling (COLM), 2025
  2. 1+1>2: Can Large Language Models Serve as Cross-Lingual Knowledge Aggregators?
    Yue Huang, Chenrui Fan, Yuan Li, and 4 more authors
    In The 2024 Conference on Empirical Methods in Natural Language Processing (EMNLP), 2024
  3. InstructZero: Efficient Instruction Optimization for Black-Box Large Language Models
    Lichang Chen, Jiuhai Chen, Heng Huang, and 2 more authors
    In International Conference on Machine Learning (ICML), 2024
  4. One Prompt is not Enough: Automated Construction of a Mixture-of-Expert Prompts
    Ruochen Wang, Sohyun An, Minhao Cheng, and 3 more authors
    In International Conference on Machine Learning (ICML), 2024
In-context Learning
    1. Where to show Demos in Your Prompt: A Positional Bias of In-Context Learning
      Kwesi Cobbina and Tianyi Zhou
      In The 2025 Conference on Empirical Methods in Natural Language Processing (EMNLP), 2025
    2. BenTo: Benchmark Task Reduction with In-Context Transferability
      Hongyu Zhao, Ming Li, Lichao Sun, and 1 more author
      In The Thirteenth International Conference on Learning Representations (ICLR), 2025
    3. An End-to-End Submodular Framework for Data-Efficient In-Context Learning
      Lilly Kumari, Shengjie Wang, Arnav Mohanty Das, and 2 more authors
      In Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL) Findings, 2024
    4. How Many Demonstrations Do You Need for In-context Learning?
      Jiuhai Chen, Lichang Chen, Chen Zhu, and 1 more author
      In The 2023 Conference on Empirical Methods in Natural Language Processing (EMNLP) Findings, 2023
    Efficient Decoding
      1. InfoFlow KV: Information-Flow-Aware KV Recomputation for Long Context
        Xin Teng, Canyu Zhang, Shaoyi Zheng, and 3 more authors
        In Forty-third International Conference on Machine Learning (ICML), 2026
      2. SpecHub: Provable Acceleration to Multi-Draft Speculative Decoding
        Hanchi Sun, Tianyi Zhou, Xun Chen, and 1 more author
        In The 2024 Conference on Empirical Methods in Natural Language Processing (EMNLP), 2024
      3. BumbleBee: Dynamic KV Cache Summarization in Transformers using Submodular Optimization
        Lilly Kumari, Shengjie Wang, Tianyi Zhou, and 3 more authors
        In First Conference on Language Modeling (COLM), 2024
      Retrieval & Embeddings
        1. Large Language Models are Strong Zero-Shot Retriever
          Tao Shen, Guodong Long, Xiubo Geng, and 5 more authors
          In Annual Meeting of the Association for Computational Linguistics (ACL) Findings, 2024
        2. Corpus-Steered Query Expansion with Large Language Models
          Yibin Lei, Yu Cao, Tianyi Zhou, and 2 more authors
          In The 18th Conference of the European Chapter of the Association for Computational Linguistics (EACL), 2024
        Safety & Jailbreaking
        1. Do Prompt-Elicited Trajectories Reflect Training-Time Reward Hacking? A Systematic Study on Monitoring Training-Time Reward Hacking in Code Generation
          Lichen Li, Hengguang Zhou, Yijun Liang, and 2 more authors
          arXiv preprint arXiv:2604.23488, 2026
        1. TrustGen: A Platform of Dynamic Benchmarking on the Trustworthiness of Generative Foundation Models
          Yue Huang, Chujie Gao, Siyuan Wu, and 7 more authors
          In The Fourteenth International Conference on Learning Representations (ICLR), 2026
        2. DrAttack: Prompt Decomposition and Reconstruction Makes Powerful LLM Jailbreakers
          Xirui Li, Ruochen Wang, Minhao Cheng, and 2 more authors
          In The 2024 Conference on Empirical Methods in Natural Language Processing (EMNLP) Findings, 2024
        3. TrustLLM: Trustworthiness in Large Language Models
          Lichao Sun, Yue Huang, and al
          In International Conference on Machine Learning (ICML), 2024
        Benchmarks & Evaluation
        1. When AI Navigates the Fog of War
          Ming Li, Xirui Li, and Tianyi Zhou
          arXiv preprint arXiv:2603.16642, 2026
        2. NLPBench: Evaluating Large Language Models on Solving NLP Problems
          Linxin Song, Jieyu Zhang, Lechao Cheng, and 3 more authors
          arXiv preprint arXiv:2309.15630, 2023
        1. TrustGen: A Platform of Dynamic Benchmarking on the Trustworthiness of Generative Foundation Models
          Yue Huang, Chujie Gao, Siyuan Wu, and 7 more authors
          In The Fourteenth International Conference on Learning Representations (ICLR), 2026
        2. Easy2Hard-Bench: Standardized Difficulty Labels for Profiling LLM Performance and Generalization
          Mucong Ding, Chenghao Deng, Jocelyn Choo, and 8 more authors
          In Advances in Neural Information Processing Systems 38 (NeurIPS) Datasets and Benchmarks Track, 2024
        3. EPM
          Item Difficulty Modeling Using Fine-tuned Small and Large Language ModelseAA Best Research
          Ming Li, Hong Jiao, Tianyi Zhou, and 3 more authors
          Educational and Psychological Measurement, 2025

        Multimodal Models

        Architectures & Unified Models
        1. Self-Evolving Visual Questioner
          Yijun Liang, Hengguang Zhou, Ming Li, and 3 more authors
          arXiv preprint arXiv:2606.13929, 2026
        2. TS-Reasoner: Aligning Time Series Foundation Models with LLM Reasoning
          Fangxu Yu, Hongyu Zhao, and Tianyi Zhou
          arXiv preprint arXiv:2510.03519, 2025
        3. BLIP3o-NEXT: Next Frontier of Native Image Generation
          Jiuhai Chen, Le Xue, Zhiyang Xu, and 12 more authors
          arXiv preprint arXiv:2510.15857, 2025
        4. Pisces: An Auto-regressive Foundation Model for Image Understanding and Generation
          Zhiyang Xu, Jiuhai Chen, Zhaojiang Lin, and 10 more authors
          arXiv preprint arXiv:2506.10395, 2025
        5. BLIP3-o: A Family of Fully Open Unified Multimodal Models – Architecture, Training and Dataset
          Jiuhai Chen, Zhiyang Xu, Xichen Pan, and 10 more authors
          arXiv preprint arXiv:2505.09568, 2025
        1. TSRouter: Dynamic Modality-Model Selection for Time Series Reasoning
          Fangxu Yu, Tao Feng, Dehai Min, and 3 more authors
          In Third Conference on Language Modeling (COLM), 2026
        2. Florence-VL: Enhancing Vision-Language Models with Generative Vision Encoder and Depth-Breadth Fusion
          Jiuhai Chen, Jianwei Yang, Haiping Wu, and 4 more authors
          In The IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025
        3. TS-Reasoner: Aligning Time Series Foundation Models with LLM Reasoning
          Fangxu Yu, Hongyu Zhao, and Tianyi Zhou
          Transactions on Machine Learning Research (TMLR), 2026
        Post-training & Alignment
        1. Reinforcement Learning with Evolving Rubrics as Rewards for Audio Reasoning
          Fangxu Yu, Tao Feng, Dehai Min, and 6 more authors
          arXiv preprint arXiv:2608.02831, 2026
        2. Visual Contrastive Self-Distillation
          Yijun Liang, Yunjie Tian, Yijiang Li, and 4 more authors
          arXiv preprint arXiv:2607.21556, 2026
        3. ChartDesign: Towards LLM Designer of Data Visualization
          Mohammed Afaan Ansari, Aniruddh Bansal, and Tianyi Zhou
          arXiv preprint arXiv:2605.16274, 2026
        4. R1-Zero’s “Aha Moment” in Visual Reasoning on a 2B Non-SFT Model
          Hengguang Zhou, Xirui Li, Ruochen Wang, and 3 more authors
          arXiv preprint arXiv:2503.05132, 2025
        5. Modality-Balancing Preference Optimization of Large Multimodal Models by Adversarial Negative Mining
          Chenxi Liu, Tianyi Xiong, Ruibo Chen, and 4 more authors
          arXiv preprint arXiv:2506.08022, 2025
        6. Learning UI-to-Code Reverse Generator Using Visual Critic Without Rendering
          Davit Soselia, Khalid Saifullah, and Tianyi Zhou
          arXiv preprint arXiv:2305.14637, 2023
        1. What does RL improve for Visual Reasoning? A Frankenstein-Style Analysis
          Xirui Li, Ming Li, and Tianyi Zhou
          In Third Conference on Language Modeling (COLM), 2026
        2. ECA: Efficient Continual Alignment for Open-Ended Image-to-Text Generation
          Jiangtao Kong, Peijun Zhao, Chun-Fu Chen, and 4 more authors
          In Forty-third International Conference on Machine Learning (ICML), 2026
        3. Vision-Zero: Scalable vlm self-improvement via strategic gamified self-play
          Qinsi Wang, Bo Liu, Tianyi Zhou, and 6 more authors
          In The Fourteenth International Conference on Learning Representations (ICLR), 2026
        4. Wait, We Don’t Need to" Wait"! Removing Thinking Tokens Improves Reasoning Efficiency
          Chenlong Wang, Yuanning Feng, Dongping Chen, and 3 more authors
          In The 2025 Conference on Empirical Methods in Natural Language Processing (EMNLP) Findings, 2025
        5. Enhancing Visual-Language Modality Alignment in Large Vision Language Models via Self-Improvement
          Xiyao Wang, Jiuhai Chen, Zhaoyang Wang, and 8 more authors
          In Annual Conference of the Nations of the Americas Chapter of the ACL (NAACL) Findings, 2025
        6. Embodied Multi-Modal Agent trained by an LLM from a Parallel TextWorld
          Yijun Yang, Tianyi Zhou, Kanxue Li, and 6 more authors
          In IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024
        7. Module-wise Adaptive Distillation for Multimodality Foundation Models
          Chen Liang, Jiahui Yu, Ming-Hsuan Yang, and 5 more authors
          In Advances in Neural Information Processing Systems 37 (NeurIPS), 2023
        8. EmoRouter: Adaptive Modality Selection for Multimodal Emotion Recognition
          Fangxu Yu, Lingzhi Yuan, Dehai Min, and 4 more authors
          Transactions on Machine Learning Research (TMLR), 2026
        Benchmarks, Hallucination & Evaluation
        1. Quantifying the Gap between Understanding and Generation within Unified Multimodal Models
          Chenlong Wang, Yuhang Chen, Zhihan Hu, and 4 more authors
          arXiv preprint arXiv:2602.02140, 2026
        2. ChartAB: A Benchmark for Chart Grounding & Dense Alignment
          Aniruddh Bansal, Davit Soselia, Dang Nguyen, and 1 more author
          arXiv preprint arXiv:2510.26781, 2025
        3. VisR-Bench: An Empirical Study on Visual Retrieval-Augmented Generation for Multilingual Long Document Understanding
          Jian Chen, Ming Li, Jihyung Kil, and 6 more authors
          arXiv preprint arXiv:2508.07493, 2025
        4. CaughtCheating: Is Your MLLM a Good Cheating Detective? Exploring the Boundary of Visual Perception and Reasoning
          Ming Li, Chenguang Wang, Yijun Liang, and 6 more authors
          arXiv preprint arXiv:2507.00045, 2025
        5. GraphicBench: A Planning Benchmark for Graphic Design with Language Agents
          Dayeon Ki, Tianyi Zhou, Marine Carpuat, and 3 more authors
          arXiv preprint arXiv:2504.11571, 2025
        6. Towards Visual Text Grounding of Multimodal Large Language Model
          Ming Li, Ruiyi Zhang, Jian Chen, and 6 more authors
          arXiv preprint arXiv:2504.04974, 2025
        7. AutoBench-V: Can Large Vision-Language Models Benchmark Themselves?
          Han Bao, Yue Huang, Yanbo Wang, and 7 more authors
          arXiv preprint arXiv:2410.21259, 2024
        1. V-REX: Benchmarking Exploratory Visual Reasoning via Chain-of-Questions
          Chenrui Fan, Yijun Liang, Shweta Bhardwaj, and 3 more authors
          In The European Conference on Computer Vision (ECCV), 2026
        2. TSRBench: A Comprehensive Multi-task Multi-modal Time Series Reasoning Benchmark for Generalist Models
          Fangxu Yu, Xingang Guo, Lingzhi Yuan, and 6 more authors
          In Forty-third International Conference on Machine Learning (ICML), 2026
        3. KDD
          AutoDavis: Automatic and Dynamic Evaluation Protocol of Large Vision-Language Models on Visual Question-Answering
          Han Bao, Yue Huang, Yanbo Wang, and 7 more authors
          In ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD) Datasets & Benchmarks Track, 2026
        4. ColorBench: Can VLMs See and Understand the Colorful World? A Comprehensive Benchmark for Color Perception, Reasoning, and Robustness
          Yijun Liang, Ming Li, Chenrui Fan, and 7 more authors
          In The Thirty-ninth Annual Conference on Neural Information Processing Systems (NeurIPS) Datasets and Benchmarks Track, 2025
        5. VideoHallu: Evaluating and Mitigating Multi-modal Hallucinations for Synthetic Videos
          Zongxia Li, Xiyang Wu, Yubin Qin, and 5 more authors
          In The Thirty-ninth Annual Conference on Neural Information Processing Systems (NeurIPS), 2025
        6. OmnixR: Evaluating Omni-modality Language Models on Reasoning across Modalities
          Lichang Chen, Hexiang Hu, Mingda Zhang, and 8 more authors
          In The Thirteenth International Conference on Learning Representations (ICLR), 2025
        7. MOSSBench: Is Your Multimodal Language Model Oversensitive to Safe Queries?
          Xirui Li, Hengguang Zhou, Ruochen Wang, and 3 more authors
          In The Thirteenth International Conference on Learning Representations (ICLR), 2025
        8. AUTOHALLUSION: Automatic Generation of Hallucination Benchmarks for Vision-Language Models
          Xiyang Wu, Tianrui Guan, Dianqi Li, and 9 more authors
          In The 2024 Conference on Empirical Methods in Natural Language Processing (EMNLP) Findings, 2024
        9. HallusionBench: An Advanced Diagnostic Suite for Entangled Language Hallucination and Visual Illusion in Large Vision-Language Models
          Tianrui Guan, Fuxiao Liu, Xiyang Wu, and 9 more authors
          In IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024
        Test-time Optimization
        1. Good Questions Help Zero-Shot Image Reasoning
          Kaiwen Yang, Tao Shen, Xinmei Tian, and 4 more authors
          arXiv preprint arXiv:2312.01598, 2023
        1. R2-T2: Re-Routing in Test-Time for Multimodal Mixture-of-Experts
          Zhongyang Li, Ziyue Li, and Tianyi Zhou
          In Forty-Second International Conference on Machine Learning (ICML), 2025
        Diffusion Models
        1. Multi-Turn Reflective Masking Elicits Reasoning in Mask Diffusion Models
          Yanming Zhang, Yihan Bian, Jingyuan Qi, and 3 more authors
          arXiv preprint arXiv:2606.16700, 2026
        2. MuLan: Multimodal-LLM Agent for Progressive Multi-Object Diffusion
          Sen Li, Ruochen Wang, Cho-Jui Hsieh, and 2 more authors
          arXiv preprint arXiv:2402.12741, 2024
        3. Diffusion Curriculum: Synthetic-to-Real Generative Curriculum Learning via Image-Guided Diffusion
          Yijun Liang, Shweta Bhardwaj, and Tianyi Zhou
          arXiv preprint arXiv:2410.13674, 2024
        1. Diffusion Curriculum: Synthetic-to-Real Generative Curriculum Learning via Image-Guided Diffusion
          Yijun Liang, Shweta Bhardwaj, and Tianyi Zhou
          In International Conference on Computer Vision (ICCV), 2025
        2. The Crystal Ball Hypothesis in diffusion models: Anticipating object positions from initial noise
          Yuanhao Ban, Ruochen Wang, Tianyi Zhou, and 3 more authors
          In The Thirteenth International Conference on Learning Representations (ICLR), 2025
        3. When and How do negative prompts take effect?
          Yuanhao Ban, Ruochen Wang, Tianyi Zhou, and 3 more authors
          In European Conference on Computer Vision (ECCV), 2024
        4. Do text-free diffusion models learn discriminative visual representations?
          Soumik Mukhopadhyay, Matthew Gwilliam, Yosuke Yamaguchi, and 6 more authors
          In European Conference on Computer Vision (ECCV), 2024

        Agents & World Models

        Agents, World Models & Embodied AI
        1. Steering Automated Scientific Discovery via Audited Epistemic Exploration
          Fangxu Yu, Tao Feng, Xuying Ning, and 3 more authors
          arXiv preprint arXiv:2611.25214, 2026
        2. Failure Recovery via Belief Updates and World Modeling for Long-Horizon Agents
          Xiyang Wu, Zhichao Liu, Shengxin Zhang, and 4 more authors
          arXiv preprint arXiv:2610.18082, 2026
        3. A Missing Piece for Trustworthy AI Reviewers: From Benchmarking Rhetorical Robustness to SciCore Review
          Chenguang Wang, Ming Li, Chengrui Fan, and 4 more authors
          arXiv preprint arXiv:2609.39027, 2026
        4. The Emerging AI Paper-Review Arms Race: Adversarial Co-Evolution in Scholarly Publishing
          Chenguang Wang, Ming Li, Adebayo Braimah, and 6 more authors
          arXiv preprint arXiv:2609.07713, 2026
        5. How Can Rhetoric Reward-Hack AI Reviewers? Dissecting Rhetorical Sensitivity in AI-Based Peer Review
          Ming Li, Chenguang Wang, Xirui Li, and 5 more authors
          arXiv preprint arXiv:2608.08975, 2026
        6. Guava: Distilling Frontier VLMs into a Compact Agent through a Robotic Manipulation Harness
          Haowen Liu, Xirui Li, Shaoxiong Yao, and 5 more authors
          arXiv preprint arXiv:2606.18363, 2026
        7. MuLan: Multimodal-LLM Agent for Progressive Multi-Object Diffusion
          Sen Li, Ruochen Wang, Cho-Jui Hsieh, and 2 more authors
          arXiv preprint arXiv:2402.12741, 2024
        8. ClawEnvKit: Automatic Environment Generation for Claw-Like Agents
          Xirui Li, Ming Li, Ion Stoica, and 2 more authors
          arXiv preprint arXiv:2604.18543, 2026
        9. Superminds Test: Actively Evaluating Collective Intelligence of Agent Society via Probing Agents
          Xirui Li, Ming Li, Yunze Xiao, and 4 more authors
          arXiv preprint arXiv:2604.22452, 2026
        10. Co-Evolving LLM Decision and Skill Bank Agents for Long-Horizon Tasks
          Xiyang Wu, Zongxia Li, Guangyao Shi, and 5 more authors
          arXiv preprint arXiv:2604.20987, 2026
        11. WALL-E: World Alignment by Rule Learning Improves World Model-based LLM Agents
          Siyu Zhou, Tianyi Zhou, Yijun Yang, and 4 more authors
          arXiv preprint arXiv:2410.07484, 2024
        12. Preprint
          Library Learning of Code Actions for Agentic Vision Tasks
          Dang Nguyen and Tianyi Zhou
          Under review, 2026
        13. Preprint
          Human Modeling Meets AI Metacognition: Toward Coupled Cognitive Alignment for Interactive Agents
          Yaochen Wang, Ming Li, Xirui Li, and 1 more author
          Position paper, under review, 2026
        1. OopsWorld! Operation-Grounded Seamless World Generation
          Dongping Chen and Tianyi Zhou
          In The Fortieth Annual Conference on Neural Information Processing Systems (NeurIPS), 2026
        2. Sandboxed Coding Agents are Competitive Omni-modal Task Solvers
          Dongping Chen, Xuanao Huang, Zhihan Hu, and 3 more authors
          In The Fortieth Annual Conference on Neural Information Processing Systems (NeurIPS), 2026
        3. CoSTA*: Cost-Sensitive Toolpath Agent for Multi-turn Image Editing
          Advait Gupta, NandaKiran Velaga, Dang Nguyen, and 1 more author
          In Findings of the 2026 Conference on Empirical Methods in Natural Language Processing (EMNLP), 2026
        4. Neuro-Symbolic Synergy for Interactive World Modeling
          Hongyu Zhao, Siyu Zhou, Haolin Yang, and 2 more authors
          In Third Conference on Language Modeling (COLM), 2026
        5. WALL-EVE: World Alignment with Rule Learning in Visual Environments
          Siyu Zhou, Tianyi Zhou, Yijun Yang, and 4 more authors
          In The European Conference on Computer Vision (ECCV), 2026
        6. IROS
          arxiv-2503.04994.png
          Polysona: Modular Driving Styles in Trajectory Prediction
          Laura Zheng, Hamidreza Yaghoubi Araghi, Tony Wu, and 2 more authors
          In IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2026
        7. IROS
          arxiv-2603.06480.png
          History-Conditioned Spatio-Temporal Visual Token Pruning for Efficient Vision-Language Navigation
          Qitong Wang, Yijun Liang, Ming Li, and 2 more authors
          In IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2026
        8. WestWorld: A Knowledge-Encoded Scalable Trajectory World Model for Diverse Robotic SystemsSpotlight
          Yuchen Wang, Jiangtao Kong, Sizhe Wei, and 6 more authors
          In Forty-third International Conference on Machine Learning (ICML), 2026
        9. CAIS
          repo-tianyi-lab_moltbook_socialization.png
          Does Socialization Emerge in AI Agent Society? A Case Study of Moltbook
          Ming Li, Xirui Li, and Tianyi Zhou
          In ACM Conference on AI and Agentic Systems (CAIS), 2026
        10. FaSTA*: Fast-Slow Toolpath Agent with Subroutine Mining for Efficient Multi-turn Image Editing
          Advait Gupta, Rishie Raj, Dang Nguyen, and 1 more author
          In The Fourteenth International Conference on Learning Representations (ICLR), 2026
        11. Skill Discovery for Software Scripting Automation via Offline Simulations with LLMs
          Paiheng Xu, Gang Wu, Xiang Chen, and 6 more authors
          In 19th Conference of the European Chapter of the Association for Computational Linguistics (EACL) findings, 2026
        12. WALL-E: World Alignment by NeuroSymbolic Learning improves World Model-based LLM Agents
          Siyu Zhou, Tianyi Zhou, Yijun Yang, and 4 more authors
          In The Thirty-ninth Annual Conference on Neural Information Processing Systems (NeurIPS), 2025
        13. DynaSaur: Large Language Agents Beyond Predefined Actions
          Dang Nguyen, Viet Dac Lai, Seunghyun Yoon, and 9 more authors
          In Conference on Language Modeling (COLM), 2025
        14. IROS
          arxiv-2503.04994.png
          Quantifying and Modeling Driving Style in Trajectory Forecasting
          Laura Zheng, Hamidreza Yaghoubi Araghi, Tony Wu, and 3 more authors
          In IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2025
        15. ACL
          Multiple LLM Agents Debate for Equitable Cultural AlignmentOral
          Dayeon Ki, Rachel Rudinger, Tianyi Zhou, and 1 more author
          In The 63rd Annual Meeting of the Association for Computational Linguistics (ACL), 2025
        16. Click, Type, Repeat: A Comprehensive Survey on GUI Agents
          Dang Nguyen, Jian Chen, Yu Wang, and 26 more authors
          In The 63rd Annual Meeting of the Association for Computational Linguistics (ACL) Findings, 2025
        17. ATLaS: Agent tuning via learning critical steps
          Zhixun Chen, Ming Li, Yuxuan Huang, and 3 more authors
          In The 63rd Annual Meeting of the Association for Computational Linguistics (ACL) Findings, 2025
        18. Embodied Multi-Modal Agent trained by an LLM from a Parallel TextWorld
          Yijun Yang, Tianyi Zhou, Kanxue Li, and 6 more authors
          In IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024
        19. ICRA
          Task-Driven Domain-Agnostic Learning with Information Bottleneck for Autonomous Steering
          Yu Shen, Laura Zheng, Tianyi Zhou, and 1 more author
          In IEEE International Conference on Robotics and Automation (ICRA), 2024
        Reinforcement Learning
        1. Curriculum Reinforcement Learning via Morphology-Environment Co-Evolution
          Shuang Ao, Tianyi Zhou, Guodong Long, and 2 more authors
          arXiv preprint arXiv:2309.12529, 2023
        1. IROS
          arxiv-2306.06192.png
          Confidence-Controlled Exploration: Efficient Sparse-Reward Policy Learning for Robotic Navigation
          Bhrij Patel, Kasun Weerakoon Kulathun Mudiyanselage, Wesley A. Suttle, and 5 more authors
          In IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2025
        2. Preference Controllable Reinforcement Learning with Advanced Multi-Objective Optimization
          Yucheng Yang, Tianyi Zhou, Meng Fang, and 1 more author
          In Forty-Second International Conference on Machine Learning (ICML), 2025
        3. Task Adaptation from Skills: Information Geometry, Disentanglement, and New Objectives for Unsupervised Reinforcement LearningSpotlight
          Yucheng Yang, Tianyi Zhou, Qiang He, and 3 more authors
          In International Conference on Learning Representations (ICLR), 2024
        4. Adaptive Regularization of Representation Rank as an Implicit Constraint of Bellman Equation
          Qiang He, Tianyi Zhou, Meng Fang, and 1 more author
          In International Conference on Learning Representations (ICLR), 2024
        5. ECML-PKDD
          arxiv-2306.16750.png
          Eigensubspace of Temporal-Difference Dynamics and How It Improves Value Approximation in Reinforcement Learning
          Qiang He, Tianyi Zhou, Meng Fang, and 1 more author
          In European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML/PKDD), 2023
        6. EAT-C: Environment-Adversarial sub-Task Curriculum for Efficient Reinforcement Learning
          Shuang Ao, Tianyi Zhou, Jing Jiang, and 3 more authors
          In International Conference on Machine Learning (ICML), 2022
        7. Pareto Policy Pool for Model-based Offline Reinforcement Learning
          Yijun Yang, Jing Jiang, Tianyi Zhou, and 2 more authors
          In International Conference on Learning Representations (ICLR), 2022
        8. CO-PILOT: COllaborative Planning and reInforcement Learning On sub-Task curriculum
          Shuang Ao, Tianyi Zhou, Guodong Long, and 3 more authors
          In Advances in Neural Information Processing Systems 35 (NeurIPS), 2021
        9. Curriculum-guided Hindsight Experience Replay
          Meng Fang, Tianyi Zhou, Yali Du, and 2 more authors
          In Advances in Neural Information Processing Systems 33 (NeurIPS), Vancouver, BC, Canada, 2019
        10. Reinforced Self-Attention Network: a Hybrid of Hard and Soft Attention for Sequence Modeling
          Tao Shen, Tianyi Zhou, Guodong Long, and 3 more authors
          In International Joint Conferences on Artificial Intelligence (IJCAI), Stockholm, Sweden, 2018
        11. TPAMI
          False Correlation Reduction for Offline Reinforcement Learning
          Zhihong Deng, Zuyue Fu, Lingxiao Wang, and 5 more authors
          IEEE Transactions on Pattern Analysis and Machine Intelligence, 2023

        Learning Paradigms

        Curriculum Learning & Data Selection
        1. Efficient Reinforcement Finetuning via Adaptive Curriculum Learning
          Taiwei Shi, Yiyang Wu, Linxin Song, and 2 more authors
          arXiv preprint arXiv:2504.05520, 2025
        2. Curriculum Reinforcement Learning via Morphology-Environment Co-Evolution
          Shuang Ao, Tianyi Zhou, Guodong Long, and 2 more authors
          arXiv preprint arXiv:2309.12529, 2023
        3. Diffusion Curriculum: Synthetic-to-Real Generative Curriculum Learning via Image-Guided Diffusion
          Yijun Liang, Shweta Bhardwaj, and Tianyi Zhou
          arXiv preprint arXiv:2410.13674, 2024
        1. Diffusion Curriculum: Synthetic-to-Real Generative Curriculum Learning via Image-Guided Diffusion
          Yijun Liang, Shweta Bhardwaj, and Tianyi Zhou
          In International Conference on Computer Vision (ICCV), 2025
        2. AAMAS
          Automatic Curriculum for Unsupervised Reinforcement Learning
          Yucheng Yang, Tianyi Zhou, Lei Han, and 2 more authors
          In International Conference on Autonomous Agents and Multiagent Systems (AAMAS), 2024
        3. When to Learn What: Model-Adaptive Data Augmentation Curriculum
          Chengkai Hou, Jieyu Zhang, and Tianyi Zhou
          In International Conference on Computer Vision (ICCV), 2023
        4. EAT-C: Environment-Adversarial sub-Task Curriculum for Efficient Reinforcement Learning
          Shuang Ao, Tianyi Zhou, Jing Jiang, and 3 more authors
          In International Conference on Machine Learning (ICML), 2022
        5. CO-PILOT: COllaborative Planning and reInforcement Learning On sub-Task curriculum
          Shuang Ao, Tianyi Zhou, Guodong Long, and 3 more authors
          In Advances in Neural Information Processing Systems 35 (NeurIPS), 2021
        6. Curriculum Learning by Optimizing Learning Dynamics
          Tianyi Zhou, Shengjie Wang, and Jeff A. Bilmes
          In International Conference on Artificial Intelligence and Statistics (AISTATS), 2021
        7. Robust Curriculum Learning: from clean label detection to noisy label self-correction
          Tianyi Zhou, Shengjie Wang, and Jeff A. Bilmes
          In International Conference on Learning Representations (ICLR), 2021
        8. AutoLRS: Automatic Learning-Rate Schedule by Bayesian Optimization on the Fly
          Yuchen Jin, Tianyi Zhou, Liangyu Zhao, and 4 more authors
          In International Conference on Learning Representations (ICLR), 2021
        9. Curriculum Learning with Dynamic Instance Hardness
          Tianyi Zhou, Shengjie Wang, and Jeff A. Bilmes
          In Advances in Neural Information Processing Systems 34 (NeurIPS), 2020
        10. Time-Consistent Self-Supervision for Semi-Supervised Learning
          Tianyi Zhou, Shengjie Wang, and Jeff A. Bilmes
          In International Conference on Machine Learning (ICML), 2020
        11. Curriculum-guided Hindsight Experience Replay
          Meng Fang, Tianyi Zhou, Yali Du, and 2 more authors
          In Advances in Neural Information Processing Systems 33 (NeurIPS), Vancouver, BC, Canada, 2019
        12. Diverse Ensemble Evolution: Curriculum Data-Model Marriage
          Tianyi Zhou, Shengjie Wang, and Jeff A. Bilmes
          In Advances in Neural Information Processing Systems 32 (NeurIPS), Montreal, QC, Canada, 2018
        13. Minimax Curriculum Learning: Machine Teaching with Desirable Difficulties and Scheduled Diversity
          Tianyi Zhou and Jeff A. Bilmes
          In Sixth International Conference on Learning Representations (ICLR), Vancouver, BC, Canada, 2018
        14. Divide-and-Conquer Learning by Anchoring a Conical Hull
          Tianyi Zhou, Jeff A. Bilmes, and Carlos Guestrin
          In Twenty-Eighth Annual Conference on Neural Information Processing Systems (NeurIPS), Montreal, Canada, 2014
        15. ICDM
          Divide-and-Conquer Anchoring for Near Separable Nonnegative Matrix Factorization and Completion in High DimensionsBest Student Paper
          Tianyi Zhou, Wei Bian, and Dacheng Tao
          In IEEE International Conference on Data Mining (ICDM), pp., Dallas, TX, USA, 2013
        16. Efficient Reinforcement Finetuning via Adaptive Curriculum Learning
          Taiwei Shi, Yiyang Wu, Linxin Song, and 2 more authors
          Transactions on Machine Learning Research (TMLR), 2026
        17. TPAMI
          Time-Consistency Curriculum for Learning from Instance-Dependent Noisy Labels
          Songhua Wu, Tianyi Zhou, Yuxuan Du, and 3 more authors
          IEEE Transactions on Pattern Analysis and Machine Intelligence, 2024
        18. TNNLS
          Data Subset Selection with Imperfect Multiple Labels
          Meng Fang, Tianyi Zhou, Jie Yin, and 2 more authors
          IEEE Transactions on Neural Networks and Learning Systems, 2018
        Data Augmentation & Synthesis
        1. AutoBench-V: Can Large Vision-Language Models Benchmark Themselves?
          Han Bao, Yue Huang, Yanbo Wang, and 7 more authors
          arXiv preprint arXiv:2410.21259, 2024
        2. Diffusion Curriculum: Synthetic-to-Real Generative Curriculum Learning via Image-Guided Diffusion
          Yijun Liang, Shweta Bhardwaj, and Tianyi Zhou
          arXiv preprint arXiv:2410.13674, 2024
        3. AerialBooth: Mutual Information Guidance for Text Controlled Aerial View Synthesis from a Single Image
          Divya Kothandaraman, Tianyi Zhou, Ming Lin, and 1 more author
          arXiv preprint arXiv:2311.15478, 2023
        1. Diffusion Curriculum: Synthetic-to-Real Generative Curriculum Learning via Image-Guided Diffusion
          Yijun Liang, Shweta Bhardwaj, and Tianyi Zhou
          In International Conference on Computer Vision (ICCV), 2025
        2. AUTOHALLUSION: Automatic Generation of Hallucination Benchmarks for Vision-Language Models
          Xiyang Wu, Tianrui Guan, Dianqi Li, and 9 more authors
          In The 2024 Conference on Empirical Methods in Natural Language Processing (EMNLP) Findings, 2024
        3. SIGGRAPH Asia
          repo-divyakraman_aerialdiffusion.png
          Aerial Diffusion: Text Guided Ground-to-Aerial View Translation from a Single Image using Diffusion Models
          Divya Kothandaraman, Tianyi Zhou, Ming C. Lin, and 1 more author
          In The 16th ACM SIGGRAPH Conference and Exhibition on Computer Graphics and Interactive Techniques in Asia Pacific (SIGGRAPH Asia), 2023
        4. When to Learn What: Model-Adaptive Data Augmentation Curriculum
          Chengkai Hou, Jieyu Zhang, and Tianyi Zhou
          In International Conference on Computer Vision (ICCV), 2023
        5. Subclass-balancing Contrastive Learning for Long-tailed Recognition
          Chengkai Hou, Jieyu Zhang, Haonan Wang, and 1 more author
          In International Conference on Computer Vision (ICCV), 2023
        6. Retrospective Adversarial Replay for Continual Learning
          Lilly Kumari, Shengjie Wang, Tianyi Zhou, and 1 more author
          In Advances in Neural Information Processing Systems 36 (NeurIPS), 2022
        7. Adversarial Auto-Augment with Label Preservation: A Representation Learning Principle Guided Approach
          Kaiwen Yang, Yanchao Sun, Jiahao Su, and 5 more authors
          In Advances in Neural Information Processing Systems 36 (NeurIPS), 2022
        8. Identity-Disentangled Adversarial Augmentation for Self-supervised Learning
          Kaiwen Yang, Tianyi Zhou, Xinmei Tian, and 1 more author
          In International Conference on Machine Learning (ICML), 2022
        Continual Learning
        1. Hybrid Memory Replay: Blending Real and Distilled Data for Class Incremental Learning
          Jiangtao Kong, Jiacheng Shi, Ashley Gao, and 3 more authors
          arXiv preprint arXiv:2410.15372, 2024
        2. Condensed Prototype Replay for Class Incremental Learning
          Jiangtao Kong, Zhenyu Zong, Tianyi Zhou, and 1 more author
          arXiv preprint arXiv:2305.16143, 2023
        1. ECA: Efficient Continual Alignment for Open-Ended Image-to-Text Generation
          Jiangtao Kong, Peijun Zhao, Chun-Fu Chen, and 4 more authors
          In Forty-third International Conference on Machine Learning (ICML), 2026
        2. Continual Task Allocation in Meta-Policy Network via Sparse Prompting
          Yijun Yang, Tianyi Zhou, Jing Jiang, and 2 more authors
          In International Conference on Machine Learning (ICML), 2023
        3. Does Continual Learning Equally Forget All Parameters?
          Haiyan Zhao, Tianyi Zhou, Guodong Long, and 2 more authors
          In International Conference on Machine Learning (ICML), 2023
        4. Retrospective Adversarial Replay for Continual Learning
          Lilly Kumari, Shengjie Wang, Tianyi Zhou, and 1 more author
          In Advances in Neural Information Processing Systems 36 (NeurIPS), 2022
        5. YoooP: You Only Optimize One Prototype per Class for Non-Exemplar Incremental Learning
          Jiangtao Kong, Zhenyu Zong, Tianyi Zhou, and 1 more author
          Transactions on Machine Learning Research, 2025
        Transfer, Multi-task & Meta-learning
          1. Many-Objective Multi-Solution Transport
            Ziyue Li, Tian Li, Virginia Smith, and 2 more authors
            In The Thirteenth International Conference on Learning Representations (ICLR), 2025
          2. ECML-PKDD
            arxiv-2301.11560.png
            Voting from Nearest Tasks: Meta-Vote Pruning of Pre-trained Models for Downstream Tasks
            Haiyan Zhao, Tianyi Zhou, Guodong Long, and 2 more authors
            In European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML/PKDD), 2023
          3. Isometric Propagation Network for Generalized Zero-shot Learning
            Lu Liu, Tianyi Zhou, Guodong Long, and 3 more authors
            In International Conference on Learning Representations (ICLR), 2021
          4. Attribute Propagation Network for Graph Zero-shot Learning
            Lu Liu, Tianyi Zhou, Guodong Long, and 2 more authors
            In The Thirty-Fourth AAAI Conference on Artificial Intelligence (AAAI), New York, USA, 2020
          5. Learning to Propagate for Graph Meta-Learning
            Lu Liu, Tianyi Zhou, Guodong Long, and 2 more authors
            In Advances in Neural Information Processing Systems 33 (NeurIPS), Vancouver, BC, Canada, 2019
          6. Prototype Propagation Networks (PPN) for Weakly-supervised Few-shot Learning on Category Graph
            Lu Liu, Tianyi Zhou, Guodong Long, and 3 more authors
            In International Joint Conferences on Artificial Intelligence (IJCAI), Macau, China, 2019
          7. KDD
            Multi-task Copula by Sparse Graph Regression
            Tianyi Zhou and Dacheng Tao
            In ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), NYC, USA, 2014
          8. TKDE
            Many-Class Few-Shot Learning on Multi-Granularity Class Hierarchy
            Lu Liu, Tianyi Zhou, Guodong Long, and 2 more authors
            IEEE Transactions on Knowledge and Data Engineering, 2020
          Federated & Collaborative Learning
          1. Federated Adapter on Foundation Models: An Out-Of-Distribution Approach
            Yiyuan Yang, Guodong Long, Tianyi Zhou, and 3 more authors
            arXiv preprint arXiv:2505.01075, 2025
          1. Personalized Additive Modeling for Multi-level Federated Learning
            Shutong Chen, Tianyi Zhou, Guodong Long, and 3 more authors
            In Forty-third International Conference on Machine Learning (ICML), 2026
          2. FedMerge: Federated Personalization via Model Merging
            Shutong Chen, Tianyi Zhou, Guodong Long, and 2 more authors
            In The 40th Annual AAAI Conference on Artificial Intelligence (AAAI), 2026
          3. Many-Objective Multi-Solution Transport
            Ziyue Li, Tian Li, Virginia Smith, and 2 more authors
            In The Thirteenth International Conference on Learning Representations (ICLR), 2025
          4. Personalized Federated Collaborative Filtering: A Variational AutoEncoder Approach
            Zhiwei Li, Guodong Long, Tianyi Zhou, and 2 more authors
            In The 39th Annual AAAI Conference on Artificial Intelligence (AAAI), 2025
          5. KDD
            arxiv-2305.07866.png
            GPFedRec: Graph-Guided Personalization for Federated Recommendation
            Chunxu Zhang, Guodong Long, Tianyi Zhou, and 3 more authors
            In 30th SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), 2024
          6. WWW
            arxiv-2305.12650.png
            When Federated Recommendation Meets Cold-Start Problem: Separating Item Attributes and User Interactions
            Chunxu Zhang, Guodong Long, Tianyi Zhou, and 3 more authors
            In The Web Conference (WWW), 2024
          7. Federated Recommendation with Additive Personalization
            Zhiwei Li, Guodong Long, and Tianyi Zhou
            In International Conference on Learning Representations (ICLR), 2024
          8. Structured Federated Learning through Clustered Additive Modeling
            Jie Ma, Tianyi Zhou, Guodong Long, and 2 more authors
            In Advances in Neural Information Processing Systems 37 (NeurIPS), 2023
          9. Structured Cooperative Learning with Graphical Model Priors
            Shuangtong Li, Tianyi Zhou, Xinmei Tian, and 1 more author
            In International Conference on Machine Learning (ICML), 2023
          10. Dual Personalization on Federated Recommendation
            Chunxu Zhang, Guodong Long, Tianyi Zhou, and 4 more authors
            In International Joint Conference on Artificial Intelligence (IJCAI), 2023
          11. Federated Learning from Pre-Trained Models: A Contrastive Learning Approach
            Yue Tan, Guodong Long, Jie Ma, and 3 more authors
            In Advances in Neural Information Processing Systems 36 (NeurIPS), 2022
          12. Personalized Federated Learning With Structural InformationOral
            Fengwen Chen, Guodong Long, Zonghan Wu, and 2 more authors
            In International Joint Conference on Artificial Intelligence (IJCAI), 2022
          13. Learning to Collaborate in Decentralized Learning of Personalized Models
            Shuangtong Li, Tianyi Zhou, Xinmei Tian, and 1 more author
            In IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022
          14. Diverse Client Selection for Federated Learning via Submodular Maximization
            Ravikumar Balakrishnan, Tian Li, Tianyi Zhou, and 3 more authors
            In International Conference on Learning Representations (ICLR), 2022
          15. FedProto: Federated Prototype Learning across Heterogeneous Clients
            Yue Tan, Guodong Long, Lu Liu, and 4 more authors
            In The Thirty-Sixth AAAI Conference on Artificial Intelligence (AAAI), 2022
          16. WWWJ
            Multi-Center Federated Learning
            Guodong Long, Ming Xie, Tao Shen, and 3 more authors
            World Wide Web, 2022

          Foundations & Earlier Work

          Attention & NLP (pre-LLM)
          1. Conditional Self-Attention for Query-based Summarization
            Yujia Xie, Tianyi Zhou, Yi Mao, and 1 more author
            arXiv preprint arXiv:2002.07338, 2020
          1. Merging Experts into One: Improving Computational Efficiency of Mixture of Experts
            Shwai He, Run-Ze Fan, Liang Ding, and 3 more authors
            In The 2023 Conference on Empirical Methods in Natural Language Processing (EMNLP), 2023
          2. TASA: Deceiving Question Answering Models by Twin Answer Sentences Attack
            Yu Cao, Dianqi Li, Meng Fang, and 4 more authors
            In The 2022 Conference on Empirical Methods in Natural Language Processing (EMNLP), 2022
          3. Phrase-level Textual Adversarial Attack with Label Preservation
            Yibin Lei, Yu Cao, Dianqi Li, and 3 more authors
            In Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL Findings), 2022
          4. ACL
            Token Dropping for Efficient BERT Pretraining
            Le Hou, Richard Yuanzhe Pang, Tianyi Zhou, and 4 more authors
            In Annual Meeting of the Association for Computational Linguistics (ACL), 2022
          5. Omni-Scale CNNs: a simple and effective kernel size configuration for time series classification
            Wensi Tang, Guodong Long, Lu Liu, and 3 more authors
            In International Conference on Learning Representations (ICLR), 2022
          6. Eliminating Sentiment Bias for Aspect-Level Sentiment Classification with Unsupervised Opinion Extraction
            Bo Wang, Tao Shen, Guodong Long, and 2 more authors
            In The 2021 Conference on Empirical Methods in Natural Language Processing (EMNLP) Findings, 2021
          7. WWW
            arxiv-2004.14781.png
            Structure-Augmented Text Representation Learning for Efficient Knowledge Graph Completion
            Bo Wang, Tao Shen, Guodong Long, and 2 more authors
            In The WEB Conference (WWW), 2021
          8. COLING
            Improving Long-Tail Relation Extraction with Collaborating Relation-Augmented Attention
            Yang Li, Tao Shen, Guodong Long, and 3 more authors
            In The 28th International Conference on Computational Linguistics (COLING), 2020
          9. Self-Attention Enhanced Selective Gate with Entity-Aware Embedding for Distantly Supervised Relation Extraction
            Yang Li, Guodong Long, Tao Shen, and 4 more authors
            In The Thirty-Fourth AAAI Conference on Artificial Intelligence (AAAI), New York, USA, 2020
          10. Tensorized Self-Attention: Efficiently Modeling Pairwise and Global Dependencies Together
            Tao Shen, Tianyi Zhou, Guodong Long, and 2 more authors
            In Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL), 2019
          11. Reinforced Self-Attention Network: a Hybrid of Hard and Soft Attention for Sequence Modeling
            Tao Shen, Tianyi Zhou, Guodong Long, and 3 more authors
            In International Joint Conferences on Artificial Intelligence (IJCAI), Stockholm, Sweden, 2018
          12. DiSAN: Directional self-attention network for rnn/cnn-free language understanding
            Tao Shen, Tianyi Zhou, Guodong Long, and 3 more authors
            In The Thirty-Second AAAI Conference on Artificial Intelligence (AAAI), New Orleans, Louisiana, USA, 2018
          13. Bi-Directional Block Self-Attention for Fast and Memory-Efficient Sequence Modeling
            Tao Shen, Tianyi Zhou, Guodong Long, and 2 more authors
            In Sixth International Conference on Learning Representations (ICLR), Vancouver, BC, Canada, 2018
          14. TIP
            Efficient Robust Conditional Random Fields
            Dongjin Song, Wei Liu, Tianyi Zhou, and 2 more authors
            IEEE Transactions on Image Processing, 2015
          Matrix Factorization & Disentanglement
            1. Adversarial Auto-Augment with Label Preservation: A Representation Learning Principle Guided Approach
              Kaiwen Yang, Yanchao Sun, Jiahao Su, and 5 more authors
              In Advances in Neural Information Processing Systems 36 (NeurIPS), 2022
            2. Identity-Disentangled Adversarial Augmentation for Self-supervised Learning
              Kaiwen Yang, Tianyi Zhou, Xinmei Tian, and 1 more author
              In International Conference on Machine Learning (ICML), 2022
            3. Class-Disentanglement and Applications in Adversarial Detection and Defense
              Kaiwen Yang, Tianyi Zhou, Yonggang Zhang, and 2 more authors
              In Advances in Neural Information Processing Systems 35 (NeurIPS), 2021
            4. ICDM
              Divide-and-Conquer Anchoring for Near Separable Nonnegative Matrix Factorization and Completion in High DimensionsBest Student Paper
              Tianyi Zhou, Wei Bian, and Dacheng Tao
              In IEEE International Conference on Data Mining (ICDM), pp., Dallas, TX, USA, 2013
            5. Shifted Subspaces Tracking on Sparse Outlier for Motion Segmentation
              Tianyi Zhou and Dacheng Tao
              In International Joint Conferences on Artificial Intelligence (IJCAI), Beijing, China, 2013
            6. Greedy Bilateral Sketch, Completion & Smoothing
              Tianyi Zhou and Dacheng Tao
              In International Conference on Artificial Intelligence and Statistics (AISTATS), Journal of Machine Learning Research - Proceedings Track, Scottsdale, Arizona, USA, 2013
            7. Multi-label Subspace Ensemble
              Tianyi Zhou and Dacheng Tao
              In International Conference on Artificial Intelligence and Statistics (AISTATS), Journal of Machine Learning Research - Proceedings Track 22: 1444-1452, La Palma, Canary Islands, Spain, 2012
            8. ISIT
              Bilateral Random Projections
              Tianyi Zhou and Dacheng Tao
              In IEEE International Symposium on Information Theory (ISIT), MIT, Boston, USA, 2012
            9. ICMR
              Labelset Anchored Subspace Ensemble (LASE) for Multi-label Annotation
              Tianyi Zhou and Dacheng Tao
              In ACM International Conference on Multimedia Retrieval (ICMR), Hong Kong, China, 2012
            10. GoDec: Randomized Low-rank & Sparse Matrix Decomposition in Noisy Case
              Tianyi Zhou and Dacheng Tao
              In Twenty-Eighth International Conference on Machine Learning (ICML), Bellevue, WA, USA, 2011
            Compressed Sensing & Sparse Learning
            1. Hamming Compressed Sensing
              Tianyi Zhou and Dacheng Tao
              arXiv preprint arXiv:1110.0073, 2011
            1. ISIT
              k-bit Hamming Compressed Sensing
              Tianyi Zhou and Dacheng Tao
              In IEEE International Symposium on Information Theory (ISIT), Istanbul, Turkey, 2013
            2. ISIT
              1-bit Hamming Compressed Sensing
              Tianyi Zhou and Dacheng Tao
              In IEEE International Symposium on Information Theory (ISIT), MIT, Boston, USA, 2012
            3. ICONIP
              Backward-Forward Least Angle Shrinkage for Sparse Quadratic Optimization
              Tianyi Zhou and Dacheng Tao
              In International Conference on Neural Information Processing (ICONIP), pp. 388-396, Sydney, Australia, 2010
            4. SMC
              Manifold elastic net for sparse learning
              Tianyi Zhou and Dacheng Tao
              In IEEE International conference on Systems, Man and Cybernetics (SMC), pp. 3699-3704, San Antonio, Texas, USA, 2009
            5. TNNLS
              Minimizing Nearest Neighbor Classification Error for Nonparametric Dimension Reduction
              Wei Bian, Tianyi Zhou, Aleix M. Martinez, and 2 more authors
              IEEE Transactions on Neural Networks and Learning Systems, 2014
            6. TIP
              Double Shrinking for Sparse Learning
              Tianyi Zhou and Dacheng Tao
              IEEE Transactions on Image Processing, 2013
            7. MLJ
              Compressed Labeling on Distilled Labelsets for Multi-label Learning
              Tianyi Zhou, Dacheng Tao, and Xindong Wu
              Machine Learning, 2012
            8. DMKD
              Manifold Elastic Net: A Unified Framework for Sparse Dimension Reduction
              Tianyi Zhou, Dacheng Tao, and Xindong Wu
              Data Mining and Knowledge Discovery, 2011
            Optimization
            1. Stream Clipper: Scalable Submodular Maximization on Stream
              Tianyi Zhou and Jeff A. Bilmes
              arXiv preprint arXiv:1606.00389, 2016
            1. Reweighting Local Mimina with Tilted SAM
              Tian Li, Tianyi Zhou, and Jeffrey A Bilmes
              In Forty-Second International Conference on Machine Learning (ICML), 2025
            2. Constrained Robust Submodular PartitioningSpotlight
              Shengjie Wang, Tianyi Zhou, Chandrashekhar Lavania, and 1 more author
              In Advances in Neural Information Processing Systems 35 (NeurIPS), 2021
            3. Jumpout: Improved Dropout for Deep Neural Networks with Rectified Linear Units
              Tianyi Zhou, Shengjie Wang, and Jeff A. Bilmes
              In International Conference on Machine Learning (ICML), Long Beach, CA, 2019
            4. Scaling Submodular Maximization via Pruned Submodularity Graphs
              Tianyi Zhou, Hua Ouyang, Jeff A. Bilmes, and 2 more authors
              In Twentyth International Conference on Artificial Intelligence and Statistics (AISTATS), Fort Lauderdale, FL, 2017
            5. KDD
              Constrained Stochastic Gradient Descent for Large-scale Least Squares Problem
              Yang Mu, Wei Ding, Tianyi Zhou, and 1 more author
              In ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), Chicago, Illinois, USA, 2013
            6. ICDM
              NESVM: a Fast Gradient Method for Support Vector Machines
              Tianyi Zhou, Dacheng Tao, and Xindong Wu
              In IEEE International Conference on Data Mining (ICDM), pp. 679-688, Sydney, Australia, 2010