Authors with underline are my supervised students, and * indicates equal contribution. Full and up-to-date list is on Google Scholar.
Show:
Preprints
- DecisionRobust: Benchmarking Robustness for JEV Style Decision Models Across Text and Vision
arXiv preprint arXiv:2610.19118 (arXiv 2026) [Paper] - Critic Experience Bank: Self-Evolving Step-Level Confidence Estimation for LLM Agents
arXiv preprint arXiv:2607.12397 (arXiv 2026) [Paper] - SkillGrad: Optimizing Agent Skills Like Gradient Descent
arXiv preprint arXiv:2605.27760 (arXiv 2026) [Paper] [Code] - The Illusion of Reasoning: Exposing Evasive Data Contamination in LLMs via Zero-CoT Truncation
arXiv preprint arXiv:2605.21856 (arXiv 2026) [Paper] - ReLope: KL-Regularized LoRA Probes for Multimodal LLM Routing
arXiv preprint arXiv:2603.24787 (arXiv 2026) [Paper] - MemCollab: Cross-Model Memory Collaboration via Contrastive Trajectory Distillation
arXiv preprint arXiv:2603.23234 (arXiv 2026) [Paper] - PreFlect: From Retrospective to Prospective Reflection in Large Language Model Agents
arXiv preprint arXiv:2602.07187 (arXiv 2026) [Paper] - GuardDoor: Safeguarding Against Malicious Diffusion Editing via Protective Backdoors
arXiv preprint arXiv:2503.03944 (arXiv 2025) [Paper] - FairCode: Evaluating Social Bias of LLMs in Code Generation
arXiv preprint arXiv:2501.05396 (arXiv 2025) [Paper]
2026
- Forced Deferral: Manipulating Routing Decisions in Multimodal LLM Cascades
Proceedings of the 40th Annual Conference on Neural Information Processing Systems (NeurIPS 2026) [Paper] - ForecastCompass: Guiding Agentic Forecasting with Adaptive Factor Memory
Proceedings of the 40th Annual Conference on Neural Information Processing Systems (NeurIPS 2026) [Paper] - From Narrative to Auditable Forecasts: A Structured Scaffold for Agentic Forecasting
Findings of the 2026 Conference on Empirical Methods in Natural Language Processing (EMNLP Findings 2026) [Paper] - CARV: A Diagnostic Benchmark for Compositional Analogical Reasoning in Multimodal LLMs
Proceedings of the 3rd Conference on Language Modeling (COLM 2026) [Paper] - Exposing Vulnerabilities in Explanation for Time Series Classifiers via Dual-Target Attacks
Proceedings of the 43rd International Conference on Machine Learning (ICML 2026) [Paper] [Code]
2025
- Understanding and Rectifying Safety Perception Distortion in VLMs
Proceedings of the 39th Annual Conference on Neural Information Processing Systems (NeurIPS 2025) [Paper] - Phi: Preference Hijacking in Multi-modal Large Language Models at Inference Time
Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing (EMNLP 2025) [Paper] - JoPA: Explaining Large Language Model’s Generation via Joint Prompt Attribution
Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (ACL 2025) [Paper] [Code] - Monitoring Decoding: Mitigating Hallucination via Evaluating the Factuality of Partial Response during Generation
Findings of the 63rd Annual Meeting of the Association for Computational Linguistics (ACL Findings 2025) [Paper] [Code] - AdvI2I: Adversarial Image Attack on Image-to-Image Diffusion models
Proceedings of the 42nd International Conference on Machine Learning (ICML 2025) [Paper] [Code] - Boosting E-commerce Content Diversity: A Graph-based RAG Approach with User Reviews
Proceedings of the 31st SIGKDD Conference on Knowledge Discovery and Data Mining (KDD 2025) [Paper] - WordGame: Efficient & Effective LLM Jailbreak via Simultaneous Obfuscation in Query and Response
Findings of the 2025 Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL Findings 2025) [Paper] - FROG: Fair Removal on Graph
Proceedings of the 34th ACM International Conference on Information and Knowledge Management (CIKM 2025) [Paper]
2024
- Personalized Steering of Large Language Models: Versatile Steering Vectors Through Bi-directional Preference Optimization
Proceedings of the 38th Annual Conference on Neural Information Processing Systems (NeurIPS 2024) [Paper] [Code] - Defending Against Alignment-Breaking Attacks via Robustly Aligned LLM
Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) (ACL 2024) [Paper] [Code] - Jailbreak Open-Sourced Large Language Models via Enforced Decoding
Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) (ACL 2024) [Paper] [Code] - Graph Adversarial Diffusion Convolution
Proceedings of the 41st International Conference on Machine Learning (ICML 2024) [Paper] [Code] - Backdoor Contrastive Learning via Bi-level Trigger Optimization
Proceedings of of the 12th International Conference on Learning Representations (ICLR 2024) [Paper] [Code] - Globally Interpretable Graph Learning via Distribution Matching
Proceedings of the Web Conference (WWW 2024) [Paper] - Graph Contrastive Learning via Interventional View Generation
Proceedings of the Web Conference (WWW 2024) [Paper]
2023
- A3FL: Adversarially Adaptive Backdoor Attacks to Federated Learning
Proceedings of the 37th Conference on Neural Information Processing Systems (NeurIPS 2023) [Paper] [Code] - FusionRetro: Molecule Representation Fusion via In-Context Learning for Retrosynthetic Planning
Proceedings of the 40th International Conference on Machine Learning (ICML 2023) [Paper] [Code] - Graph Contrastive Backdoor Attacks
Proceedings of the 40th International Conference on Machine Learning (ICML 2023) [Paper] - Spectral augmentation for self-supervised learning on graphs
Proceedings of the 11th International Conference on Learning Representations (ICLR 2023) [Paper] [Code]
2022
- Graph Structural Attack by Perturbing Spectral Distance
Proceedings of the 28th ACM SIGKDD international conference on knowledge discovery & data mining (KDD 2022) [Paper] [Code] - Communication-Efficient Adaptive Federated Learning
Proceedings of the 39th International Conference on Machine Learning (ICML 2022) [Paper] - Communication-Compressed Adaptive Gradient Method for Distributed Nonconvex Optimization
Proceedings of the 25th International Conference on Artificial Intelligence and Statistics (AISTATS 2022) [Paper] - Communication-Compressed Adaptive Gradient Method for Distributed Nonconvex Optimization
International Workshop on Trustable, Verifiable and Auditable Federated Learning in Conjunction with AAAI (AAAI Workshop 2022) [Paper] - Unbiased Graph Embedding with Biased Graph Observations
Proceedings of the Web Conference (WWW 2022) [Paper] [Code] - Graph Embedding with Hierarchical Attentive Membership
Proceedings of the 15th International Conference on Web Search and Data Mining (WSDM 2022) [Paper]
2020
- Graph Attention Networks over Edge Content-based Channels
Proceedings of the 26th ACM SIGKDD international conference on knowledge discovery & data mining (KDD 2020) [Paper] [Code] - JNET: Learning User Representations via Joint Network Embedding and Topic Embedding
Proceedings of the 13th International Conference on Web Search and Data Mining (WSDM 2020) [Paper] [Code]
2019
- Sequential Learning with Active Partial Labeling for Building Metadata
Proceedings of the 6th ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation (BuildSys 2019) [Paper] [Code] - Learning Personalized Topical Compositions with Item Response Theory
Proceedings of the 12th ACM International Conference on Web Search and Data Mining (WSDM 2019) [Paper]
2017
- Road Traffic Speed Prediction: A Probabilistic Model Fusing Multi-source Data
IEEE Transactions on Knowledge and Data Engineering (TKDE 2017) [Paper]
2014
- Opinion Mining and Sentiment Analysis in Social Networks: A Retweeting Structure-aware Approach
Proceedings of 7th IEEE/ACM International Conference on Utility and Cloud Computing (UCC 2014) [Paper]