Demo + Code and Datasets Download (Please cite my related publications)

• A Survey of Machine Unlearning. [Code] [Cite] (950+ stars, 55K+ accesses)

Our work has been cited in the International AI Safety Report 2025 (chaired by Turing-award winner Yoshua Bengio and written by top 100 AI experts) in which machine unlearning is a pioneering paradigm to remove sensitive information or harmful data from trained AI models.

• Privacy-Preserving Explainable AI: A Survey. [Code] [Cite1] [Cite2]

• LLM-empowered Image Editing. [Code] [Cite]

• Social Network Simulation. [Code]

• Mamba for Time Series. [Code]

• MultiSpider 2.0: Benchmarking the Limits of Language Models with Collaborative Language Agents. [Code] [Cite1] [Cite2]

• AV-SQL: AV-SQL: Decomposing Complex Text-to-SQL Queries with Agentic Views. [Code] [Cite]

• FusionSQL: An Efficient and Effective Evaluator for Text2SQL Models on Unseen and Unlabeled Data. [Code] [Cite1]

• FINER-SQL: Boosting Small Language Models for Text-to-SQL with Fine-Grained Execution Feedback and Cost-Efficient Rewards. [Code] [Cite]

• GRAST-SQL: Scaling Text-to-SQL via LLM-efficient Schema Filtering with Functional Dependency Graph Rerankers. [Code] [Cite]

• VALASQL: An Extensible Benchmark for Value Ambiguity Resolution in Text-to-SQL. [Code] [Cite]

• MATS-SQL: A Multi-agent Text2SQL Framework using Small Language Models and Execution Feedback [Code] [Cite]

• Fast-FedUL: A Training-Free Federated Unlearning with Provable Skew Resilience. [Code] [Cite]

• Higher-order knowledge-enhanced recommendation with heterogeneous hypergraph multi-attention. [Code] [Cite]

• On-Device Diagnostic Recommendation with Heterogeneous Federated BlockNets. [Code] [Cite]

• Towards Self-Adaptive LLM-based News Verification with Real-time Evidence [Demo]

• Manipulating Recommender Systems: A Survey of Poisoning Attacks and Countermeasures. [Code] [Cite]

• A Comprehensive Survey on Heart Sound Analysis in the Deep Learning Era. [Code] [Cite]

• Crowdsourcing benchmark. [Code] [Cite1] [Cite2]

• A comparative study of question answering over knowledge bases. [Code] [Cite]

• Entity Alignment for Knowledge Graphs with Multi-order Convolutional Networks. [Code] [Cite]

• A dual benchmarking study of facial forgery and facial forensics. [Code] [Cite]

• FactCatch: Incremental Pay-as-You-Go Fact Checking with Minimal User Effort. [Code] [Cite]

• Prototype Learning for Interpretable Respiratory Sound Analysis. [Code] [Cite]

• Example-based Explanations with Adversarial Attacks for Respiratory Sound Analysis. [Code] [Cite]

• Fast Yet Effective Speech Emotion Recognition with Self-distillation. [Code] [Cite]

• Knowledge Transfer For On-Device Speech Emotion Recognition with Neural Structured Learning. [Code] [Cite]

• Network Alignment with Holistic Embeddings. [Code] [Cite]

• Efficient Integration of Multi-Order Dynamics and Internal Dynamics in Stock Movement Prediction. [Code] [Cite]

• Graph representation learning benchmark. [Code]

• Lightweight Branching Self-Distillation: Be Your Own Teacher. [Code] [Cite]

• Traffic Speed Prediction. [Code] [Cite2] (Best Paper Awards)