Wei Du

25 papers · 2022–2026 · 9 conferences · across top CS/AI conferences

Achievements

+7 more ↓

🐝 Cross-Pollinator (13) 🌉 Interdisciplinary Bridge 🧭 Keyword Pioneer 🌍 Conference Polyglot (9) 🌈 Renaissance Researcher (9)

🌍 Conference Polyglot (9) 🏆 Keyword Champion (2) 🗃️ Keyword Collector (110) ⚡ Prolific Year (7) 💎 Century Club (21) 🔥 Unstoppable (5) ❓ The Questioner

Conferences

AAAI (10) ACL (3) IJCAI (3) COLING (2) EMNLP (2) ICLR (2) ICCV (1) INTERSPEECH (1) NAACL (1)

Top co-authors

Gongshen Liu (8) Haodong Zhao (4) Tianjie Ju (4) Guoxian Yu (3) Shifei Ding (3) Fangqi Li (2) Ling Ding (2) Gaoyang Li (2) Peixuan Li (2) You Zhou (2)

Research topics

Privacy (2)

Keywords

contrastive learning (5) large language model (4) backdoor attack (4) pre-trained language model (3) graph neural network (3) adversarial learning (3) few-shot learning (2) communication learning (2) text generation (2) ownership verification (2) multi-agent reinforcement learning (2) adversarial robustness (2) multi-view clustering (2) trigger word (2) transfer learning (2) knowledge distillation (2) adversarial attack (2) data poisoning (1) image classification (1) multi-task learning (1)

Papers

Learning Whom to Align With: Progressive Anomaly Combination Detection for Partially View-Aligned Clustering AAAI 2026 CompTab: A Comprehensive Benchmark for Real-World TableQA with Complex Reasoning and Irregular Tables ACL 2026 Efficient Few-Step Solution Generation via Discrete Flow Matching for Combinatorial Optimization AAAI 2026 MLLM Enriched Explainable Multiple Clustering AAAI 2026 DVAGen: Dynamic Vocabulary Augmented Generation EMNLP 2025 Contrastive Auxiliary Learning with Structure Transformation for Heterogeneous Graphs AAAI 2025 OpenMathInstruct-2: Accelerating AI for Math with Massive Open-Source Instruction Data ICLR 2025 Triples as the Key: Structuring Makes Decomposition and Verification Easier in LLM-based TableQA ICLR 2025 Multi-Agent Communication with Information Preserving Graph Contrastive Learning IJCAI 2025 Imputation-free Incomplete Multi-view Clustering via Knowledge Distillation IJCAI 2025 SynGhost: Invisible and Universal Task-agnostic Backdoor Attack via Syntactic Transfer NAACL 2025 Expressive Multi-Agent Communication via Identity-Aware Learning AAAI 2024 Revisiting the Information Capacity of Neural Network Watermarks: Upper Bound Estimation and Beyond AAAI 2024 Backdoor NLP Models via AI-Generated Text COLING 2024 Investigating Multi-Hop Factual Shortcuts in Knowledge Editing of Large Language Models ACL 2024 UOR: Universal Backdoor Attacks on Pre-trained Language Models ACL 2024 How Large Language Models Encode Context Knowledge? A Layer-Wise Probing Study COLING 2024 Learning Efficient and Robust Multi-Agent Communication via Graph Information Bottleneck AAAI 2024 Compressing Cross-Lingual Multi-Task Models at Qualtrics AAAI 2023 Feature Distribution Fitting with Direction-Driven Weighting for Few-Shot Images Classification AAAI 2023 3DHacker: Spectrum-based Decision Boundary Generation for Hard-label 3D Point Cloud Attack ICCV 2023 PLMmark: A Secure and Robust Black-Box Watermarking Framework for Pre-trained Language Models AAAI 2023 Effective Proxy for Human Labeling: Ensemble Disagreement Scores in Large Language Models for Industrial NLP EMNLP 2023 A Universal Identity Backdoor Attack against Speaker Verification based on Siamese Network INTERSPEECH 2022 PPT: Backdoor Attacks on Pre-trained Models via Poisoned Prompt Tuning IJCAI 2022