Hua Wei

33 papers · 2019–2026 · 8 conferences · across top CS/AI conferences

Achievements

+11 more ↓

🐣 Hot Topic Early Bird 🧭 Keyword Pioneer 🌈 Renaissance Researcher (5) 🌉 Interdisciplinary Bridge 🌍 Conference Polyglot (7)

🧭 Keyword Pioneer 🐣 Hot Topic Early Bird 🏃 Academic Marathon (6) 👑 Triple Crown 🏆 Grand Slam 🏆 Keyword Champion (5) 🔥 Unstoppable (7) 🚀 Conference Pioneer ⚡ Prolific Year (9) 🗃️ Keyword Collector (148) 💎 Century Club (26)

Conferences

AAAI (12) IJCAI (6) ACL (5) EACL (3) ICML (3) NIPS (2) CVPR (1) ICLR (1)

Top co-authors

Longchao Da (7) Tiejin Chen (6) Zhenhui Li (5) Jiaxing Zhang (4) Porter Jenkins (4) Zhuomin Chen (3) Dongsheng Luo (3) Guanjie Zheng (3) Hao Mei (3) Kaixiong Zhou (2)

Keywords

traffic signal control (5) uncertainty quantification (4) multi-agent system (4) reinforcement learning (3) deep learning (3) large language model (3) evidential regression (2) neural network (2) multi-modal large language model (2) residual learning (2) multi-agent reinforcement learning (2) policy optimization (2) game ai (2) autonomous driving (2) offline reinforcement learning (2) trajectory prediction (2) graph neural network (2) variational inference (1) sim-to-real transfer (1) policy evaluation (1)

Papers

Conformal Feedback Alignment: Quantifying Answer-Level Reliability for Robust LLM Alignment EACL 2026 Instructional Agents: Reducing Teaching Faculty Workload through Multi-Agent Instructional Design EACL 2026 Lost in Execution: On the Multilingual Robustness of Tool Calling in Large Language Models ACL 2026 A Multi-Agent Framework for High-Interaction Terminal Simulation ACL 2026 Every Response Counts: Quantifying Uncertainty of LLM-based Multi-Agent Systems through Tensor Decomposition ACL 2026 Measuring What Matters: Scenario-Driven Evaluation for Trajectory Predictors in Autonomous Driving AAAI 2026 Zer0-Jack: A memory-efficient gradient-based jailbreaking method for black box Multi-modal Large Language Models EACL 2026 Fully Heteroscedastic Count Regression with Deep Double Poisson Networks ICML 2025 Unveiling Privacy Risks in Multi-modal Large Language Models: Task-specific Vulnerabilities and Mitigation Challenges ACL 2025 GE-Chat: A Graph Enhanced RAG Framework for Evidential Response Generation of LLMs IJCAI 2025 RISE: Radius of Influence based Subgraph Extraction for 3D Molecular Graph Explanation ICML 2025 Vision Language Model Helps Private Information De-Identification in Vision Data ACL 2025 DeepShade: Enable Shade Simulation by Text-conditioned Image Generation IJCAI 2025 Towards Robust Fidelity for Evaluating Explainability of Graph Neural Networks ICLR 2024 RegExplainer: Generating Explanations for Graph Neural Networks in Regression Tasks NIPS 2024 Prompt to Transfer: Sim-to-Real Transfer for Traffic Signal Control with Prompt Learning AAAI 2024 Uncertainty Regularized Evidential Regression AAAI 2024 Probabilistic Offline Policy Ranking with Approximate Bayesian Computation AAAI 2024 The Evidence Contraction Issue in Deep Evidential Regression: Discussion and Solution AAAI 2024 eTraM: Event-based Traffic Monitoring Dataset CVPR 2024 Generating In-Distribution Proxy Graphs for Explaining Graph Neural Networks ICML 2024 X-Light: Cross-City Traffic Signal Control Using Transformer on Transformer as Meta Multi-Agent Reinforcement Learner IJCAI 2024 Reinforcement Learning Approaches for Traffic Signal Control under Missing Data IJCAI 2023 SafeLight: A Reinforcement Learning Method toward Collision-Free Traffic Signal Control AAAI 2023 Positive Distribution Pollution: Rethinking Positive Unlabeled Learning from a Unified Perspective AAAI 2023 Honor of Kings Arena: an Environment for Generalization in Competitive Reinforcement Learning NIPS 2022 Bayesian Model-Based Offline Reinforcement Learning for Product Allocation AAAI 2022 Transformer-Style Relational Reasoning with Dynamic Memory Updating for Temporal Network Modeling AAAI 2021 How Do We Move: Modeling Human Movement with System Dynamics AAAI 2021 Knowledge-based Residual Learning IJCAI 2021 Boosting Offline Reinforcement Learning with Residual Generative Modeling IJCAI 2021 Toward A Thousand Lights: Decentralized Deep Reinforcement Learning for Large-Scale Traffic Signal Control AAAI 2020 Revisiting Spatial-Temporal Similarity: A Deep Learning Framework for Traffic Prediction AAAI 2019