Mengdi Huai

26 papers · 2018–2026 · 8 conferences · across top CS/AI conferences

Achievements

+9 more ↓

🐝 Cross-Pollinator (13) 🐣 Hot Topic Early Bird 🏃 Academic Marathon (7) 🌍 Conference Polyglot (7) 🌈 Renaissance Researcher (9)

🏃 Academic Marathon (7) 🐣 Hot Topic Early Bird 🐝 Cross-Pollinator (13) 🏆 Keyword Champion (3) 🗃️ Keyword Collector (96) 🚀 Conference Pioneer 💎 Century Club (24) 🔥 Unstoppable (8) ⚡ Prolific Year (10)

Conferences

AAAI (13) ICML (4) IJCAI (3) NIPS (2) ACL (1) EMNLP (1) ICCV (1) MICCAI (1)

Top co-authors

Wei Qian (9) Aidong Zhang (9) Chenxu Zhao (9) Chenglin Miao (8) Yangyi Li (7) Di Wang (6) Liuyi Yao (4) Aobo Chen (4) Ninghao Liu (3) Lichao Sun (2)

Research topics

Differential Privacy (2) Privacy (2)

Keywords

uncertainty quantification (4) machine unlearning (3) neural network interpretability (3) pairwise learning (3) conformal prediction (3) differential privacy (3) adversarial attack (2) shapley value (2) large language model (2) adversarial robustness (2) deep neural network (2) selective forgetting (2) domain generalization (1) data poisoning (1) adversarial learning (1) online learning (1) metric learning (1) causal inference (1) false discovery rate (1) concept-based explanation (1)

Papers

Towards Benchmarking Privacy Vulnerabilities in Selective Forgetting with Large Language Models AAAI 2026 Quantifying and Understanding Uncertainty in Large Reasoning Models ACL 2026 Neuron Explanations for Conformal Prediction (Student Abstract) AAAI 2025 Quantifying Uncertainty in Natural Language Explanations of Large Language Models for Question Answering EMNLP 2025 Membership Inference Attacks with False Discovery Rate Control ICCV 2025 Data Poisoning Attacks against Conformal Prediction ICML 2024 Rethinking Adversarial Robustness in the Context of the Right to be Forgotten ICML 2024 Improving Interpretation Faithfulness for Vision Transformers ICML 2024 Bridging Model Heterogeneity in Federated Learning via Uncertainty-based Asymmetrical Reciprocity Learning ICML 2024 Backdoor Attacks via Machine Unlearning AAAI 2024 Towards Modeling Uncertainties of Self-Explaining Neural Networks via Conformal Prediction AAAI 2024 AdvST: Revisiting Data Augmentations for Single Domain Generalization AAAI 2024 Fostering Trustworthiness in Machine Learning Algorithms AAAI 2024 Automated Natural Language Explanation of Deep Visual Neurons with Large Models (Student Abstract) AAAI 2024 Modeling and Understanding Uncertainty in Medical Image Classification MICCAI 2024 SEAT: Stable and Explainable Attention AAAI 2023 Understanding and Enhancing Robustness of Concept-Based Models AAAI 2023 Static and Sequential Malicious Attacks in the Context of Selective Forgetting NIPS 2023 Towards Automating Model Explanations with Certified Robustness Guarantees AAAI 2022 Differentially Private Pairwise Learning Revisited IJCAI 2021 Pairwise Learning with Differential Privacy Guarantees AAAI 2020 Towards Interpretation of Pairwise Learning AAAI 2020 EC-GAN: Inferring Brain Effective Connectivity via Generative Adversarial Networks AAAI 2020 Deep Metric Learning: The Generalization Analysis and an Adaptive Algorithm IJCAI 2019 Privacy-aware Synthesizing for Crowdsourced Data IJCAI 2019 Representation Learning for Treatment Effect Estimation from Observational Data NIPS 2018