Mingyi Hong

BLUR: A Bi-Level Optimization Approach for LLM Unlearning EACL 2026 RoSTE: An Efficient Quantization-Aware Supervised Fine-Tuning Approach for Large Language Models ICML 2025 SemEval-2025 Task 4: Unlearning sensitive content from Large Language Models ACL 2025 Understanding Inverse Reinforcement Learning under Overparameterization: Non-Asymptotic Analysis and Global Optimality AISTATS 2025 Split-Merge: Scalable and Memory-Efficient Merging of Expert LLMs EMNLP 2025 LUME: LLM Unlearning with Multitask Evaluations EMNLP 2025 AssistedDS: Benchmarking How External Domain Knowledge Assists LLMs in Automated Data Science EMNLP 2025 Joint Reward and Policy Learning with Demonstrations and Human Feedback Improves Alignment ICLR 2025 Do LLMs Recognize Your Preferences? Evaluating Personalized Preference Following in LLMs ICLR 2025 DiSK: Differentially Private Optimizer with Simplified Kalman Filter for Noise Reduction ICLR 2025 Towards LLM Unlearning Resilient to Relearning Attacks: A Sharpness-Aware Minimization Perspective and Beyond ICML 2025 Inference-Time Alignment of Diffusion Models with Direct Noise Optimization ICML 2025 On the Vulnerability of Applying Retrieval-Augmented Generation within Knowledge-Intensive Application Domains ICML 2025 BRiTE: Bootstrapping Reinforced Thinking Process to Enhance Language Model Reasoning ICML 2025 Unlearning as multi-task optimization: A normalized gradient difference approach with an adaptive learning rate NAACL 2025 SemEval-2025 Task 4: Unlearning sensitive content from Large Language Models SEMEVAL 2025 RAW: A Robust and Agile Plug-and-Play Watermark Framework for AI-Generated Images with Provable Guarantees NIPS 2024 Demystifying Poisoning Backdoor Attacks from a Statistical Perspective ICLR 2024 Revisiting Zeroth-Order Optimization for Memory-Efficient LLM Fine-Tuning: A Benchmark ICML 2024 EMC$^2$: Efficient MCMC Negative Sampling for Contrastive Learning with Global Convergence ICML 2024 MADA: Meta-Adaptive Optimizers Through Hyper-Gradient Descent ICML 2024 Differentially Private SGD Without Clipping Bias: An Error-Feedback Approach ICLR 2024 Defensive Unlearning with Adversarial Training for Robust Concept Erasure in Diffusion Models NIPS 2024 Krylov Cubic Regularized Newton: A Subspace Second-Order Method with Dimension-Free Convergence Rate AISTATS 2024 DOPPLER: Differentially Private Optimizers with Low-pass Filter for Privacy Noise Reduction NIPS 2024 Unraveling the Gradient Descent Dynamics of Transformers NIPS 2024 Pre-training Differentially Private Models with Limited Public Data NIPS 2024 SLTrain: a sparse plus low rank approach for parameter and memory efficient pretraining NIPS 2024 Getting More Juice Out of the SFT Data: Reward Learning from Human Demonstration Improves SFT for LLM Alignment NIPS 2024 A Unified Detection Framework for Inference-Stage Backdoor Defenses NIPS 2023 Linearly Constrained Bilevel Optimization: A Smoothed Implicit Gradient Approach ICML 2023 What Is Missing in IRM Training and Evaluation? Challenges and Solutions ICLR 2023 Selectivity Drives Productivity: Efficient Dataset Pruning for Enhanced Transfer Learning NIPS 2023 When Demonstrations meet Generative World Models: A Maximum Likelihood Framework for Offline Inverse Reinforcement Learning NIPS 2023 A Bayesian Approach to Robust Inverse Reinforcement Learning CORL 2023 Understanding Backdoor Attacks through the Adaptability Hypothesis ICML 2023 FedAvg Converges to Zero Training Loss Linearly for Overparameterized Multi-Layer Neural Networks ICML 2023 VCC: Scaling Transformers to 128K Tokens or More by Prioritizing Important Tokens NIPS 2023 Advancing Model Pruning via Bi-level Optimization NIPS 2022 Inducing Equilibria via Incentives: Simultaneous Design-and-Play Ensures Global Convergence NIPS 2022 A Stochastic Linearized Augmented Lagrangian Method for Decentralized Bilevel Optimization NIPS 2022 Learning to Coordinate in Multi-Agent Systems: A Coordinated Actor-Critic Algorithm and Finite-Time Guarantees L4DC 2022 Distributed adversarial training to robustify deep neural networks at scale UAI 2022 Decentralized Learning for Overparameterized Problems: A Multi-Agent Kernel Approximation Approach ICLR 2022 How to Robustify Black-Box ML Models? A Zeroth-Order Optimization Perspective ICLR 2022 Understanding Clipping for Federated Learning: Convergence and Client-Level Differential Privacy ICML 2022 A Stochastic Multi-Rate Control Framework For Modeling Distributed Optimization Algorithms ICML 2022 Revisiting and Advancing Fast Adversarial Training Through The Lens of Bi-Level Optimization ICML 2022 Distributed Optimization for Overparameterized Problems: Achieving Optimal Dimension Independent Communication Complexity NIPS 2022 Maximum-Likelihood Inverse Reinforcement Learning with Finite-Time Guarantees NIPS 2022 RMSprop converges with proper hyper-parameter ICLR 2021 Decentralized Riemannian Gradient Descent on the Stiefel Manifold ICML 2021 STEM: A Stochastic Two-Sided Momentum Algorithm Achieving Near-Optimal Sample and Communication Complexities for Federated Learning NIPS 2021 When Expressivity Meets Trainability: Fewer than $n$ Neurons Can Work NIPS 2021 A Near-Optimal Algorithm for Stochastic Bilevel Optimization via Double-Momentum NIPS 2021 Finding First-Order Nash Equilibria of Zero-Sum Games with the Regularized Nikaido-Isoda Function AISTATS 2021 Generalization Bounds for Stochastic Saddle Point Problems AISTATS 2021 Finding Second-Order Stationary Points Efficiently in Smooth Nonconvex Linearly Constrained Optimization Problems NIPS 2020 Understanding Gradient Clipping in Private SGD: A Geometric Perspective NIPS 2020 Provably Efficient Neural GTD for Off-Policy Learning NIPS 2020 Distributed Training with Heterogeneous Data: Bridging Median- and Mean-Based Algorithms NIPS 2020 Min-Max Optimization without Gradients: Convergence and Applications to Black-Box Evasion and Poisoning Attacks ICML 2020 Improving the Sample and Communication Complexity for Decentralized Non-Convex Optimization: Joint Gradient Estimation and Tracking ICML 2020 Topology Attack and Defense for Graph Neural Networks: An Optimization Perspective IJCAI 2019 PA-GD: On the Convergence of Perturbed Alternating Gradient Descent to Second-Order Stationary Points for Structured Nonconvex Optimization ICML 2019 ZO-AdaMM: Zeroth-Order Adaptive Momentum Method for Black-Box Optimization NIPS 2019 Variance Reduced Policy Evaluation with Smooth Function Approximation NIPS 2019 Provably Global Convergence of Actor-Critic: A Case for Linear Quadratic Regulator with Ergodic Cost NIPS 2019 signSGD via Zeroth-Order Oracle ICLR 2019 On the Convergence of A Class of Adam-Type Algorithms for Non-Convex Optimization ICLR 2019 On Fast Convergence of Proximal Algorithms for SQRT-Lasso Optimization: Don’t Worry About its Nonsmooth Loss Function UAI 2019 On Faster Convergence of Cyclic Block Coordinate Descent-type Methods for Strongly Convex Minimization JMLR 2018 Multi-Agent Reinforcement Learning via Double Averaging Primal-Dual Optimization NIPS 2018 Gradient Primal-Dual Algorithm Converges to Second-Order Stationary Solution for Nonconvex Distributed Optimization Over Networks ICML 2018 Towards K-means-friendly Spaces: Simultaneous Deep Learning and Clustering ICML 2017 A Stochastic Nonconvex Splitting Method for Symmetric Nonnegative Matrix Factorization AISTATS 2017 Prox-PDA: The Proximal Primal-Dual Algorithm for Fast Distributed Nonconvex Optimization and Learning Over Networks ICML 2017 An Improved Convergence Analysis of Cyclic Block Coordinate Descent-type Methods for Strongly Convex Minimization AISTATS 2016 NESTT: A Nonconvex Primal-Dual Splitting Method for Distributed and Stochastic Optimization NIPS 2016 Improved Iteration Complexity Bounds of Cyclic Block Coordinate Descent for Convex Problems NIPS 2015 Parallel Successive Convex Approximation for Nonsmooth Nonconvex Optimization NIPS 2014