← Authors

Mengdi Wang

105 papers · 2016–2026 · 17 conferences · across top CS/AI conferences

Achievements

🧭 Keyword Pioneer 🌍 Conference Polyglot (17) πŸƒ Academic Marathon (10) πŸŒ‰ Interdisciplinary Bridge 🐝 Cross-Pollinator (5) 🌈 Renaissance Researcher (6) 🐣 Hot Topic Early Bird πŸ—ΊοΈ Taxonomy Completionist (24) 🏠 Conference Loyalist (27) πŸ† Keyword Champion (2) πŸ‘‘ Triple Crown 🀝 Dynamic Duo (15) πŸ”¬ Deep Specialist (22) πŸ† Grand Slam πŸ“ˆ Trend Setter ❓ The Questioner (2) ⚑ Prolific Year (7) πŸš€ Conference Pioneer πŸ—ƒοΈ Keyword Collector (97) πŸ’Ž Century Club (104) πŸ”₯ Unstoppable (11)

Conferences

NIPS (27) ICML (26) ICLR (14) AISTATS (8) JMLR (7) AAAI (4) EMNLP (3) IJCAI (3) EACL (2) CVPR (2) L4DC (2) UAI (2) ICCV (1) COLT (1) ACL (1) NAACL (1) WACV (1)

Top co-authors

Minshuo Chen (15) Kaixuan Huang (11) Lin Yang (9) Xuezhou Zhang (9) Ming Yin (9) Hui Yuan (9) Huazheng Wang (9) Alec Koppel (8) Tuo Zhao (8) Csaba SzepesvΓ‘ri (8)

Research topics

Computer Vision (1) Optimization & Theory (1)

Keywords

reinforcement learning (14) sample complexity (13) regret bound (9) markov decision process (8) stochastic optimization (7) policy gradient (6) markov chain (6) representation learning (5) large language model (5) off-policy evaluation (5) kernel methods (4) inference-time alignment (4) model-based reinforcement learning (4) linear function approximation (3) curse of dimensionality (3) stochastic gradient (3) off-policy learning (3) bayesian regret (3) dimensionality reduction (3) online learning (3)

Papers

Jailbreaks as Inference-Time Alignment: A Framework for Understanding Safety Failures in LLMs EACL 2026
CycleSL: Server-Client Cyclical Update Driven Scalable Split Learning WACV 2026
TreeBoN: Enhancing Inference-Time Alignment with Speculative Tree-Search and Best-of-N Sampling EMNLP 2025
Temporal Consistency for LLM Reasoning Process Error Identification EMNLP 2025
Preacher: Paper-to-Video Agentic System ICCV 2025
Emergent Symbolic Mechanisms Support Abstract Reasoning in Large Language Models ICML 2025
A First-order Generative Bilevel Optimization Framework for Diffusion Models ICML 2025
BaWA: Automatic Optimizing Pruning Metric for Large Language Models with Balanced Weight and Activation ICML 2025
MATH-Perturb: Benchmarking LLMs’ Math Reasoning Abilities against Hard Perturbations ICML 2025
A Common Pitfall of Margin-based Language Model Alignment: Gradient Entanglement ICLR 2025
EmoAgent: Assessing and Safeguarding Human-AI Interaction for Mental Health Safety EMNLP 2025
Shallow Preference Signals: Large Language Model Aligns Even Better with Truncated Data? ACL 2025
Rectified Diffusion: Straightness Is Not Your Need in Rectified Flow ICLR 2025
Towards Understanding Text Hallucination of Diffusion Models via Local Generation Bias ICLR 2025
IterComp: Iterative Composition-Aware Feedback Learning from Model Gallery for Text-to-Image Generation ICLR 2025
Diffusion Transformer Captures Spatial-Temporal Dependencies: A Theory for Gaussian Process Data ICLR 2025
Deep Reinforcement Learning for Efficient and Fair Allocation of Healthcare Resources IJCAI 2025
WenyanGPT: A Large Language Model for Classical Chinese Tasks IJCAI 2025
Collab: Controlled Decoding using Mixture of Agents for LLM Alignment ICLR 2025
Immune: Improving Safety Against Jailbreaks in Multi-modal LLMs via Inference-Time Alignment CVPR 2025
FlexSBDD: Structure-Based Drug Design with Flexible Protein Modeling NIPS 2024
Nonparametric Classification on Low Dimensional Manifolds using Overparameterized Convolutional Residual Networks NIPS 2024
Offline Multitask Representation Learning for Reinforcement Learning NIPS 2024
One-Layer Transformer Provably Learns One-Nearest Neighbor In Context NIPS 2024
Gradient Guidance for Diffusion Models: An Optimization Perspective NIPS 2024
Transfer Q-star : Principled Decoding for LLM Alignment NIPS 2024
A Theoretical Perspective for Speculative Decoding Algorithm NIPS 2024
Information-Directed Pessimism for Offline Reinforcement Learning ICML 2024
Tree Search-Based Evolutionary Bandits for Protein Sequence Optimization AAAI 2024
TurboSVM-FL: Boosting Federated Learning through SVM Aggregation for Lazy Clients AAAI 2024
Visual Adversarial Examples Jailbreak Aligned Large Language Models AAAI 2024
Policy Evaluation for Reinforcement Learning from Human Feedback: A Sample Complexity Analysis AISTATS 2024
Theory of Consistency Diffusion Models: Distribution Estimation Meets Fast Sampling ICML 2024
MaxMin-RLHF: Alignment with Diverse Human Preferences ICML 2024
Is Inverse Reinforcement Learning Harder than Standard Reinforcement Learning? A Theoretical Perspective ICML 2024
Theoretical insights for diffusion guidance: A case study for Gaussian mixture models ICML 2024
Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications ICML 2024
PARL: A Unified Framework for Policy Alignment in Reinforcement Learning from Human Feedback ICLR 2024
Sample-Efficient Learning of POMDPs with Multiple Observations In Hindsight ICLR 2024
Sample Complexity of Neural Policy Mirror Descent for Policy Optimization on Low-Dimensional Manifolds JMLR 2024
On the Sample Complexity and Metastability of Heavy-tailed Policy Search in Continuous Control JMLR 2024
Global Convergence in Training Large-Scale Transformers NIPS 2024
Fast Best-of-N Decoding via Speculative Rejection NIPS 2024
Sample Complexity of Nonparametric Off-Policy Evaluation on Low-Dimensional Manifolds using Deep Networks ICLR 2023
Posterior Sampling with Delayed Feedback for Reinforcement Learning with Linear Function Approximation NIPS 2023
Unified Off-Policy Learning to Rank: a Reinforcement Learning Perspective NIPS 2023
Efficient RL with Impaired Observability: Learning to Act with Delayed and Missing State Observations NIPS 2023
Reward-Directed Conditional Diffusion: Provable Distribution Estimation and Reward Improvement NIPS 2023
Byzantine-Robust Online and Offline Distributed Reinforcement Learning AISTATS 2023
Provable Benefits of Representational Transfer in Reinforcement Learning COLT 2023
Offline Reinforcement Learning with Differentiable Function Approximation is Provably Efficient ICLR 2023
Learning Kernelized Contextual Bandits in a Distributed and Asynchronous Environment ICLR 2023
Deep Reinforcement Learning for Cost-Effective Medical Diagnosis ICLR 2023
Representation Learning for Low-rank General-sum Markov Games ICLR 2023
STEERING : Stein Information Directed Exploration for Model-Based Reinforcement Learning ICML 2023
Score Approximation, Estimation and Distribution Recovery of Diffusion Models on Low-Dimensional Data ICML 2023
Provably Efficient Representation Learning with Tractable Planning in Low-Rank POMDP ICML 2023
Effective Minkowski Dimension of Deep Nonparametric Regression: Function Approximation and Statistical Theories ICML 2023
Learning Good State and Action Representations for Markov Decision Process via Tensor Decomposition JMLR 2023
Double Duality: Variational Primal-Dual Policy Optimization for Constrained Reinforcement Learning JMLR 2023
Offline stochastic shortest path: Learning, evaluation and towards optimality UAI 2022
Bandit Theory and Thompson Sampling-Guided Directed Evolution for Sequence Optimization NIPS 2022
Communication Efficient Distributed Learning for Kernelized Contextual Bandits NIPS 2022
Optimal Estimation of Policy Gradient via Double Fitted Iteration ICML 2022
Efficient Reinforcement Learning in Block MDPs: A Model-free Representation Learning approach ICML 2022
Off-Policy Fitted Q-Evaluation with Differentiable Function Approximators: Z-Estimation and Inference Theory ICML 2022
Near-optimal Offline Reinforcement Learning with Linear Representation: Leveraging Variance Information with Pessimism ICLR 2022
Parameter-Efficient Sparsity for Large Language Models Fine-Tuning IJCAI 2022
Decentralized Gossip-Based Stochastic Bilevel Optimization over Communication Networks NIPS 2022
Multi-Agent Reinforcement Learning with General Utilities via Decentralized Shadow Reward Actor-Critic AAAI 2022
On the Convergence and Sample Efficiency of Variance-Reduced Policy Gradient Method NIPS 2021
Towards Compact CNNs via Collaborative Compression CVPR 2021
Sparse Feature Selection Makes Batch Reinforcement Learning More Sample Efficient ICML 2021
Bootstrapping Fitted Q-Evaluation for Off-Policy Inference ICML 2021
Contrastive Multi-document Question Generation EACL 2021
Online Sparse Reinforcement Learning AISTATS 2021
Generalization Bounds for Stochastic Saddle Point Problems AISTATS 2021
Solving Discounted Stochastic Two-Player Games with Near-Optimal Time and Sample Complexity AISTATS 2020
Sketching Transformed Matrices with Applications to Natural Language Processing AISTATS 2020
Model-Based Reinforcement Learning with Value-Targeted Regression ICML 2020
Minimax-Optimal Off-Policy Evaluation with Linear Function Approximation ICML 2020
Reinforcement Learning in Feature Space: Matrix Bandit, Kernels, and Regret Bound ICML 2020
A Duality Approach for Regret Minimization in Average-Award Ergodic Markov Decision Processes L4DC 2020
Provably Efficient Reinforcement Learning with Kernel and Neural Function Approximations NIPS 2020
Generalized Leverage Score Sampling for Neural Networks NIPS 2020
High-Dimensional Sparse Linear Bandits NIPS 2020
Variational Policy Gradient Method for Reinforcement Learning with General Utilities NIPS 2020
Model-Based Reinforcement Learning with Value-Targeted Regression L4DC 2020
Online Factorization and Partition of Complex Networks by Random Walk UAI 2019
Learning low-dimensional state embeddings and metastable clusters from time series data NIPS 2019
Approximation Hardness for A Class of Sparse Optimization Problems JMLR 2019
Picasso: A Sparse Learning Library for High Dimensional Data Analysis in R and Python JMLR 2019
State Aggregation Learning from Markov Transition Data NIPS 2019
Towards Coherent and Cohesive Long-form Text Generation NAACL 2019
Sample-Optimal Parametric Q-Learning Using Linearly Additive Features ICML 2019
Near-Optimal Time and Sample Complexities for Solving Markov Decision Processes with a Generative Model NIPS 2018
Dimensionality Reduction for Stationary Time Series via Stochastic Nonconvex Optimization NIPS 2018
Estimation of Markov Chain via Rank-Constrained Likelihood ICML 2018
Minimax-Optimal Privacy-Preserving Sparse PCA in Distributed Systems AISTATS 2018
Scalable Bilinear Pi Learning Using State and Action Features ICML 2018
Diffusion Approximations for Online Principal Component Estimation and Global Convergence NIPS 2017
Strong NP-Hardness for Sparse Optimization with Concave Penalty Functions ICML 2017
Accelerating Stochastic Composition Optimization JMLR 2017
Finite-sum Composition Optimization via Variance Reduced Gradient Descent AISTATS 2017
Accelerating Stochastic Composition Optimization NIPS 2016