Jiantao Jiao

31 papers · 2018–2025 · 8 conferences · across top CS/AI conferences

Achievements

+10 more ↓

🏃 Academic Marathon (7) 🌉 Interdisciplinary Bridge 🧭 Keyword Pioneer 🌍 Conference Polyglot (8) 🐝 Cross-Pollinator (10)

🐝 Cross-Pollinator (10) 🌈 Renaissance Researcher (9) 🗺️ Taxonomy Completionist (61) 🏆 Grand Slam 🏆 Keyword Champion 👑 Triple Crown 🗃️ Keyword Collector (131) 💎 Century Club (31) 🔥 Unstoppable (8) ⚡ Prolific Year (5)

Conferences

NIPS (15) ICML (8) ICLR (3) AAAI (1) AISTATS (1) COLT (1) EMNLP (1) JMLR (1)

Top co-authors

Banghua Zhu (9) Paria Rashidinejad (5) Kannan Ramchandran (5) Yanjun Han (5) Michael Jordan (5) Tianhao Wu (4) Hanlin Zhu (4) Yuandong Tian (4) Nived Rajaraman (4) Stuart J. Russell (3)

Research topics

Applications (1) Privacy (1) Statistics (1)

Keywords

imitation learning (5) sample complexity (3) policy learning (3) large language model (3) online learning (2) language modeling (2) reinforcement learning (2) minimax rate (2) moment matching (2) offline reinforcement learning (2) federated learning (2) regret bound (2) behavior cloning (2) policy optimization (2) sample efficiency (1) model selection (1) differential privacy (1) object detection (1) reward modeling (1) image classification (1)

Papers

Meta-Rewarding Language Models: Self-Improving Alignment with LLM-as-a-Meta-Judge EMNLP 2025 Token Assorted: Mixing Latent and Text Tokens for Improved Language Model Reasoning ICML 2025 EmbedLLM: Learning Compact Representations of Large Language Models ICLR 2025 Thinking LLMs: General Instruction Following with Thought Generation ICML 2025 How to Evaluate Reward Models for RLHF ICLR 2025 An Analysis of Tokenization: Transformers under Markov Data NIPS 2024 Toxicity Detection for Free NIPS 2024 Towards a Theoretical Understanding of the 'Reversal Curse' via Training Dynamics NIPS 2024 Iterative Data Smoothing: Mitigating Reward Overfitting and Overoptimization in RLHF ICML 2024 Online Learning in Stackelberg Games with an Omniscient Follower ICML 2023 Doubly-Robust Self-Training NIPS 2023 Importance Weighted Actor-Critic for Optimal Conservative Offline Reinforcement Learning NIPS 2023 Towards Optimal Caching and Model Selection for Large Model Inference NIPS 2023 Securing Secure Aggregation: Mitigating Multi-Round Privacy Leakage in Federated Learning AAAI 2023 Byzantine-Robust Federated Learning with Optimal Statistical Rates AISTATS 2023 Optimal Conservative Offline RL with General Function Approximation via Augmented Lagrangian ICLR 2023 Jump-Start Reinforcement Learning ICML 2023 Principled Reinforcement Learning with Human Feedback from Pairwise or K-wise Comparisons ICML 2023 Beyond the Best: Distribution Functional Estimation in Infinite-Armed Bandits NIPS 2022 Minimax Optimal Online Imitation Learning via Replay Estimation NIPS 2022 Nearly Optimal Policy Optimization with Stable at Any Time Guarantee ICML 2022 Bridging Offline Reinforcement Learning and Imitation Learning: A Tale of Pessimism NIPS 2021 On the Value of Interaction and Function Approximation in Imitation Learning NIPS 2021 MADE: Exploration via Maximizing Deviation from Explored Regions NIPS 2021 Toward the Fundamental Limits of Imitation Learning NIPS 2020 SLIP: Learning to predict in unknown dynamical systems with long-term memory NIPS 2020 Approximate Profile Maximum Likelihood JMLR 2019 Theoretically Principled Trade-off between Robustness and Accuracy ICML 2019 Local moment matching: A unified methodology for symmetric functional estimation and distribution estimation under Wasserstein distance COLT 2018 The Nearest Neighbor Information Estimator is Adaptively Near Minimax Rate-Optimal NIPS 2018 Entropy Rate Estimation for Markov Chains with Large State Space NIPS 2018