Siliang Zeng - RankMe

29 papers A* 6A 1Misc 1Journal 16Unranked 5

Year	Rank	Type	Title / Venue / Authors
2025	J	`jnl`	Aligning Frozen LLMs by Reinforcement Learning: An Iterative Reweight-then-Optimize Approach. CoRR Xinnan Zhang, Chenliang Li, Siliang Zeng, Jiaxiang Li, Zhongruo Wang, Kaixiang Lin, Songtao Lu, Alfredo García, Mingyi Hong
2025	J	`jnl`	Bridging the Training-Inference Gap in LLMs by Leveraging Self-Generated Tokens. Trans. Mach. Learn. Res. Zhepeng Cen, Yao Liu, Siliang Zeng, Pratik Chaudhari, Huzefa Rangwala, George Karypis, Rasool Fakoor
2025	J	`jnl`	From Demonstrations to Rewards: Alignment Without Explicit Human Preferences. CoRR Siliang Zeng, Yao Liu, Huzefa Rangwala, George Karypis, Mingyi Hong, Rasool Fakoor
2025	A*	`conf`	Joint Reward and Policy Learning with Demonstrations and Human Feedback Improves Alignment. ICLR Chenliang Li, Siliang Zeng, Zeyi Liao, Jiaxiang Li, Dongyeop Kang, Alfredo García, Mingyi Hong
2025	J	`jnl`	Reinforcing Multi-Turn Reasoning in LLM Agents via Turn-Level Credit Assignment. CoRR Siliang Zeng, Quan Wei, William Brown, Oana Frunza, Yuriy Nevmyvaka, Mingyi Hong
2025	J	`jnl`	Structural Estimation of Markov Decision Processes in High-Dimensional State Space with Finite-Time Guarantees. Oper. Res. Siliang Zeng, Mingyi Hong, Alfredo García
2025	A	`conf`	Understanding Inverse Reinforcement Learning under Overparameterization: Non-Asymptotic Analysis and Global Optimality. AISTATS Ruijia Zhang, Siliang Zeng, Chenliang Li, Alfredo García, Mingyi Hong
2025	J	`jnl`	Understanding Inverse Reinforcement Learning under Overparameterization: Non-Asymptotic Analysis and Global Optimality. CoRR Ruijia Zhang, Siliang Zeng, Chenliang Li, Alfredo García, Mingyi Hong
2024	J	`jnl`	Bridging the Training-Inference Gap in LLMs by Leveraging Self-Generated Tokens. CoRR Zhepeng Cen, Yao Liu, Siliang Zeng, Pratik Chaudhari, Huzefa Rangwala, George Karypis, Rasool Fakoor
2024	A*	`conf`	Getting More Juice Out of the SFT Data: Reward Learning from Human Demonstration Improves SFT for LLM Alignment. NeurIPS Jiaxiang Li, Siliang Zeng, Hoi-To Wai, Chenliang Li, Alfredo García, Mingyi Hong
2024	J	`jnl`	Getting More Juice Out of the SFT Data: Reward Learning from Human Demonstration Improves SFT for LLM Alignment. CoRR Jiaxiang Li, Siliang Zeng, Hoi-To Wai, Chenliang Li, Alfredo García, Mingyi Hong
2024	J	`jnl`	Joint Demonstration and Preference Learning Improves Policy Alignment with Human Feedback. CoRR Chenliang Li, Siliang Zeng, Zeyi Liao, Jiaxiang Li, Dongyeop Kang, Alfredo García, Mingyi Hong
2023	Misc	`conf`	A Bayesian Approach to Robust Inverse Reinforcement Learning. CoRL Ran Wei, Siliang Zeng, Chenliang Li, Alfredo García, Anthony D. McDonald, Mingyi Hong
2023	J	`jnl`	A Bayesian Approach to Robust Inverse Reinforcement Learning. CoRR Ran Wei, Siliang Zeng, Chenliang Li, Alfredo García, Anthony D. McDonald, Mingyi Hong
2023	—	`conf`	ProfLLM: A framework for adapting offline large language models to few-shot expert knowledge. ICAICE Hao Wang, Siliang Zeng, Zhenwei Xue, Xinglin Zhu, Fei Wu, Ning Wang
2023	J	`jnl`	Understanding Expertise through Demonstrations: A Maximum Likelihood Framework for Offline Inverse Reinforcement Learning. CoRR Siliang Zeng, Chenliang Li, Alfredo García, Mingyi Hong
2023	A*	`conf`	When Demonstrations meet Generative World Models: A Maximum Likelihood Framework for Offline Inverse Reinforcement Learning. NeurIPS Siliang Zeng, Chenliang Li, Alfredo García, Mingyi Hong
2022	A*	`conf`	A Stochastic Linearized Augmented Lagrangian Method for Decentralized Bilevel Optimization. NeurIPS Songtao Lu, Siliang Zeng, Xiaodong Cui, Mark S. Squillante, Lior Horesh, Brian Kingsbury, Jia Liu, Mingyi Hong
2022	—	`conf`	Learning to Coordinate in Multi-Agent Systems: A Coordinated Actor-Critic Algorithm and Finite-Time Guarantees. L4DC Siliang Zeng, Tianyi Chen, Alfredo García, Mingyi Hong
2022	A*	`conf`	Maximum-Likelihood Inverse Reinforcement Learning with Finite-Time Guarantees. NeurIPS Siliang Zeng, Chenliang Li, Alfredo García, Mingyi Hong
2022	J	`jnl`	On the Divergence of Decentralized Nonconvex Optimization. SIAM J. Optim. Mingyi Hong, Siliang Zeng, Junyu Zhang, Haoran Sun
2022	J	`jnl`	Structural Estimation of Markov Decision Processes in High-Dimensional State Space with Finite-Time Guarantees. CoRR Siliang Zeng, Mingyi Hong, Alfredo García
2021	J	`jnl`	A Momentum-Assisted Single-Timescale Stochastic Approximation Algorithm for Bilevel Optimization. CoRR Prashant Khanduri, Siliang Zeng, Mingyi Hong, Hoi-To Wai, Zhaoran Wang, Zhuoran Yang
2021	A*	`conf`	A Near-Optimal Algorithm for Stochastic Bilevel Optimization via Double-Momentum. NeurIPS Prashant Khanduri, Siliang Zeng, Mingyi Hong, Hoi-To Wai, Zhaoran Wang, Zhuoran Yang
2021	J	`jnl`	Learning to Coordinate in Multi-Agent Systems: A Coordinated Actor-Critic Algorithm and Finite-Time Guarantees. CoRR Siliang Zeng, Tianyi Chen, Alfredo García, Mingyi Hong
2020	—	`conf`	Multi-Agent Reinforcement Learning for Adaptive Routing: A Hybrid Method using Eligibility Traces. ICCA Siliang Zeng, Xingfei Xu, Yi Chen
2020	—	`conf`	Network-Level System Performance Prediction Using Deep Neural Networks with Cross-Layer Information. ICC Qi Cao, Siliang Zeng, Man-On Pun, Yi Chen
2020	J	`jnl`	On the Divergence of Decentralized Non-Convex Optimization. CoRR Mingyi Hong, Siliang Zeng, Junyu Zhang, Haoran Sun
2006	—	`conf`	A new In-network data aggregation technology of wireless sensor networks. SKG Jianbo Xu, Siliang Zeng, Fengjiao Qu