6 citations · 9 across the 12 of their papers we have counts for
7 papers · 1 filter
GEM: A Gym for Agentic LLMs
Zichen Liu, Anya Sims, Keyu Duan +16
The training paradigm for large language models (LLMs) is moving from static datasets to experience-based learning, where agents acquire skills via interacting with complex environ…
Efficient Process Reward Model Training via Active Learning
Keyu Duan, Zichen Liu, Xin Mao +5
Process Reward Models (PRMs) provide step-level supervision to large language models (LLMs), but scaling up training data annotation remains challenging for both humans and LLMs. T…
Understanding R1-Zero-Like Training: A Critical Perspective
Zichen Liu, Changyu Chen, Wenjun Li +5
DeepSeek-R1-Zero has shown that reinforcement learning (RL) at scale can directly enhance the reasoning capabilities of LLMs without supervised fine-tuning. In this work, we critic…
On Learning Informative Trajectory Embeddings for Imitation, Classification and Regression
Zichang Ge, Changyu Chen, Arunesh Sinha +1
In real-world sequential decision making tasks like autonomous driving, robotics, and healthcare, learning from observed state-action trajectories is critical for tasks like imitat…
Sample-Efficient Alignment for LLMs
Zichen Liu, Changyu Chen, Chao Du +2
We study methods for efficiently aligning large language models (LLMs) with human preferences given budgeted online feedback. We first formulate the LLM alignment problem in the fr…
Towards Neural Network based Cognitive Models of Dynamic Decision-Making by Humans
Changyu Chen, Shashank Reddy Chirra, Maria José Ferreira +3
Modeling human cognitive processes in dynamic decision-making tasks has been an endeavor in AI for a long time because such models can help make AI systems more intuitive, personal…
Generative Modelling of Stochastic Actions with Arbitrary Constraints in Reinforcement Learning
Changyu Chen, Ramesha Karunasena, Thanh Hong Nguyen +2
Many problems in Reinforcement Learning (RL) seek an optimal policy with large discrete multidimensional yet unordered action spaces; these include problems in randomized allocatio…