22 citations · 31 across the 12 of their papers we have counts for
12 papers
Evolutionary System Prompt Learning for Reinforcement Learning in LLMs
Lunjun Zhang, Ryan Chen, Bradly C. Stadie
Building agentic systems that can autonomously self-improve from experience is a longstanding goal of AI. Large language models (LLMs) today primarily self-improve via two mechanis…
EMA Policy Gradient: Taming Reinforcement Learning for LLMs with EMA Anchor and Top-k KL
Lunjun Zhang, Jimmy Ba
Reinforcement Learning (RL) has enabled Large Language Models (LLMs) to acquire increasingly complex reasoning and agentic behaviors. In this work, we propose two simple techniques…
D2 Actor Critic: Diffusion Actor Meets Distributional Critic
Lunjun Zhang, Shuo Han, Hanrui Lyu +1
We introduce D2AC, a new model-free reinforcement learning (RL) algorithm designed to train expressive diffusion policies online effectively. At its core is a policy improvement ob…
CoLD: Counterfactually-Guided Length Debiasing for Process Reward Models in Mathematical Reasoning
Congmin Zheng, Jiachen Zhu, Jianghao Lin +6
Process Reward Models (PRMs) play a central role in evaluating and guiding multi-step reasoning in large language models (LLMs), especially for mathematical problem solving. Howeve…
Thinking vs. Doing: Agents that Reason by Scaling Test-Time Interaction
Junhong Shen, Hao Bai, Lunjun Zhang +8
The current paradigm of test-time scaling relies on generating long reasoning traces ("thinking" more) before producing a response. In agent problems that require interaction, this…
Learning to Drive via Asymmetric Self-Play
Chris Zhang, Sourav Biswas, Kelvin Wong +5
Large-scale data is crucial for learning realistic and capable driving policies. However, it can be impractical to rely on scaling datasets with real data alone. The majority of dr…
Generative Verifiers: Reward Modeling as Next-Token Prediction
Lunjun Zhang, Arian Hosseini, Hritik Bansal +3
Verifiers or reward models are often used to enhance the reasoning performance of large language models (LLMs). A common approach is the Best-of-N method, where N candidate solutio…
Towards Unsupervised Object Detection From LiDAR Point Clouds
Lunjun Zhang, Anqi Joyce Yang, Yuwen Xiong +4
In this paper, we study the problem of unsupervised object detection from 3D point clouds in self-driving scenes. We present a simple yet effective method that exploits (i) point c…
Learning Realistic Traffic Agents in Closed-loop
Chris Zhang, James Tu, Lunjun Zhang +3
Realistic traffic simulation is crucial for developing self-driving software in a safe and scalable manner prior to real-world deployment. Typically, imitation learning (IL) is use…
Copilot4D: Learning Unsupervised World Models for Autonomous Driving via Discrete Diffusion
Lunjun Zhang, Yuwen Xiong, Ze Yang +3
Learning world models can teach an agent how the world works in an unsupervised manner. Even though it can be viewed as a special case of sequence modeling, progress for scaling wo…
Understanding Hindsight Goal Relabeling from a Divergence Minimization Perspective
Lunjun Zhang, Bradly C. Stadie
Hindsight goal relabeling has become a foundational technique in multi-goal reinforcement learning (RL). The essential idea is that any trajectory can be seen as a sub-optimal demo…
World Model as a Graph: Learning Latent Landmarks for Planning
Lunjun Zhang, Ge Yang, Bradly C. Stadie
Planning - the ability to analyze the structure of a problem in the large and decompose it into interrelated subproblems - is a hallmark of human intelligence. While deep reinforce…