activity
20242026
collaborators

7 papers

cs.AI2026

Beyond the Sampled Token: Preserving Candidate Support in RLVR

Ruotian Peng, Yi Ren, Zhouliang Yu +2

We revisit exploration collapse in reinforcement learning with verifiable rewards (RLVR), from the perspective of the \emph{candidate distribution} for next-token prediction. We fo…

cs.LG2026

Token Hidden Reward: Steering Exploration-Exploitation in Group Relative Deep Reinforcement Learning

Wenlong Deng, Yi Ren, Yushu Li +4

Reinforcement learning with verifiable rewards has significantly advanced the reasoning capabilities of large language models, yet how to explicitly steer training toward explorati…

cs.CL2026

On Group Relative Policy Optimization Collapse in Agent Search: The Lazy Likelihood-Displacement

Wenlong Deng, Yushu Li, Boying Gong +3

Tool-integrated (TI) reinforcement learning (RL) enables large language models (LLMs) to perform multi-step reasoning by interacting with external tools such as search engines and…

cs.LG2025

Learning Dynamics of Deep Learning -- Force Analysis of Deep Neural Networks

Yi Ren

This thesis explores how deep learning models learn over time, using ideas inspired by force analysis. Specifically, we zoom in on the model's training procedure to see how one tra…

cs.LG2025

Learning Dynamics of LLM Finetuning

Yi Ren, Danica J. Sutherland

Learning dynamics, which describes how the learning of specific training examples influences the model's predictions on other examples, gives us a powerful tool for understanding t…

cs.LG2025

On the Effect of Negative Gradient in Group Relative Deep Reinforcement Optimization

Wenlong Deng, Yi Ren, Muchen Li +3

Reinforcement learning (RL) has become popular in enhancing the reasoning capabilities of large language models (LLMs), with Group Relative Policy Optimization (GRPO) emerging as a…