activity
20242026
collaborators
Showing cs.LGShow all

7 papers · 1 filter

cs.LG2026

Beyond Solvability: Task Learnability as a Static Prior for LLM RL Post-Training

Ting Zhou, Zhenqing Ling, Daoyuan Chen +4

Reinforcement learning (RL) has become a central post-training paradigm for eliciting reasoning capabilities in large language models, yet uniform task sampling allocates compute w…

cs.LG2026

GEOALIGN: Geometric Rollout Curation for Robust LLM Reinforcement Learning

Ting Zhou, Zhenqing Ling, Yiyang Zhao +2

Online reinforcement learning is widely used to align large language models (LLMs) with reward signals, yet training can be unstable under noisy or misspecified rewards. We identif…

cs.LG2026

Spectral Evolution Search: Efficient Inference-Time Scaling for Reward-Aligned Image Generation

Jinyan Ye, Zhongjie Duan, Zhiwen Li +4

Inference-time scaling offers a versatile paradigm for aligning visual generative models with downstream objectives without parameter updates. However, existing approaches that opt…

cs.LG2025

Trinity-RFT: A General-Purpose and Unified Framework for Reinforcement Fine-Tuning of Large Language Models

Xuchen Pan, Yanxi Chen, Yushuo Chen +11

Trinity-RFT is a general-purpose, unified and easy-to-use framework designed for reinforcement fine-tuning (RFT) of large language models. It is built with a modular and decoupled…

cs.LG2025

BiMix: A Bivariate Data Mixing Law for Language Model Pretraining

Ce Ge, Zhijian Ma, Daoyuan Chen +2

Large language models have demonstrated remarkable capabilities across various tasks, primarily attributed to the utilization of diversely sourced data. However, the impact of pret…

cs.LG2024

On the Convergence of Zeroth-Order Federated Tuning for Large Language Models

Zhenqing Ling, Daoyuan Chen, Liuyi Yao +2

The confluence of Federated Learning (FL) and Large Language Models (LLMs) is ushering in a new era in privacy-preserving natural language processing. However, the intensive memory…