6 papers
Polynomial Expansion Rank Adaptation: Enhancing Low-Rank Fine-Tuning with High-Order Interactions
Wenhao Zhang, Lin Mu, Li Ni +2
Low-rank adaptation (LoRA) is a widely used strategy for efficient fine-tuning of large language models (LLMs), but its strictly linear structure fundamentally limits expressive ca…
Group-Relative REINFORCE Is Secretly an Off-Policy Algorithm: Demystifying Some Myths About GRPO and Its Friends
Chaorui Yao, Yanxi Chen, Yuchang Sun +5
Off-policy reinforcement learning (RL) for large language models (LLMs) is attracting growing interest, driven by practical constraints in real-world applications, the complexity o…
IntentRL: Training Proactive User-intent Agents for Open-ended Deep Research via Reinforcement Learning
Haohao Luo, Zexi Li, Yuexiang Xie +3
Deep Research (DR) agents extend Large Language Models (LLMs) beyond parametric knowledge by autonomously retrieving and synthesizing evidence from large web corpora into long-form…
On the Entropy Dynamics in Reinforcement Fine-Tuning of Large Language Models
Shumin Wang, Yuexiang Xie, Wenhao Zhang +4
Entropy serves as a critical metric for measuring the diversity of outputs generated by large language models (LLMs), providing valuable insights into their exploration capabilitie…
Data-Juicer 2.0: Cloud-Scale Adaptive Data Processing for and with Foundation Models
Daoyuan Chen, Yilun Huang, Xuchen Pan +12
Foundation models demand advanced data processing for their vast, multimodal datasets. However, traditional frameworks struggle with the unique complexities of multimodal data. In…
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…