3 papers
cs.AI2026
Consolidation or Adaptation? PRISM: Disentangling SFT and RL Data via Gradient Concentration
Yang Zhao, Yangou Ouyang, Xiao Ding +8
While Hybrid Supervised Fine-Tuning (SFT) followed by Reinforcement Learning (RL) has become the standard paradigm for training LLM agents, effective mechanisms for data allocation…
cs.LG2026
MAESTRO: Meta-learning Adaptive Estimation of Scalarization Trade-offs for Reward Optimization
Yang Zhao, Hepeng Wang, Xiao Ding +8
Group-Relative Policy Optimization (GRPO) has emerged as an efficient paradigm for aligning Large Language Models (LLMs), yet its efficacy is primarily confined to domains with ver…
cs.CL2025
Beyond Similarity: A Gradient-based Graph Method for Instruction Tuning Data Selection
Yang Zhao, Li Du, Xiao Ding +10
Large language models (LLMs) have shown great potential across various industries due to their remarkable ability to generalize through instruction tuning. However, the limited ava…