3 papers
cs.LG2026
One Model for All: Multi-Objective Controllable Language Models
Qiang He, Yucheng Yang, Tianyi Zhou +3
Aligning large language models (LLMs) with human preferences is critical for enhancing LLMs' safety, helpfulness, humor, faithfulness, etc. Current reinforcement learning from huma…
cs.LG2025
Task Adaptation from Skills: Information Geometry, Disentanglement, and New Objectives for Unsupervised Reinforcement Learning
Yucheng Yang, Tianyi Zhou, Qiang He +3
Unsupervised reinforcement learning (URL) aims to learn general skills for unseen downstream tasks. Mutual Information Skill Learning (MISL) addresses URL by maximizing the mutual…
cs.CL2025
ATLaS: Agent Tuning via Learning Critical Steps
Zhixun Chen, Ming Li, Yuxuan Huang +3
Large Language Model (LLM) agents have demonstrated remarkable generalization capabilities across multi-domain tasks. Existing agent tuning approaches typically employ supervised f…