Showing 2026Show all
3 papers · 1 filter
cs.CL2026
Large Language Models Do Not Always Need Readable Language
Jiayi Zhu, Haoxuan Peng, Junxi Wang +3
Large language models (LLMs) are commonly prompted and interfaced with human-readable natural language, even when the intended reader is another model. This paper investigates whet…
cs.LG2026
EnvRL: Learn from Environment Dynamics in Agentic Reinforcement Learning
Zhitong Wang, Songze Li, Hao Peng +4
Reinforcement learning (RL) has emerged as a powerful paradigm for training Large Language Models (LLMs) as agents. However, conventional RL methods for long-horizon agentic tasks…
cs.CV2026
Powerful Teachers Matter: Text-Guided Multi-view Knowledge Distillation with Visual Prior Enhancement
Xin Zhang, Jianyang Xu, Hao Peng +5
Knowledge distillation transfers knowledge from large teacher models to smaller students for efficient inference. While existing methods primarily focus on distillation strategies,…