Showing cs.LGShow all
3 papers · 1 filter
cs.LG2026
Trust Region On-Policy Distillation
Xingrun Xing, Haoqing Wang, Boyan Gao +2
On-Policy Distillation (OPD) is a fundamental technique for efficient post-training of large language models (LLMs), with broad applications in agent learning, multi-task enhanceme…
cs.LG2026
When Should LLMs Reason? Adaptive Inference Routing via Entropy Dynamics
Wei Xia, Haoqing Wang, Zhi-Hong Deng +1
Chain-of-thought (CoT) reasoning can improve LLM performance, but its benefits vary across tasks, models, and individual queries. On some tasks, CoT provides marginal or negative a…
cs.LG2026
MeKi: Memory-based Expert Knowledge Injection for Efficient LLM Scaling
Ning Ding, Fangcheng Liu, Kyungrae Kim +4
Scaling Large Language Models (LLMs) typically relies on increasing the number of parameters or test-time computations to boost performance. However, these strategies are impractic…