4 papers
ESPO: Early-Stopping Proximal Policy Optimization
Zihang Li, Rui Zhou, Yingcheng Shi +8
When a large language model under reinforcement learning commits a wrong reasoning step early in a trajectory, standard algorithms force it to keep generating until the maximum hor…
Bridge-RAG: An Abstract Bridge Tree Based Retrieval Augmented Generation Algorithm
Zihang Li, Wenjun Liu, Yikun Zong +7
As an important paradigm for enhancing the generation quality of Large Language Models (LLMs), retrieval-augmented generation (RAG) faces the two challenges regarding retrieval acc…
A1: A Fully Transparent Open-Source, Adaptive and Efficient Truncated Vision-Language-Action Model
Kaidong Zhang, Jian Zhang, Rongtao Xu +20
Vision-Language-Action (VLA) models have emerged as a powerful paradigm for open-world robot manipulation, but their practical deployment is often constrained by cost: billion-scal…
VisualRWKV-HD and UHD: Advancing High-Resolution Processing for Visual Language Models
Zihang Li, Haowen Hou
Accurately understanding complex visual information is crucial for visual language models (VLMs). Enhancing image resolution can improve visual perception capabilities, not only re…