papers

Publications (7)

cs.CL2024

Strengthened Symbol Binding Makes Large Language Models Reliable Multiple-Choice Selectors

Mengge Xue, Zhenyu Hu, Liqun Liu +5

Multiple-Choice Questions (MCQs) constitute a critical area of research in the study of Large Language Models (LLMs). Previous works have investigated the selection bias problem in…

cs.RO2026

Behavior Foundations for Quadruped Robots: ABot-C0 Technical Report

Xufeng Zhao, Fuzhi Yang, Jianhui Chen +17

The motion controller is one of the most fundamental modules in embodied intelligence systems. Driven by large-scale human motion-capture data and the motion-tracking paradigm, hum…

cs.CV2026

ABot-N1: Toward a General Visual Language Navigation Foundation Model

Ruiyan Gong, Yingnan Guo, Junjun Hu +44

The paper presents ABot-N1, a visual‑language navigation foundation model that separates high‑level reasoning from low‑level control via a slow‑fast architecture and pixel‑based go…

#visual language navigation#embodied AI#foundation models#chain-of-thought reasoning
cs.RO2026

ABot-N0: Technical Report on the VLA Foundation Model for Versatile Embodied Navigation

Zedong Chu, Shichao Xie, Xiaolong Wu +41

Embodied navigation has long been fragmented by task-specific architectures. We introduce ABot-N0, a unified Vision-Language-Action (VLA) foundation model that achieves a ``Grand U…

cs.AI2026

ABot-AgentOS: A General Robotic Agent OS with Lifelong Multi-modal Memory

Jiayi Tian, Shiao Liu, Yuting Xu +31

The paper introduces ABot-AgentOS, a general operating system layer for robotic agents that adds deliberative planning, multi‑modal memory, verification, and cloud‑edge collaborati…

#embodied ai#robotic agent operating system#multi-modal memory#long-horizon tasks
cs.CL2024

Enhancing Reinforcement Learning with Label-Sensitive Reward for Natural Language Understanding

Kuo Liao, Shuang Li, Meng Zhao +5

Recent strides in large language models (LLMs) have yielded remarkable performance, leveraging reinforcement learning from human feedback (RLHF) to significantly enhance generation…