paper-with-me

홈 › Papers

FreeFly-Thinking : Aligning Chain-of-Thought Reasoning with Continuous UAV Navigation

2026-03-07 · Jiaxu Zhou, Shaobo Wang, Zhiyuan Yang, Zhenjun Yu, Tao Li arxiv

Vision-Language Navigation aims to enable agents to understand natural language instructions and carry out appropriate navigation actions in real-world environments. Most work focuses on indoor settings, with little research in complex outdoor scenes. Current UAV Vision-and-Language Navigation models typically act as black boxes without explicit reasoning. We introduce FreeFly-thinking, an end-to-end VLN framework that converts the UAV agent's egocentric images and language instructions into a series of actions, inspired by environment of urban architecture proposed by OpenFly. We first construct a UAV dataset for navigation task, and then performing natural language chain of thought. We adopt a two-stage training strategy: Supervised fine-tuning and Reinforcement fine-tuning. Experiments on unseen test demonstrate a strong performance, presenting robustness and efficiency in UAV navigation issue.

📄 PDF Abstract BibTeX arXiv:2603.07181

Code (0)

등록된 구현이 없습니다.

Tasks

Vision-Language Navigation

Similar Papers 제목 키워드 기반

Rethinking the Chain-of-Thought: The Roles of In-Context Learning and Pre-trained Priors

2025-09-01 · Hao Yang, Zhiyu Yang, Yunjie Zhang, Shanyi Zhu 외 arxiv

Chain-of-Thought reasoning has emerged as a pivotal methodology for enhancing model inference capabilities. Despite growing interest in Chain-of-Thought reasoning, its underlying mechanisms remain unclear. This paper exp…

Prompt EngineeringLogical Reasoning

Beyond Correctness: Benchmarking and Aligning Response Behaviors in Hybrid-Thinking MLLMs

2026-08-13 · Xinming Wang, Weinong Wang, Hongming Yang, Yansong Lin 외 arxiv

Hybrid-thinking multimodal large language models (MLLMs) allow a single model to alternate between deliberative thinking and latency-efficient non-thinking inference. Although these modes differ in reasoning budget, thei…

Reinforcement Learning

MyGO Multiplex CoT: A Method for Self-Reflection in Large Language Models via Double Chain of Thought Thinking

2025-01-20 · Shihao Ji, Zihui Song, Fucheng Zhong, Jisen Jia 외

Recent advancements in large language models (LLMs) have demonstrated their impressive abilities in various reasoning and decision-making tasks. However, the quality and coherence of the reasoning process can still benef…

Decision MakingGSM8KHumanEvalLLM real-life tasks+2

Fast-Slow Thinking RM: Efficient Integration of Scalar and Generative Reward Models

2026-03-02 · Jiayun Wu, Peixu Hou, Shan Qu, Peng Zhang 외 arxiv

Reward models (RMs) are critical for aligning Large Language Models via Reinforcement Learning from Human Feedback (RLHF). While Generative Reward Models (GRMs) achieve superior accuracy through chain-of-thought (CoT) re…

Reinforcement Learning

On the Thinking-Language Modeling Gap in Large Language Models

2025-05-19 · Chenxi Liu, Yongqiang Chen, Tongliang Liu, James Cheng 외

System 2 reasoning is one of the defining characteristics of intelligence, which requires slow and logical thinking. Human conducts System 2 reasoning via the language of thoughts that organizes the reasoning process as …

Language ModelingLanguage Modelling