中文
相关论文

相关论文: BUMBLE: Unifying Reasoning and Acting with Vision-…

200 篇论文

Cross-view spatial reasoning is essential for embodied AI, underpinning spatial understanding, mental simulation and planning in complex environments. Existing benchmarks primarily emphasize indoor or street settings, overlooking the unique…

计算机视觉与模式识别 · 计算机科学 2026-01-22 Haotian Xu , Yue Hu , Zhengqiu Zhu , Chen Gao , Ziyou Wang , Junreng Rao , Wenhao Lu , Weishi Li , Quanjun Yin , Yong Li

Bytes form the basis of the digital world and thus are a promising building block for multimodal foundation models. Recently, Byte Language Models (BLMs) have emerged to overcome tokenization, yet the excessive length of bytestreams…

计算与语言 · 计算机科学 2025-02-21 Eric Egli , Matteo Manica , Jannis Born

This report provides an architecture-led analysis of two modern vision-language models (VLMs), Qwen2.5-VL-7B-Instruct and Llama-4-Scout-17B-16E-Instruct, and explains how their architectural properties map to a practical video-to-artifact…

计算机视觉与模式识别 · 计算机科学 2025-12-30 Thomson Tong , Diba Darooneh

We present MobileVLM, a competent multimodal vision language model (MMVLM) targeted to run on mobile devices. It is an amalgamation of a myriad of architectural designs and techniques that are mobile-oriented, which comprises a set of…

计算机视觉与模式识别 · 计算机科学 2024-01-02 Xiangxiang Chu , Limeng Qiao , Xinyang Lin , Shuang Xu , Yang Yang , Yiming Hu , Fei Wei , Xinyu Zhang , Bo Zhang , Xiaolin Wei , Chunhua Shen

A fundamental requirement for real-world robotic deployment is the ability to understand and respond to natural language instructions. Existing language-conditioned manipulation tasks typically assume that instructions are perfectly aligned…

Recent progress in vision language foundation models has shown their ability to understand multimodal data and resolve complicated vision language tasks, including robotics manipulation. We seek a straightforward way of making use of…

机器人学 · 计算机科学 2024-02-06 Xinghang Li , Minghuan Liu , Hanbo Zhang , Cunjun Yu , Jie Xu , Hongtao Wu , Chilam Cheang , Ya Jing , Weinan Zhang , Huaping Liu , Hang Li , Tao Kong

Large multimodal models (LMMs) show strong visual-linguistic reasoning but their capacity for spatial decision-making and action remains unclear. In this work, we investigate whether LMMs can achieve embodied spatial action like human…

Integration of VLM reasoning with symbolic planning has proven to be a promising approach to real-world robot task planning. Existing work like UniDomain effectively learns symbolic manipulation domains from real-world demonstrations,…

机器人学 · 计算机科学 2026-02-10 Haoming Ye , Yunxiao Xiao , Cewu Lu , Panpan Cai

We investigate pneumatic non-prehensile manipulation (i.e., blowing) as a means of efficiently moving scattered objects into a target receptacle. Due to the chaotic nature of aerodynamic forces, a blowing controller must (i) continually…

机器人学 · 计算机科学 2022-07-01 Jimmy Wu , Xingyuan Sun , Andy Zeng , Shuran Song , Szymon Rusinkiewicz , Thomas Funkhouser

Recent advances in multimodal large language models (LLMs) have led to significant progress in understanding, generation, and retrieval tasks. However, current solutions often treat these tasks in isolation or require training LLMs from…

机器学习 · 计算机科学 2025-09-24 Teng Xiao , Zuchao Li , Lefei Zhang

Multimodal large language models (MLLMs) have demonstrated impressive capabilities across various vision-language tasks. However, a generalist MLLM typically underperforms compared with a specialist MLLM on most VL tasks, which can be…

计算机视觉与模式识别 · 计算机科学 2024-07-18 Leyang Shen , Gongwei Chen , Rui Shao , Weili Guan , Liqiang Nie

Task planning and motion planning are two of the most important problems in robotics, where task planning methods help robots achieve high-level goals and motion planning methods maintain low-level feasibility. Task and motion planning…

机器人学 · 计算机科学 2025-11-12 Xiaohan Zhang , Yan Ding , Yohei Hayamizu , Zainab Altaweel , Yifeng Zhu , Yuke Zhu , Peter Stone , Chris Paxton , Shiqi Zhang

As robotic technologies advancing towards more complex multimodal interactions and manipulation tasks, the integration of advanced Vision-Language Models (VLMs) has become a key driver in the field. Despite progress with current methods,…

机器人学 · 计算机科学 2025-03-26 Sheng Wang

The integration of large language models (LLMs) with robotics has significantly advanced robots' abilities in perception, cognition, and task planning. The use of natural language interfaces offers a unified approach for expressing the…

机器人学 · 计算机科学 2024-09-27 Wenhao Yu , Jie Peng , Yueliang Ying , Sai Li , Jianmin Ji , Yanyong Zhang

Humans act with context and intention, with reasoning playing a central role. While internet-scale data has enabled broad reasoning capabilities in AI systems, grounding these abilities in physical action remains a major challenge. We…

机器人学 · 计算机科学 2025-12-11 Peijun Tang , Shangjin Xie , Binyan Sun , Baifu Huang , Kuncheng Luo , Haotian Yang , Weiqi Jin , Jianan Wang

Understanding and modeling human mobility patterns is crucial for effective transportation planning and urban development. Despite significant advances in mobility research, there remains a critical gap in simulation platforms that allow…

人工智能 · 计算机科学 2025-06-30 Yifan Liu , Xishun Liao , Haoxuan Ma , Jonathan Liu , Rohan Jadhav , Jiaqi Ma

In this paper, we propose BeamLLM, a vision-aided millimeter-wave (mmWave) beam prediction framework leveraging large language models (LLMs) to address the challenges of high training overhead and latency in mmWave communication systems. By…

机器学习 · 计算机科学 2025-06-30 Can Zheng , Jiguang He , Guofa Cai , Zitong Yu , Chung G. Kang

Humans excel at performing complex tasks by leveraging long-term memory across temporal and spatial experiences. In contrast, current Large Language Models (LLMs) struggle to effectively plan and act in dynamic, multi-room 3D environments.…

计算机视觉与模式识别 · 计算机科学 2025-12-18 Wenbo Hu , Yining Hong , Yanjun Wang , Leison Gao , Zibu Wei , Xingcheng Yao , Nanyun Peng , Yonatan Bitton , Idan Szpektor , Kai-Wei Chang

Vision-language-action models have advanced robotic manipulation but remain constrained by reliance on the large, teleoperation-collected datasets dominated by the static, tabletop scenes. We propose a simulation-first framework to verify…

机器人学 · 计算机科学 2026-02-06 Wenbo Wang , Fangyun Wei , QiXiu Li , Xi Chen , Yaobo Liang , Chang Xu , Jiaolong Yang , Baining Guo

Robotic systems often face execution failures due to unexpected obstacles, sensor errors, or environmental changes. Traditional failure recovery methods rely on predefined strategies or human intervention, making them less adaptable. This…

机器人学 · 计算机科学 2025-03-24 Faseeh Ahmad , Hashim Ismail , Jonathan Styrud , Maj Stenmark , Volker Krueger