Results 281 to 290 of about 488,216 (336)

Grounding Naples: Settings, Zones, Grounds, and Groundings

2023
Degree Show Catalogue documenting the first year of a two-year ESALA MArch (Integrated Pathway) studio, ‘Grounding Naples. Studio Leaders: Chris French and Michael Lewis. 2022-2024.
Chris French, Michael Lewis
openaire   +1 more source

Grounding grounded

2021
This comment on the exchange between Stefan Muller-Doohm/Roman Yos and Fabian Freyenhagen aims to put the debate in the context of the broader question of the relative merits of earlier and later critical theory. I agree withMuller-Doohm and Yosin suggesting that the approaches of Horkheimer and Adorno on the one hand, and Habermas on the other, to ...
openaire   +2 more sources

ScreenSpot-Pro: GUI Grounding for Professional High-Resolution Computer Use

ACM Multimedia
Recent advancements in Multi-modal Large Language Models (MLLMs) have led to significant progress in developing GUI agents for general tasks such as web browsing and mobile phone use.
Kaixin Li, Ziyang Meng, Hongzhan Lin, Ziyang Luo, Yuchen Tian, Jing Ma, Zhiyong Huang, Tat-Seng Chua   +7 more
semanticscholar   +1 more source

LLM-Grounder: Open-Vocabulary 3D Visual Grounding with Large Language Model as an Agent

IEEE International Conference on Robotics and Automation, 2023
3D visual grounding is a critical skill for household robots, enabling them to navigate, manipulate objects, and answer questions based on their environment.
Jianing Yang, Xuweiyi Chen, Shengyi Qian, Nikhil Madaan, Madhavan Iyengar, David F. Fouhey, Joyce Chai   +6 more
semanticscholar   +1 more source

SeeClick: Harnessing GUI Grounding for Advanced Visual GUI Agents

Annual Meeting of the Association for Computational Linguistics
Graphical User Interface (GUI) agents are designed to automate complex tasks on digital devices, such as smartphones and desktops. Most existing GUI agents interact with the environment through extracted structured data, which can be notably lengthy (e.g.
Kanzhi Cheng, Qiushi Sun, Yougang Chu, Fangzhi Xu, Yantao Li, Jianbing Zhang, Zhiyong Wu   +6 more
semanticscholar   +1 more source

LLaVA-Grounding: Grounded Visual Chat with Large Multimodal Models

arXiv.org, 2023
With the recent significant advancements in large multi-modal models (LMMs), the importance of their grounding capability in visual chat is increasingly recognized.
Hao Zhang, Hongyang Li, Feng Li, Tianhe Ren, Xueyan Zou, Shilong Liu, Shijia Huang, Jianfeng Gao, Lei Zhang, Chun-yue Li, Jianwei Yang   +10 more
semanticscholar   +1 more source

Navigating the Digital World as Humans Do: Universal Visual Grounding for GUI Agents

International Conference on Learning Representations
Multimodal large language models (MLLMs) are transforming the capabilities of graphical user interface (GUI) agents, facilitating their transition from controlled simulations to complex, real-world applications across various platforms.
Boyu Gou, Ruohan Wang, Boyuan Zheng, Yanan Xie, Cheng Chang, Yiheng Shu, Huan Sun, Yu Su   +7 more
semanticscholar   +1 more source

Ground squirrels

Current Biology, 2022
Pra et al. provide an overview of ground squirrels and the physiological adaptations these animals have evolved to contend with harsh climates.
Rafael Dai, Pra, Sviatoslav N, Bagriantsev, Elena O, Gracheva   +2 more
openaire   +2 more sources

Grounding Image Matching in 3D with MASt3R

European Conference on Computer Vision
Image Matching is a core component of all best-performing algorithms and pipelines in 3D vision. Yet despite matching being fundamentally a 3D problem, intrinsically linked to camera pose and scene geometry, it is typically treated as a 2D problem.
Vincent Leroy, Yohann Cabon, Jérôme Revaud   +2 more
semanticscholar   +1 more source

MiniCheck: Efficient Fact-Checking of LLMs on Grounding Documents

Conference on Empirical Methods in Natural Language Processing
Recognizing if LLM output can be grounded in evidence is central to many tasks in NLP: retrieval-augmented generation, summarization, document-grounded dialogue, and more. Current approaches to this kind of fact-checking are based on verifying each piece
Liyan Tang, Philippe Laban, Greg Durrett
semanticscholar   +1 more source