Sealbook / Open source / Desktop & everyday apps

zhaochen0110/Awesome_Think_With_Images

Resources and paper list for "Thinking with Images for LVLMs". This repository accompanies our survey on how LVLMs can leverage visual information for complex reasoning, planning, and generation.

large-vision-language-modelsmultimodal-reasoning-visual-reasoningsurvey-awesome-listthinking-with-images

GitHub ↗Website ↗

License & maintenance

No license stated: by default nobody may reuse the code. Ask the authors before using it in a product.

Last code push 11 days ago.

Similar projects

	Repository	Stars	Language	License	Activity
1	massgravel/Microsoft-Activation-ScriptsOpen-source Windows and Office activator featuring HWID, Ohook, TSforge, and Online KMS activation methods, along with advanced troubleshoot	★ 195k	Batchfile	GPL-3.0	Active
2	clash-verge-rev/clash-verge-revA modern GUI client based on Tauri, designed to run in Windows, macOS and Linux for tailored proxy experience	★ 152.2k	Rust	GPL-3.0	Active
3	microsoft/PowerToysMicrosoft PowerToys is a collection of utilities that supercharge productivity and customization on Windows	★ 139.5k	C	MIT	Active
4	tauri-apps/tauriBuild smaller, faster, and more secure desktop and mobile applications with a web frontend.	★ 112k	Rust	Apache-2.0	Active
5	opendatalab/MinerUTransforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.	★ 82k	Python	Other	Active
6	ventoy/VentoyA new bootable USB solution.	★ 80.2k	C	GPL-3.0	Active
7	docling-project/doclingGet your documents ready for gen AI	★ 69.1k	Python	MIT	Active
8	gorhill/uBlockuBlock Origin - An efficient blocker for Chromium and Firefox. Fast and lean.	★ 68.7k	JavaScript	GPL-3.0	Active