-
Digital Image Media Lab
- Seoul, South Korea
-
06:16
(UTC -12:00) - https://genie-kim.github.io/
Highlights
- Pro
Stars
Official Repo For OMG-LLaVA and OMG-Seg codebase [CVPR-24 and NeurIPS-24]
Natural language team builder for Claude Code Agent Teams โ create purpose-driven AI teams with a single sentence
A Claude Code plugin that makes Opus behave like Fable โ completion, evidence, and verification enforced as procedure. Ships only what a Fable-vs-Opus comparison proved transferable.
Official repository for the paper "Towards Comprehensive Scene Understanding: Integrating First and Third-Person Views for LVLMs" (NeurIPS 2025 Spotlight)
[ICLR 2026] "VTool-R1: VLMs Learn to Think with Images via Reinforcement Learning on Multimodal Tool Use"
Hierarchical Reasoning Model Official Release
One local control plane for every AI agent: route across models, fuse new capabilities, orchestrate tools, and stay fully in control.
Real-time Claude Code usage monitor with predictions and warnings
๐ฟ 17K+ Company-wise LeetCode Interview Questions. Filter by topic, difficulty. WIP Local code execution engine.
Lists of company wise questions. Every csv file in the companies directory corresponds to a list of questions on leetcode for a specific company based on the leetcode company tags. Updated as of 20โฆ
This repository contains the replication package for the paper "How Much is Unseen Depends Chiefly on Information About the Seen," accepted at the ICLR 2025 conference as a spotlight paper.
OpenHealth, AI Health Assistant | Powered by Your Data
100+ AI Agents, Agent Skills and RAG Apps - Free and Open Source.
A deep dive on the history of robotics and the future of humanoids
A PyTorch library for implementing flow matching algorithms, featuring continuous and discrete flow matching implementations. It includes practical examples for both text and image modalities.
AlphaFold 3 inference pipeline.
Create pre-defined window/pane layouts and run commands in iTerm
Naver Search Workflow for Alfred (์ํ๋ ๋ ๋ค์ด๋ฒ ๊ฒ์/์ฌ์ /์ง๋ ์๋์์ฑ ์ํฌํ๋ก์ฐ)
Code and Data for Paper: SELMA: Learning and Merging Skill-Specific Text-to-Image Experts with Auto-Generated Data
[๐๐๐๐๐ ๐ ๐ข๐ง๐๐ข๐ง๐ ๐ฌ ๐๐๐๐ & ๐๐๐ ๐๐๐๐ ๐๐๐๐๐ ๐๐ซ๐๐ฅ] ๐๐ฏ๐ฉ๐ข๐ฏ๐ค๐ช๐ฏ๐จ ๐๐ข๐ต๐ฉ๐ฆ๐ฎ๐ข๐ต๐ช๐ค๐ข๐ญ ๐๐ฆ๐ข๐ด๐ฐ๐ฏ๐ช๐ฏ๐จ ๐ช๐ฏ ๐๐ข๐ฏ๐จ๐ถ๐ข๐จ๐ฆ ๐๐ฐ๐ฅ๐ฆ๐ญ๐ด ๐ธ๐ช๐ต๐ฉ ๐๐ช๐ฏ๐ฆ-๐จ๐ณ๐ข๐ช๐ฏ๐ฆ๐ฅ ๐๐ฆ๐ธ๐ข๐ณ๐ฅ๐ด
A collection of resources on controllable generation with text-to-image diffusion models.