Stars
[ICLR 2026] Official repository for "Real-3DQA"
Efficient Universal Perception Encoder: a single on-device vision encoder with versatile representations that match or exceed specialized experts across multiple task domains.
A Simple and Universal Swarm Intelligence Engine, Predicting Anything. 简洁通用的群体智能引擎，预测万物
VGGT-SLAM: Dense RGB SLAM Optimized on the SL(4) Manifold
[RA-L'25] An Reliable and Efficient Framework for Zero-Shot Object Navigation
🏠 Ask Claude about Korean apartment prices — powered by 국토교통부 open API
Use Codex from Claude Code to review code or delegate tasks.
Korean SAT leader board
An in-the-wild benchmark for AI agents in the OpenClaw Environment.
"ClawWork: OpenClaw as Your AI Coworker - 💰 $15K earned in 11 Hours"
Official PyTorch implementation of CVPR'26 paper "Unleashing Vision-Language Semantics for Deepfake Video Detection".
Code Implementation of "WorldCam: Interactive Autoregressive 3D Gaming Worlds with Camera Pose as a Unifying Geometric Representation"
한국인을 위한 스킬 모음집 - SRT, KTX, KBO, 카카오톡, 한글과 컴퓨터, 미세먼지, 우편번호, 블루리본 등등...
a minimal, beginner-friendly VLA to show how robot policies can fuse images, text, and states to generate actions
A light-weight and powerful meta-prompting, context engineering and spec-driven development system for Claude Code by TÂCHES.
A diffusion-based framework for document OCR that replaces autoregressive decoding with block-level parallel diffusion decoding.
OpenResearcher: A Fully Open Pipeline for Long-Horizon Deep Research Trajectory Synthesis
🦞 Just talk to your agent — it learns and EVOLVES 🧬.
Show usage stats for OpenAI Codex and Claude Code, without having to login.
Toolkit for linearizing PDFs for LLM datasets/training
AutoGaze automatically removes redundant patches in a video, reducing #tokens in ViT/MLLM by 4x-100x.
Transforms complex documents like PDFs into LLM-ready markdown/JSON for your Agentic workflows.
PDF Parser for AI-ready data. Automate PDF accessibility. Open-source.