- South Korea
-
10:15
(UTC +09:00) - http://cold-young.github.io
- in/chanyoung-ahn-868ab2283
Highlights
- Pro
Stars
A meta-skill that designs domain-specific agent teams, defines specialized agents, and generates the skills they use.
This repository presents a comprehensive solution to the hand-eye calibration problem, a fundamental challenge in robotics and computer vision. Hand-eye calibration is critical for applications req…
AFUN: Towards an Affordance Foundation Model for Functionality Understanding
👶🏻 신입 개발자 전공 지식 & 기술 면접 백과사전 📖
URDF & MuJoCo MJCF distribution of the KISTAR Hand family - PRIME Lab
Your agent writes bad React. This catches it
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.
This is a official code for the benchmark of the paper "VTDexManip: A Dataset and Benchmark for Visual-tactile Pretraining and Dexterous Manipulation with Reinforcement Learning" (ICLR 2025)
[CVPR'2024] "SkillDiffuser: Interpretable Hierarchical Planning via Skill Abstractions in Diffusion-Based Task Execution"
Official codebase for PRESTO (Planning with Environment Representation, Sampling, and Trajectory Optimization)
Awesome list for AI agent harness engineering: tools, patterns, evals, memory, MCP, permissions, observability, and orchestration.
A generative and self-guided robotic agent that endlessly propose and master new skills.
EgoVerse: Egocentric Data for Robot Learning from Around the World
A collection of notebooks/recipes showcasing some fun and effective ways of using Claude.
Specialized encoders for robot manipulation. Sparsh-Skin An encoder tailored for magnetic tactile sensors to understand interactions from dexterous hands.Sparsh-X A fusion encoder that combines mul…
NVIDIA Isaac GR00T N1.7 - A Foundation Model for Generalist Robots.
Convert any PDF into a podcast episode!
RoTO is an open-source Reinforcement Learning benchmark environment designed to standardise and promote future research in tactile-based manipulation.
Official implementation of "SIM1: Physics-Aligned Simulator as Zero-Shot Data Scaler in Deformable Worlds "
Papers from the computer science community to read and discuss.