Jongmin Lee's repositories
SO3_EquiPose
3D Equivariant Pose Regression via Direct Wigner-D Harmonics Prediction (NeurIPS 2024)
ace
[CVPR 2023 - Highlight] Accelerated Coordinate Encoding (ACE): Learning to Relocalize in Minutes using RGB and Poses
academicpages.github.io
Github Pages template for academic personal websites, forked from mmistakes/minimal-mistakes
AgentLaboratory
Agent Laboratory is an end-to-end autonomous research workflow meant to assist you as the human researcher toward implementing your research ideas
Awesome-Gaze-Estimation
Awesome Curated List of Eye Gaze Estimation Paper
Awesome-Generalist-Robots-via-Foundation-Models
Paper list in the survey paper: Toward General-Purpose Robots via Foundation Models: A Survey and Meta-Analysis
benchmark_sparse
Benchmarking various sparse convolution libraries: MinkowskiEngine, SpConv, TorchSparse, and Open3D.
browser-use
Make websites accessible for AI agents
Burstormer
SOTA for Burst Super-resolution, Low-light Burst Image Enhancement, Burst Image De-noising
d2go
D2Go is a toolkit for efficient deep learning
deep-research
An AI-powered research assistant that performs iterative, deep research on any topic by combining search engines, web scraping, and large language models. The goal of this repo is to provide the simplest implementation of a deep research agent - e.g. an agent that can refine its research direction overtime and deep dive into a topic.
equiadapt
Library to make any existing neural network architecture equivariant
equivariant-preintegration
A C++ header-only Eigen-based Library for equivariant Inertial Measurement Unit (IMU) preintegration
fast-equivariant-deconv
[Neurips 2024] This repository is the official implementation of the Spatio-hemispherical equivariant convolution for dMRI deconvolution paper presented at Neurips 2024..
Genesis
A generative world for general-purpose robotics & embodied AI learning.
glomap
GLOMAP - Global Structured-from-Motion Revisited
imc2023-kornia-starter-pack
Simple jupyter notebook for 3D reconstruction using kornia and pycolmap
KoLLaVA
KoLLaVA: Korean Large Language-and-Vision Assistant (feat.LLaVA)
ml-fastvit
This repository contains the official implementation of the research paper, "FastViT: A Fast Hybrid Vision Transformer using Structural Reparameterization"
Qwen2-VL
Qwen2-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.
rotation-steerers
A steerer for D-dimensional keypoint descriptions is a DxD matrix that transforms the descriptions as if they were computed from a rotated image.
RotationNormFlow
Official code for "Delving into Discrete Normalizing Flows on SO(3) Manifold for Probabilistic Rotation Modeling" (CVPR 2023)
U-ARE-ME
Uncertainty-Aware Rotation Estimation in Manhattan Environments using only monocular cues.
xtuner
An efficient, flexible and full-featured toolkit for fine-tuning LLM (InternLM2, Llama3, Phi3, Qwen, Mistral, ...)