-
Bristol Myers Squibb
- Cambridge, MA
- https://scholar.google.com/citations?user=73JdVH0AAAAJ
- @huhlim
- in/lim-heo-889b5ba4
Stars
AlphaFold Meets Flow Matching for Generating Protein Ensembles
Predict multiple protein conformations using sequence clustering and AlphaFold2.
Improved protein complex prediction with AlphaFold-multimer by denoising the MSA profile
Fast protein backbone generation with SE(3) flow matching.
Making Protein Design accessible to all via Google Colab!
Geometric Latent Diffusion Models for 3D Molecule Generation
A natural language interface for computers
🚀🎬 ShortGPT - Experimental AI framework for youtube shorts / tiktok channel automation
Convert coarse-grained protein structure to all-atom model
Demo of diffusion models #DDPM applied to molecular dynamics of small peptide
An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.
Codes for "Chameleon: Plug-and-Play Compositional Reasoning with Large Language Models".
A Collection of Variational Autoencoders (VAE) in PyTorch.
Portable file system cache diagnostics and control
Differentiable ODE solvers with full GPU support and O(1)-memory backpropagation.
Differentiable SDE solvers with GPU support and efficient sensitivity analysis.
🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch and FLAX.
High-speed download of LLaMA, Facebook's 65B parameter GPT model
Implementation for SE(3) diffusion model with application to protein backbone generation
GearNet and Geometric Pretraining Methods for Protein Structure Representation Learning, ICLR'2023 (https://arxiv.org/abs/2203.06125)
Diffusion models of protein structure; trigonometry and attention are all you need!
The Pytorch Tutorial of Score-based and Diffusion Model
State-of-the-Art Deep Learning scripts organized by models - easy to train and deploy with reproducible accuracy and performance on enterprise-grade infrastructure.
Denoising diffusion probabilistic models for replica exchange
NequIP is a code for building E(3)-equivariant interatomic potentials