tqxli

tsai

Time series Timeseries Deep Learning Machine Learning Python Pytorch fastai | State-of-the-art Deep Learning library for Time Series and Sequences in Pytorch / fastai

SlotFormer

Code release for ICLR 2023 paper: SlotFormer on object-centric dynamics models

poyo

Official Implementation of POYO-1 https://poyo-brain.github.io/

SiT

Official implementation of "Self-slimmed Vision Transformer" (ECCV2022)

evit

Python code for ICLR 2022 spotlight paper EViT: Expediting Vision Transformers via Token Reorganizations

DynamicViT

[NeurIPS 2021] [T-PAMI] DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification

EIT

PyTorch implementation of "Seeing the forest and the tree: Building representations of both individual and collective dynamics with transformers" (NeurIPS 2022)

context_general_bci

Towards large neural data models.

ERDiff

[NeurIPS'23 Spotlight] Official Repo for "Extraction and recovery of spatio-temporal structure in latent dynamics alignment with diffusion models"

MONAI

AI Toolkit for Healthcare Imaging

3D-deformable-attention

[ICCV 2023] Official implementation of the paper "DFA3D: 3D Deformable Attention For 2D-to-3D Feature Lifting"

Swin3D

A shift-window based transformer for 3D sparse tasks

mae

PyTorch implementation of MAE https//arxiv.org/abs/2111.06377

X-Pose

[ECCV 2024] Official implementation of the paper "X-Pose: Detecting Any Keypoints"

Pose-Segment-Anything

Marrying Pose Estimation model with Segment Anything & Stable Diffusion, Automatically Joint Detection , Segment and edit any part of your body.

Track-Anything

Track-Anything is a flexible and interactive tool for video object tracking and segmentation, based on Segment Anything, XMem, and E2FGVI.

Grounded-Segment-Anything

Grounded SAM: Marrying Grounding DINO with Segment Anything & Stable Diffusion & Recognize Anything - Automatically Detect , Segment and Generate Anything

roma

RoMa: A lightweight library to deal with 3D rotations in PyTorch.

joint-vae

Pytorch implementation of JointVAE, a framework for disentangling continuous and discrete factors of variation :star2:

Neuroformer

al-folio

A beautiful, simple, clean, and responsive Jekyll theme for academics

rastermap

a visualization method for neural data

axolotl

Go ahead and axolotl questions

llm-course

Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.

AmadeusGPT

[NeurIPS 2023] We turn natural language descriptions of behaviors into machine-executable code

MultiBench

[NeurIPS 2021] Multiscale Benchmarks for Multimodal Representation Learning

MotionDiffuse

MotionDiffuse: Text-Driven Human Motion Generation with Diffusion Model

MotionGPT

[NeurIPS 2023] MotionGPT: Human Motion as a Foreign Language, a unified motion-language generation model using LLMs

dynamax

State Space Models library in JAX

ssm

Bayesian learning and inference for state space models