avijit9

Prompt-Engineering-Guide

🐙 Guides, papers, lecture, notebooks and resources for prompt engineering

typst

A new markup-based typesetting system that is powerful and easy to learn.

Open-Sora

Open-Sora: Democratizing Efficient Video Production for All

Grounded-Segment-Anything

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

langchain-tutorials

Overview and tutorial of the LangChain Library

LLaMA-Adapter

[ICLR 2024] Fine-tuning LLaMA to follow Instructions within 1 Hour and 1.2M Parameters

GroundingDINO

Official implementation of the paper "Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection"

GraphGPT

Extrapolating knowledge graphs from unstructured text using GPT-3 🕵️‍♂️

lovely-tensors

Tensors, ready for human consumption

pytorch-i3d

LLaMA-VID

Official Implementation for LLaMA-VID: An Image is Worth 2 Tokens in Large Language Models

dr-doc-search

Converse with book - Built with GPT-3

awesome-test-time-adaptation

Collection of awesome test-time (domain/batch/instance) adaptation methods

motpy

Library for tracking-by-detection multi object tracking implemented in python

LaViLa

Code release for "Learning Video Representations from Large Language Models"

Llama2RAG

A working example of RAG using LLama 2 70b and Llama Index

Ego4d

Ego4d dataset repository. Download the dataset, visualize, extract features & example usage of the dataset

hand_object_detector

Project and dataset webpage:

laughter-detection

efficient-video-recognition

TSP

TSP: Temporally-Sensitive Pretraining of Video Encoders for Localization Tasks (ICCVW 2021)

awesome-video-domain-adaptation

A comprehensive collection of awesome research and other items about video domain adaptation

bc-emb

Building-and-Evaluating-Advanced-RAG-Applications

Jupyter notebooks for course Building and Evaluating Advanced RAG Applications, taught by Jerry Liu (Co-founder and CEO of LlamaIndex) and Anupam Datta (Co-founder and chief scientist of TruEra).

EgoProceL-egocentric-procedure-learning

Code implementation for our ECCV, 2022 paper titled "My View is the Best View: Procedure Learning from Egocentric Videos"

CO2A

verb_ambiguity

Official implementation of "An Action Is Worth Multiple Words: Handling Ambiguity in Action Recognition", BMVC 2022

GeoNet

Repository for accessing and training using GeoNet dataset, published at CVPR 2023.

epic_kitchens_affordances

CAST