chanhee-luke

M-Track

Code for CVPR22 paper One Step at a Time: Long-Horizon Vision-and-Language Navigation with Milestones

BPE_PMI

Byte Pair Encoding with Pointwise Mutual Information

Recurrent-VLN-BERT

Code of the CVPR 2021 Oral paper: A Recurrent Vision-and-Language BERT for Navigation

6341-Luke-Song

CSE 6341 publicly available code

alexa-arena

alfred

ALFRED - A Benchmark for Interpreting Grounded Instructions for Everyday Tasks

alfworld

ALFWorld: Aligning Text and Embodied Environments for Interactive Learning

allennlp

An open-source NLP research library, built on PyTorch.

awesome-language-agents

List of language agents based on paper "Cognitive Architectures for Language Agents"

chanhee-luke.github.io

embert

Code for EmBERT, a transformer model for embodied, language-guided visual task completion.

hlsm

ChatGPT-Next-Web

A cross-platform ChatGPT/Gemini UI (Web / PWA / Linux / Win / MacOS). 一键拥有你自己的跨平台 ChatGPT/Gemini 应用。

CodeT5

Home of CodeT5: Open Code LLMs for Code Understanding and Generation

JARVIS

JARVIS, a system to connect LLMs with ML community. Paper: https://arxiv.org/pdf/2303.17580.pdf

Mandelbrot-Browser

Quick mandelbrot browser/generator

Mewthree

Pokemon Showdown Bot

odex

Execution-Based Evaluation for Open Domain Code Generation

OpenNMT-py

Open Source Neural Machine Translation in PyTorch

pytorch_lstmcrf

Pytorch implementation of LSTM-CRF for named entity recognition

reflexion

Reflexion: Language Agents with Verbal Reinforcement Learning

RESIDE

EMNLP 2018: RESIDE: Improving Distantly-Supervised Neural Relation Extraction using Side Information

Sandbox

Personal NLP research platform

scibert

A BERT model for scientific text.

Swin-Transformer

This is an official implementation for "Swin Transformer: Hierarchical Vision Transformer using Shifted Windows".

TaskMatrix

teach

TEACh is a dataset of human-human interactive dialogues to complete tasks in a simulated household environment.

text

Data loaders and abstractions for text and NLP

Video-LLaMA

Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding

virtualhome_aug

API to run VirtualHome, a Multi-Agent Household Simulator