MAI-UI: Real-World Centric Foundation GUI Agents ranging from 2B to 235B

Benchmarking Autonomous Mobile Agents in Agent-User Interactive and MCP-Augmented Environments

Allegro is a powerful text-to-video model that generates high-quality videos up to 6 seconds at 15 FPS and 720p resolution from simple text input.

Codebase for Aria - an Open Multimodal Native MoE

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

PyRCA: A Python Machine Learning Library for Root Cause Analysis

CodeTF: One-stop Transformer Library for State-of-the-art Code LLM

Home of StarCoder: fine-tuning & inference!

LAVIS - A One-stop Library for Language-Vision Intelligence

This is the official code for the paper CodeRL: Mastering Code Generation through Pretrained Models and Deep Reinforcement Learning (NeurIPS22).

APPS: Automated Programming Progress Standard (NeurIPS 2021)

PyTorch code for BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation

A collection of recent papers, benchmarks and datasets of AI4Code domain.

methods2test is a supervised dataset consisting of Test Cases and their corresponding Focal Methods from a set of Java software repositories

Pre-Trained Models for ToD-BERT

Merlion: A Machine Learning Framework for Time Series Intelligence

Code for ALBEF: a new vision-language pre-training method

Graphormer is a general-purpose deep learning backbone for molecular modeling.

This repository maintains the QAConv dataset, a question-answering dataset on informative conversations including business emails, panel discussions, and work channels.

Recent Advances in Programming Language Pre-Trained Models (PL-PTMs)

Code for ICML 2021 paper: How could Neural Networks understand Programs?

Official code of our work, Unified Pre-training for Program Understanding and Generation [NAACL 2021].

Implementation of the paper "Language-agnostic representation learning of source code from structure and context".

CodeBERT

Multi Task Vision and Language

CodeBERT

CodeXGLUE

[EMNLP 2020] Discern: Discourse-Aware Entailment Reasoning Network for Conversational Machine Reading