Pengzhi Gao

Xiaomi-GUI-0. [Technical Report] An End-to-End Multimodal GUI Agent for Real Mobile Environments

ScaleWoB.github.io. ScaleWoB: Scalable world-of-bit that revolutionizes the evaluation of Computer-Use Agents.

mobilegym. MobileGym: A Verifiable and Highly Parallel Simulation Platform for Mobile GUI Agent Research · 浏览器里运行的安卓模拟器 · Browser-hosted Android Simulator · Verifiable Evaluation · Scalable Online RL Training

controlfoley. ControlFoley: Unified and Controllable Video-to-Audio Generation with Cross-Modal Conflict Handling

svor. SVOR - Stable Video Object Removal

mecat. Python

awesome-world-models-for-digital-agents. Digital Agents Meet World Models: A Survey

claude-code-py. Build Claude Code From Scratch in Python

gWorld. Generative Visual Code Mobile World Model

Awesome-GUI-World-Model. A curated list of papers and resources for GUI world models.

MobileWorld. Benchmarking Autonomous Mobile Agents in Agent-User Interactive and MCP-Augmented Environments (ACL 2026)

MiroThinker. MiroThinker is a deep research agent optimized for complex research and prediction tasks. Our latest models, MiroThinker-1.7, achieves 74.0 and 75.3 on the BrowseComp and BrowseComp Zh, respectively.

verl. verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework

Open-AutoGLM. An Open Phone Agent Model & Framework. Unlocking the AI Phone for Everyone

dr-tulu. Official repository for DR Tulu: Reinforcement Learning with Evolving Rubrics for Deep Research

guievalkit. [ICML 2026] GUIEvalKit: Open-source Evaluation Toolkit for GUI Agents

gemmax. Gemma-based Multilingual Machine Translation Models

fineweb-2. Python

DeepSeek-R1.

UI-TARS. Pioneering Automated GUI Interaction with Native Agents

GUI-Agents-Paper-List. Awesome GUI Agent Paper List

Simul-LLM. [ACL 2024] An easily extensible framework for simultaneous, text-to-text neural machine translation (SimulMT) for LLMs.

AI-Scientist. The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery 🧑‍🔬

LLM101n. LLM101n: Let's build a Storyteller

LLMs-from-scratch. Implement a ChatGPT-like LLM in PyTorch from scratch, step by step

DeepSeek-V2. DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model

vllm. A high-throughput and memory-efficient inference and serving engine for LLMs

texar. Toolkit for Machine Learning, Natural Language Processing, and Text Generation, in TensorFlow. This is part of the CASL project: http://casl-project.ai/

LlamaFactory. Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

wmt23-news-systems. Ruby

CrossConST-LLM. Code for arXiv paper "Towards Boosting Many-to-Many Multilingual Machine Translation with Large Language Models"

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

Yi. A series of large language models trained from scratch by developers @01-ai

ALMA. State-of-the-art LLM-based translation models.

Baichuan2. A series of large language models developed by Baichuan Intelligent Technology

llama-cookbook. Welcome to the Llama Cookbook! This is your go to guide for Building with Llama: Getting started with Inference, Fine-Tuning, RAG. We also show you how to solve end to end problems using Llama model family and using them on various provider services

SimCR. Code for NAACL 2024 main conference paper "An Empirical Study of Consistency Regularization for End-to-End Speech-to-Text Translation"

GPT-4-LLM. Instruction Tuning with GPT-4

awesome-instruction-dataset. A collection of open-source dataset to train instruction-following LLMs (ChatGPT,LLaMA,Alpaca)

seamless_communication. Foundational Models for State-of-the-Art Speech and Text Translation

Qwen. The official repo of Qwen (通义千问) chat & pretrained large language model proposed by Alibaba Cloud.

llama. Inference code for Llama models

Awesome-LLM. Awesome-LLM: a curated list of Large Language Model

Baichuan-13B. A 13B large language model developed by Baichuan Intelligent Technology

whisper. Robust Speech Recognition via Large-Scale Weak Supervision

Baichuan-7B. A large-scale 7B pretraining language model developed by BaiChuan-Inc.

CrossConST-SR. Code for EMNLP 2023 industry track paper "Learning Multilingual Sentence Representations with Cross-lingual Consistency Regularization"

CrossConST-MT. Code for Findings of ACL 2023 paper "Improving Zero-shot Multilingual Neural Machine Translation by Leveraging Cross-lingual Consistency Regularization"

codon. A high-performance, zero-overhead, extensible Python compiler with built-in NumPy support

nextai-translator. 基于 ChatGPT API 的划词翻译浏览器插件和跨平台桌面端应用 - Browser extension and cross-platform desktop application for translation based on ChatGPT API.

CTranslate2. Fast inference engine for Transformer models

fastText. Library for fast text representation and classification.

Bi-SimCut. Code for NAACL 2022 main conference paper "Bi-SimCut: A Simple Strategy for Boosting Neural Machine Translation"

subword-nmt. Unsupervised Word Segmentation for Neural Machine Translation and Text Generation

rebiber. A simple tool to update bib entries with their official information (e.g., DBLP or the ACL anthology).

slideslive-slides-dl. slideslive slides downloading script

MASS. MASS: Masked Sequence to Sequence Pre-training for Language Generation

visual-pivoting. [EMNLP 2020] Using Visual Feature Space as a Pivot Across Languages

Cutoff. The source code for the Cutoff data augmentation approach proposed in this paper: "A Simple but Tough-to-Beat Data Augmentation Approach for Natural Language Understanding and Generation".

R-Drop. Python

VTLM. Cross-lingual Visual Pre-training for Multimodal Machine Translation

adaptdl. Resource-adaptive cluster scheduler for deep learning training.

SpeechTransProgress. Tracking the progress in end-to-end speech translation

sentencepiece. Unsupervised text tokenizer for Neural Network-based text generation.

flores. Facebook Low Resource (FLoRes) MT Benchmark

langid.py. Stand-alone language identification system

sentence-transformers. State-of-the-Art Embeddings, Retrieval, and Reranking

TextAttack. TextAttack 🐙 is a Python framework for adversarial attacks, data augmentation, and model training in NLP https://textattack.readthedocs.io/en/master/

TAADpapers. Must-read Papers on Textual Adversarial Attack and Defense

data_diversification. Instruction to data diversification

TRADES. TRADES (TRadeoff-inspired Adversarial DEfense via Surrogate-loss minimization)

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

tokenizers. 💥 Fast State-of-the-Art Tokenizers optimized for Research and Production

models. Officially maintained, supported by PaddlePaddle, including CV, NLP, Speech, Rec, TS, big models and so on.

XLM. PyTorch original implementation of Cross-lingual Language Model Pretraining.

fairseq. Facebook AI Research Sequence-to-Sequence Toolkit written in Python.

ai-deadlines. :alarm_clock: AI conference deadline countdowns

lowresource-nlp-bootcamp-2020. The website for the CMU Language Technologies Institute low resource NLP bootcamp 2020

MT-Reading-List. A machine translation reading list maintained by Tsinghua Natural Language Processing Group

Deep-Learning-Interview-Book. 深度学习面试宝典（含数学、机器学习、深度学习、计算机视觉、自然语言处理和SLAM等方向）

nlptutorial. A Tutorial about Programming for Natural Language Processing

aaai_tutorial. This site holds materials of the AAAI 2020 Tutorial on Modularizing Natural Language Processing

stave. An extensible framework for building visualization and annotation tools to enable better interaction with NLP and Artificial Intelligence. This is part of the CASL project: http://casl-project.ai/

academicpages.github.io. Github Pages template based upon HTML and Markdown for personal, portfolio-based websites.

texar-pytorch. Integrating the Best of TF into PyTorch, for Machine Learning, Natural Language Processing, and Text Generation. This is part of the CASL project: http://casl-project.ai/

forte. Forte is a flexible and powerful ML workflow builder. This is part of the CASL project: http://casl-project.ai/

transformers. 🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

markdown-here. Google Chrome, Firefox, and Thunderbird extension that lets you write email in Markdown and render it before sending.

pytorch-examples. Simple examples to introduce PyTorch

xgboost. Scalable, Portable and Distributed Gradient Boosting (GBDT, GBRT or GBM) Library, for Python, R, Java, Scala, C++ and more. Runs on single machine, Hadoop, Spark, Dask, Flink and DataFlow

LightGBM. A fast, distributed, high performance gradient boosting (GBT, GBDT, GBRT, GBM or MART) framework based on decision tree algorithms, used for ranking, classification and many other machine learning tasks.