ChatBridge, an approach to learning a unified multimodal model to interpret, correlate, and reason about various modalities without relying on all combinations of paired data.

FastComposer: Tuning-Free Multi-Subject Image Generation with Localized Attention

Code for Arxiv 2023: Improving Language Model Negociation with Self-Play and In-Context Learning from AI Feedback

GLM-130B: An Open Bilingual Pre-Trained Model (ICLR 2023)

StableLM: Stability AI Language Models

Codes and Models for VALOR: Vision-Audio-Language Omni-Perception Pretraining Model and Dataset

Inference code for Llama models

Running large language models on a single GPU for throughput-oriented scenarios.

The official repository of our CVPR2023 paper "FFHQ-UV: Normalized Facial UV-Texture Dataset for 3D Face Reconstruction".

Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities

Awesome multilingual OCR toolkits based on PaddlePaddle (practical ultra lightweight OCR system, support 80+ languages recognition, provide data annotation and synthesis tools, support training and…

METER: A Multimodal End-to-end TransformER Framework

Counterfactual Samples Synthesizing for Robust VQA

PyTorch implementation of "Debiased Visual Question Answering from Feature and Sample Perspectives" (NeurIPS 2021)

Official Implementation of Information Theoretic Counterfactual Learning from Missing Not At Random Feedback. NeurIPS 2020.

Code for the ICML 2021 (long talk) paper: "ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision"

The pure and clear PyTorch Distributed Training Framework.

Slicing a PyTorch Tensor Into Parallel Shards

The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (V…

[NeurIPS 2020] "The Lottery Ticket Hypothesis for Pre-trained BERT Networks", Tianlong Chen, Jonathan Frankle, Shiyu Chang, Sijia Liu, Yang Zhang, Zhangyang Wang, Michael Carbin

やり直すんだ。そして、次はうまくやる。

关于domain generalization，domain adaptation，causality，robutness，prompt，optimization，generative model各式各样研究的阅读笔记

Pretrain, finetune and deploy AI models on multiple GPUs, TPUs with zero code changes.

Repo for ICCV 2021 paper: Beyond Question-Based Biases: Assessing Multimodal Shortcut Learning in Visual Question Answering

Code for Greedy Gradient Ensemble for Visual Question Answering （ICCV 2021, Oral）

A curated list of awesome work on causal inference, particularly in machine learning.

[ICLR 2022] code for "How Much Can CLIP Benefit Vision-and-Language Tasks?" https://arxiv.org/abs/2107.06383