One-to-Few Label Assignment for End-to-End Dense Detection (CVPR2023)

Learnable latent embeddings for joint behavioral and neural analysis - Official implementation of CEBRA

The source code of SPN-V2

Adapting Meta AI's Segment Anything to Downstream Tasks with Adapters and Prompts

A curated list of practical guide resources of LLMs (LLMs Tree, Examples, Papers)

MTL-TabNet: Multi-task Learning based Model for Image-based Table Recognition

AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.

Code for loralib, an implementation of "LoRA: Low-Rank Adaptation of Large Language Models"

The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.

Pretraining with Natural and Synthetic Data for Few-shot Table-based Question Answering

Official Implementation of OCR-free Document Understanding Transformer (Donut) and Synthetic Document Generator (SynthDoG), ECCV 2022

[CVPR' 22] Towards Robust Adaptive Object Detection under Noisy Annotations

A collection of original, innovative ideas and algorithms towards Advanced Literate Machinery. This project is maintained by the OCR Team in the Language Technology Lab, Tongyi Lab, Alibaba Group.

BELLE: Be Everyone's Large Language model Engine（开源中文对话大模型）

A curated list of reinforcement learning with human feedback resources (continually updated)

YOLOX is a high-performance anchor-free YOLO, exceeding yolov3~v5 with MegEngine, ONNX, TensorRT, ncnn, and OpenVINO supported. Documentation: https://yolox.readthedocs.io/

AdelaiDet is an open source toolbox for multiple instance-level detection and recognition tasks.

Resources of deep learning for mathematical reasoning (DL4MATH).

A full-fledged version of Pix2Seq

Simple Implementation of Pix2Seq model for object detection in PyTorch

Pix2Seq codebase: multi-tasks with generative modeling (autoregressive and diffusion)

PyTorch implementation of Multi-Label Image Recognition with Graph Convolutional Networks, CVPR 2019.

Making large AI models cheaper, faster and more accessible

DocLayNet: A Large Human-Annotated Dataset for Document-Layout Analysis

Foundation Architecture for (M)LLMs

[CVPR 2021] Instance Localization for Self-supervised Detection Pretraining

[NeurIPS 2021 Spotlight] Aligning Pretraining for Detection via Object-Level Contrastive Learning

Implementations of few-shot object detection benchmarks