[ICLR'25] The first benchmark aiming to evaluate whether LMMs can assist oracle bone inscription processing tasks

360LayoutAnaylsis, a series Document Analysis Models and Datasets deleveped by 360 AI Research Institute

A universal Stable-Diffusion toolbox

Official Repo for Open-Reasoner-Zero

This repository collects awesome survey, resource, and paper for lifelong learning LLM agents

✔（已完结）最全面的 深度学习 笔记【土堆 Pytorch】【李沐 动手学深度学习】【吴恩达 深度学习】

DeepSeek 系列工作解读、扩展和复现。

Qwen2.5-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.

A novel Multimodal Large Language Model (MLLM) architecture, designed to structurally align visual and textual embeddings.

大模型基础: 一文了解大模型基础知识

DeepSeek-VL: Towards Real-World Vision-Language Understanding

A synthetic data generator for text recognition

SpaDiT: Diffusion Transformer for Spatial Gene Expression Prediction using scRNA-seq

Rectified Flow diffusion model in a tiny size

This is the implement code for Robot Garment Action Diffusion

Official PyTorch Implementation of "Scalable Diffusion Models with Transformers"

From Scratch: ResNet, MobileNetV2, Transformers, DDPM, DDIM

The official D2 plugin for Obsidian. D2 is a modern diagram scripting language thats turns text to diagrams.

[AAAI2025 Oral] Predicting the Original Appearance of Damaged Historical Documents

[CVPR2024] Diffusion-based Blind Text Image Super-Resolution (Official)

跨性别相关资源列表

A collection of reflection removal methods

[NAACL 2024] Visually Guided Generative Text-Layout Pre-training for Document Intelligence

Scaling Properties of Diffusion Models For Perceptual Tasks

DocReal: Robust Document Dewarping of Real-Life Images via Attention-Enhanced Control Point Prediction

[ICCV 2023] A latent space for stochastic diffusion models

Dual Diffusion Implicit Bridges for Image-to-Image Translation. ICLR 2023.