📑 PageIndex: Document Index for Vectorless, Reasoning-based RAG

Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞

STEP-GUI: The top GUI agent solution in the galaxy. Developed by the StepFun-GELab team and powered by StepFun’s cutting-edge research capabilities.

A natural language interface for computers

The Open-Source Multimodal AI Agent Stack: Connecting Cutting-Edge AI Models and Agent Infra

verl: Volcano Engine Reinforcement Learning for LLMs

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

Intriguing Properties of Data Attribution on Diffusion Models (ICLR 2024)

AutoSplice: A Text-prompt Manipulated Image Dataset for Media Forensics, WMF@CVPR2023

Implementation of DALL-E 2, OpenAI's updated text-to-image synthesis neural network, in Pytorch

✨✨[NeurIPS 2025] This is the official implementation of our paper "Video-RAG: Visually-aligned Retrieval-Augmented Long Video Comprehension"

🔥[AAAI 2026, Official Code] Regression Over Classification: Assessing Image Aesthetics via Multimodal Large Language Models. 克服大模型在美学评估过程中对分数不敏感的问题

A comprehensive collection of IQA papers

UniPercept: Towards Unified Perceptual-Level Image Understanding across Aesthetics, Quality, Structure, and Texture

[CVPR 2025 Oral] OverLoCK: An Overview-first-Look-Closely-next ConvNet with Context-Mixing Dynamic Kernels

【TMM 2025🔥】 Mixture-of-Experts for Large Vision-Language Models

Image Polygonal Annotation with Python (polygon, rectangle, circle, line, point and image-level flag annotation).

COCO API - Dataset @ http://cocodataset.org/

Ongoing research training transformer models at scale

GLIDE: a diffusion-based text-conditional image synthesis model

[AAAI 2025] Official repository of paper “Mesoscopic Insights: Orchestrating Multi-scale & Hybrid Architecture for Image Manipulation Localization”

TruFor

Official code for CAT-Net: Compression Artifact Tracing Network. Image manipulation detection and localization.

The official repo for RGCL:Improving Hateful Meme Detection through Retrieval-Guided Contrastive Learning and RA-HMD: Robust Adaptation of Large Multimodal Models for Retrieval Augmented Hateful Me…

🚀 A simple way to launch, train, and use PyTorch models on almost any device and distributed configuration, automatic mixed precision (including fp8), and easy-to-configure FSDP and DeepSpeed support

Optimizing MLLM-based Scoring via a Score-Token + Decoder Paradigm. This paper proposes a unified scoring paradigm for Multimodal Large Language Models (MLLMs).

Codes of the Fine-grained Textual Inversion network for Zero-Shot Composed Image Retrieval

High-performance inference framework for large language models, focusing on efficiency, flexibility, and availability.

[CVPR 2025] Teaching Large Language Models to Regress Accurate Image Quality Scores using Score Distribution