The Cradle framework is a first attempt at General Computer Control (GCC). Cradle supports agents to ace any computer task by enabling strong reasoning abilities, self-improvment, and skill curation, in a standardized general environment with minimal requirements.

Collecting awesome papers of RAG for AIGC. We propose a taxonomy of RAG foundations, enhancements, and applications in paper "Retrieval-Augmented Generation for AI-Generated Content: A Survey".

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

An official implementation for "CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval"

A Comparative Framework for Multimodal Recommender Systems

[TPAMI 2023] Multimodal Image Synthesis and Editing: The Generative AI Era

Automated modeling and machine learning framework FEDOT

✨✨Woodpecker: Hallucination Correction for Multimodal Large Language Models

LLM2CLIP significantly improves already state-of-the-art CLIP models.

(ECCVW 2025)GPT4RoI: Instruction Tuning Large Language Model on Region-of-Interest

This repo contains evaluation code for the paper "MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI"

🔥🔥🔥 A curated list of papers on LLMs-based multimodal generation (image, video, 3D and audio).

X-VLM: Multi-Grained Vision Language Pre-Training (ICML 2022)

A CLI tool/python module for generating images from text using guided diffusion and CLIP from OpenAI.

Towards Generalist Biomedical AI

A knowledge base construction engine for richly formatted data

[ICLR 2025] This is the official repository of our paper "MedTrinity-25M: A Large-scale Multimodal Dataset with Multigranular Annotations for Medicine“

Sequence-to-Sequence Framework in PyTorch

DANCE: a deep learning library and benchmark platform for single-cell analysis

Attention-based multimodal fusion for sentiment analysis