generative-ai

A handy lib for smooth interaction with large language models (LLMs) and crafting AI apps.

Official Implementation of LongLive-RAG: A general retrieval-augmented framework for long video generation.

Open-source agent skills for turning raw book ideas into full manuscripts with blind literary evaluation gates.

[BMVC 2025] Official implementation for paper EZIGen: Enhancing zero-shot personalized image generation with precise subject encoding and decoupled guidance

A Collection of AIGC Research Groups

AI-native studio for multi-device shows that happen inside phones.

A cog implementation of Meta's MusicGen models

Deepmark AI enables a unique testing environment for language models (LLM) assessment on task-specific metrics and on your own data so your GenAI-powered solution has predictable and reliable performance.

AI tools curated by autonomous agents for makers and SMBs

AIOZ-GDANCE: a large-scale dataset & baseline for music-driven group dance generation. (CVPR 2023)

[ECCV 2024] EchoScene: Indoor Scene Generation via Information Echo over Scene Graph Diffusion.

Deepstory turns a text/generated text into a video where the character is animated to speak your story using his/her voice.

🔵🔎 Findto is a decentralized search assistant for AI and Web.

[ECCV2024] PartCraft: Crafting Creative Objects by Parts

This paper list focuses on the theoretical and empirical analysis of language models, especially large language models (LLMs). The papers in this list investigate the learning behavior, generalization ability, and other properties of language models through theoretical analysis, empirical analysis, or a combination of both.

Transform your software development lifecycle with Specifai - an intelligent platform that turns project ideas into structured requirements and actionable tasks in minutes.

An LLM training framework built from the ground up, featuring a custom BumbleBee architecture and end-to-end support for multiple open-source models across Pretraining → SFT → RLHF/DPO.

ACCV 2020 "Speech2Video Synthesis with 3D Skeleton Regularization and Expressive Body Poses"

The official implementation of DiffAbXL benchmarked in the paper "Exploring Log-Likelihood Scores for Ranking Antibody Sequence Designs", formerly titled "Benchmarking Generative Models for Antibody Design".

A curated list of resources for AI-generated user interfaces — systems where LLMs dynamically create, compose, and render UI components.