Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3.6, DeepSeek-V4, GLM-5.1, InternLM3, Llama4, ...) and 300+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, GLM4.5v, Gemma4, Llava, …

An agent-managed museum exhibit, built in Rust with Gajae-Code / LazyCodex — developed and maintained with no human intervention.

[CVPR 2026] PromptEnhancer is a prompt-rewriting tool, refining prompts into clearer, structured versions for better image generation.

📹 A more flexible framework that can generate videos at any resolution and creates videos from images.

We introduce BabyVision, a benchmark revealing the infancy of AI vision.

omo/lazycodex: The coding agent for tokenmaxxers;the one and only agent harness for complex codebases. For your Codex, for your OpenCode

基于深度强化学习的开源自动因子工厂。

Official implementation of "WorDepth: Variational Language Prior for Monocular Depth Estimation"

Get 10X more out of Claude Code, Codex or any coding agent

[ECCV 2026] Towards Scalable Pre-training of Visual Tokenizers for Generation

A Cross-Platform Backend for High-Performance Sparse Convolutions

A Plugin-Based Multi-Agent System for In-Editor Academic Writing, Review, and Editing

[ArXiv 2025] MobileI2V: Fast and High-Resolution Image-to-Video on Mobile Devices

Kandinsky 5.0: A family of diffusion models for Video & Image generation

Lightweight Image Video Action Generation Inference Framework

The repository provides code for running inference and finetuning with the Meta Segment Anything Model 3 (SAM 3), links for downloading the trained model checkpoints, and example notebooks that sho…

[NeurIPS 2025] Official implementation of ScaleDiff: Higher-Resolution Image Synthesis via Efficient and Model-Agnostic Diffusion

PyTorch implementation of JiT https://arxiv.org/abs/2511.13720

[CVPR 2026] Scaling Spatial Intelligence with Multimodal Foundation Models

Local UI to run and train LLMs and diffusion models, including Kimi K3, MiniMax-H3, Gemma 4, Qwen3.6, DeepSeek-V4, FLUX and more.

Depth Anything 3

Automatically crawl arXiv papers daily and summarize them using AI. Illustrating them using GitHub Pages.

Cambrian-S: Towards Spatial Supersensing in Video

[NeurIPS 2025 Oral]Infinity⭐️: Unified Spacetime AutoRegressive Modeling for Visual Generation

Interactive, editable docs designed for coding agents

collection of diffusion model papers categorized by their subareas

Open-source AI penetration testing tool to find and fix your app’s vulnerabilities.

[WACV'25 Oral] Fine-Tuning Image-Conditional Diffusion Models is Easier than You Think