A unified foundation model for FIDL.

[ICML26] AVGen-Bench is a task-driven benchmark for multi-granular evaluation of Text-to-Audio-Video (T2AV) generation.

Open-source, community-driven agent harness

[CVPR 2026] UniGenDet: A Unified Generative-Discriminative Framework for Co-Evolutionary Image Generation and Generated Image Detection

reverse engineering Gemini's SynthID detection

The agent that grows with you

AI agents running research on single-GPU nanochat training automatically

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

Agentic Coding for Builders who Ship

EditHF-1M: A Million-Scale Rich Human Preference Feedback for Image Editing

Next-Token Prediction is All You Need

Your Intelligent End-to-End Multi-Modal Risk Assessment AI Expert

[AAAI2025] Revisiting Tampered Scene Text Detection in the Era of Generative AI

Official implementation of paper: From Masks to Pixels and Meaning: A New Taxonomy, Benchmark, and Metrics for VLM Image Tampering

A curated collection of automated research tools, covering literature search, paper reading, experiment management, and code generation to help researchers accelerate their workflow.

Your Personal AI Assistant; easy to install, deploy on your own machine or on the cloud; supports multiple chat apps with easily extensible capabilities.

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

[NeurIPS'24 Spotlight] A comprehensive benchmark & codebase for Image manipulation detection/localization.

[ICLR'26] Easier Painting Than Thinking: Can Text-to-Image Models Set the Stage, but Not Direct the Play?

Official code for AAAI26 paper: Unveiling the Attribute Misbinding Threat in Identity-Preserving Models

Implementation of paper EditCLIP: Representation Learning for Image Editing (ICCV 2025)

This repository is the official implementation of NeurIPS 2025 Paper "Dual Data Alignment Makes AI-Generated Image Detector Easier Generalizable".

Unsloth Studio is a web UI for training and running open models like Gemma 4, Qwen3.6, DeepSeek, gpt-oss locally.

[ICCV 2025 DeepID Challenge] Official 1st Place in both tracks (Detection & Localization)

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, …