Stars
LongLive: Real-time Interactive Long Video Generation
[NeurIPS2025] "AI-Researcher: Autonomous Scientific Innovation" -- A production-ready version: https://novix.science/chat
[ICCV 2025] FoundIR: Unleashing Million-scale Training Data to Advance Foundation Models for Image Restoration
GenEval: An object-focused framework for evaluating text-to-image alignment
This repository contains a paper collection of the methods for document image processing, including appearance enhancement, deshadowing, dewarping, deblurring, binarization and so on.
A curated list of awesome papers on dataset distillation and related applications.
Offical implementation of "RealNet: A Feature Selection Network with Realistic Synthetic Anomaly for Anomaly Detection (CVPR 2024)"
This is the official implementation for Human-Agent Collaborative Paper-to-Page Crafting for Under $0.1.
[Preprint 2025] Ditto: Scaling Instruction-Based Video Editing with a High-Quality Synthetic Dataset
A simple yet powerful agent framework that delivers with open-source models
Parallel Scaling Law for Language Model — Beyond Parameter and Inference Time Scaling
G2RPO: Granular GRPO for precise reward in flow models
Thinking with Videos from Open-Source Priors. We reproduce chain-of-frames visual reasoning by fine-tuning open-source video models. Give it a star 🌟 if you find it useful.
This repository is the official code for the paper "LightFair: Towards an Efficient Alternative for Fair T2I Diffusion via Debiasing Pre-trained Text Encoders" (NeurIPS 2025).
[NeurIPS 2025 D&B] Open-source Multi-agent Poster Generation from Papers
Official implementation of Continuous 3D Perception Model with Persistent State
PromptEnhancer is a prompt-rewriting tool, refining prompts into clearer, structured versions for better image generation.
Paper List of Inference/Test Time Scaling/Computing
Stand-In is a lightweight, plug-and-play framework for identity-preserving video generation.
Scalable group inference for generating high quality and diverse images with diffusion models.
Implementation of "S^2-Guidance: Stochastic Self Guidance for Training-Free Enhancement of Diffusion Models"
One-shot and Few-shot 3D Editing without Per-Scene Optimization
Streamlining Cartoon Production with Generative Post-Keyframing
[NeurIPS 2025] Improving Video Generation with Human Feedback