PyTorch implementation of NEPA

[AAAI 2026] Beyond Cosine Similarity: Magnitude-Aware CLIP for No-Reference Image Quality Assessment

《机器学习》（西瓜书）代码实战

李宏毅2021/2022/2023春季机器学习课程课件及作业

Specification and documentation for Agent Skills

Overcoming False Illusions in Real-World Face Restoration with Multi-Modal Guided Diffusion Model [ICLR 2025]

[ICLR2025, ICML2025, NeurIPS2025 Spotlight] Quantized Attention achieves speedup of 2-5x compared to FlashAttention, without losing end-to-end metrics across language, image, and video models.

The paper list of "Memory in the Age of AI Agents: A Survey"

一个基于nano banana pro🍌的原生AI PPT生成应用，迈向真正的＂Vibe PPT＂; 支持上传任意模板图片；上传任意素材&智能解析；一句话/大纲/页面描述自动生成PPT；口头修改指定区域、一键导出 - An AI-native PPT generator based on nano banana pro🍌

<Foundations of Computer Vision> Book

TurboDiffusion: 100–200× Acceleration for Video Diffusion Models

SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformer

HY-World 1.5: A Systematic Framework for Interactive World Modeling with Real-Time Latency and Geometric Consistency

Musings

What are the principles we can use to build LLM-powered software that is actually good enough to put in the hands of production customers?

An AI agent that automates the creation of CVPR/NeurIPS standard academic diagrams. Implements a strict "Logic (Architect) -> Vision (Renderer)" workflow to transform paper abstracts into high-fide…

《深度学习入门-基于Python的理论与实现》，包含源代码和高清PDF(带书签)；慕课网imooc《深度学习之神经网络(CNN-RNN-GAN)算法原理-实战》；《菜菜的机器学习sklearn》

Books To Master Deep Learning

Up-to-date version of labs for ISLP

"DeepCode: Open Agentic Coding (Paper2Code & Text2Web & Text2Backend)"

A next.js web application that integrates AI capabilities with draw.io diagrams. This app allows you to create, modify, and enhance diagrams through natural language commands and AI-assisted visual…

UnicEdit-10M and UnicBench project

Official implementation for What matters for Representation Alignment: Global Information or Spatial Structure?

Towards Real-Time Diffusion-Based Streaming Video Super-Resolution — An efficient one-step diffusion framework for streaming VSR with locality-constrained sparse attention and a tiny conditional de…

A list of works on evaluation of visual generation models, including evaluation metrics, models, and systems

Code of π^3: Permutation-Equivariant Visual Geometry Learning

Paper Debugger is the best overleaf companion

Reward Forcing: Efficient Streaming Video Generation with Rewarded Distribution Matching Distillation

LLM Council works together to answer your hardest questions