Native macOS app for local AI image generation and editing on Apple silicon: Z-Image Turbo and Qwen-Image-2.1 in Swift and Metal, fp32, checked against diffusers, zero swap on 16 G...
A virtual camera films an AI agent's screen while a tracker locks onto every glyph. Two fframes passes, one SkSL shader, all sound synthesized.
Officitial codebase for We Have Been Interpreting Diffusion Transformer Backbone Behaviors Wrong
Vela: User Behavior as Supervision Sparks LLM Intelligence — official paper, task templates, and prompts from AllSpark at Xiaohongshu.
A reader that writes answers in the margin. Select any line, ask, and an open model on Together AI answers beside it.
Local Qwen-Image generation and editing for Windows GPUs
一句话让 AI 帮你做产品宣传片！把产品名或网址告诉 Cursor、Claude Code、Codex 等 AI 编程工具，它会自己调研产品、画出多种风格样图让你挑选、截取 4K 真实页面、按音乐节拍卡点剪辑、生成 AI 旁白并逐句转写校验、自动审图，最后交付一支 4K 商业宣传视频和可在线播放的网页版。App、网站、SaaS、开源项目、课程、AI 模型都能...
Blender add-on: create and edit 3D models by chatting with AI - send text or an image, get working bpy code
[NeurIPS 2026] Diff-Aid: Inference-time Adaptive Interaction Denoising for Rectified Text-to-Image Generation
Scam With Your Friends Web: unofficial open-source browser remake. Co-op AI call center game with a 3D office, voice chat and daily quotas. React + Three.js; self-host on Cloudflar...
Code release for the paper Revisiting the 16x Pretraining Compute Gap between Diffusion and Autoregressive Language Models
Practical AI & Machine Learning for Materials Science: ACerS short course (Oct 2026). Colab-ready notebooks on featurization, supervised learning, interpretation, Bayesian optimiza...
AI 自主渗透测试系统 | 百度“agent+”攻防挑战赛冠军项目 Autumn-27/ARTEX
🔨 [NeurIPS 2026] Official implementation of “TabFORGE: A Tabular Foundation Model for Generative Modelling”
This repo is a alternative solution for standard self-attention. It uses tree routing with learnable functions for cheaper self-attention while not compromising accuracy.
ForcingBooster: Adaptive Patch-wise Denoising for Fast Autoregressive Video Diffusion
Claude generates a daily new tab page based on your browser history.
研图 Figure Atlas：289 张经典深度学习论文原图（附原文图注、出处与许可）与 28,102 个开源科研图标，中英文检索、改色下载。Original figures from 227 papers + research icons from 10 open-source packs.
PaperBench High-Difficulty and Expanded Tasks: paper reproduction beyond machine learning. 93 tasks in 12 research areas, run in domain-native software and graded by clean replay. ...
[IEEE TGRS 2026] Toward Realistic Remote Sensing Dataset Distillation with Discriminative Prototype-guided Diffusion
Daily AI news, fact-checked and traced back to its roots. A source-checked history of AI since 1943, a glossary with lineage, and the labs and people behind it. Open data, built ni...
让 AI 生成审美在线、结构保真、有创新点的工业设计概念图 / Fix ugly AI product renders: a SKILL.md workflow with six-layer prompts, a review rubric & 36 category-sorted design exemplars. Works with Kimi Work...
Nonlinear kinematic frequency decomposition and disentanglement + dual-style diffusion for motion style transfer and editing (SIGGRAPH Asia 2026).
Implementation of Play2Perfect, from Tyler Ga Wei Lum et al. of Stanford, but with a Self Play element