[SIGGRAPH 2026] Official implementation of "LongE2V: Long-Horizon Event-based Video Reconstruction, Prediction, and Frame Interpolation with Video Diffusion Models"
ai fintech financial advisor for your portfolio
fintech forge of AI-powered financial tools and insights to secure authentication and dashboards to empowers developers, analysts, and students to build and extend finance-focused
FinTech AI Solution for SMEs to calculate financial values
fintech dashboard for personal finance management which track income and expenses, leverage AI-powered analytics, manage budgets and financial goals, enjoy a dark theme
Rust + Python Topological ML Toolkit for persistent homology, Betti-curve features, manifold embeddings, topology docs, backend contracts, and E2E benchmarks for sklearn/PyTorch/Te...
A Python/Cython implementation of Pruned BPE, a Byte Pair Encoding tokenizer that improves visible vocabulary efficiency by pruning low-exposure tokens while preserving internal me...
google gemini desktop ai desktop-app standalone-utility pwa progressive-web-app chrome-installation edge-apps taskbar-pinning system-shortcut system-integration setup-guide tutoria...
Python SDK for LLM guardrails with safety classification, PII detection, prompt injection defense, and grounding checks. Protect AI applications locally with zero external APIs, st...
Official implementation of ARDY: Autoregressive Diffusion with Hybrid Representation for Interactive Human Motion Generation (SIGGRAPH 2026).
A minimal Vision-Language-Action model you can read: frozen CLIP + a tiny head on ManiSkill PickCube. Runs on a Mac, no GPU.
Mine your Claude Code and Codex logs into a local you.md agent profile.
pixel-wise image classification of the satellite images obtained from copernicus
「說人話」：繁體中文的去 AI 味改寫 skill。抓 38 種 AI 寫作痕跡，順手校正中國用語與半形標點，給 Claude Code / Codex / Cursor 用。
Transformer architecture explained step by step - the full architecture, every attention variant, positional embeddings, and every layer inside a Transformer.
Train a tiny Transformer from scratch on your iMessage history, entirely on your Mac.
拉片笔记:把电影变成 AI 辅助的拉片笔记 - 本地抽帧/剧情泳道时间轴/结构树/情绪曲线/段落深拆
AI-powered deepfake detector that classifies uploaded face images and videos as Real or Fake with confidence scores. Full-stack app built with PyTorch (EfficientNet-B0), FastAPI, a...
An agentic AI tool for searching, screening, and ranking NIH funding opportunities based on research interests and proposal relevance.
(ECCV 2026): Official code for Flash-BoN: Instant Drafts for Inference-Time Scaling in Diffusion Models
Benchmark harness and leaderboard for zero-shot, open-type named-entity recognition — GLiNER, GLiNER2, and LLM backends with nervaluate scoring and bootstrap CIs.