AI Agent Skills

PyTorch implementation of "Lagging Inference Networks and Posterior Collapse in Variational Autoencoders" (ICLR 2019)

[CVPR 2016] Unsupervised Feature Learning by Image Inpainting using GANs

Provides guidance for training and analyzing Sparse Autoencoders (SAEs) using SAELens to decompose neural network activations into interpretable features. Use when disco…

PyTorch Implementation of In-Domain GAN Inversion for StyleGAN2

Enhanced LanceDB memory plugin for OpenClaw — Hybrid Retrieval (Vector + BM25), Cross-Encoder Rerank, Multi-Scope Isolation, Management CLI

This repository implements the the encoder and decoder model with attention model for OCR

LEDNet: A Lightweight Encoder-Decoder Network for Real-time Semantic Segmentation

Multilingual TTS model with voice cloning and duration control, based on T5Gemma encoder-decoder LLM

Contextual Encoder-Decoder Network for Visual Saliency Prediction [Neural Networks 2020]

[ACL 2024 🔥] Video-ChatGPT is a video conversation model capable of generating meaningful conversation about videos. It combines the capabilities of LLMs with a pretrai…

Upload and fully manage YouTube videos and live events: metadata, thumbnails, captions, playlists, scheduled broadcasts, encoder streams, binding, lifecycle transitions,…

Hybrid RAG system combining vector search, knowledge graph (LightRAG), and cross-encoder reranking — with Docling document parsing, visual intelligence (image/table capt…

Production-grade RAG API built in Rust. Hybrid search with HNSW dense vectors and BM25 sparse matching, cross-encoder reranking, layout-aware document extraction via Doc…

Create a structured narrative record documenting why a design system decision was made — the context, options considered, trade-offs, and rationale. This produces a huma…

Use when turning a Jetson encoder use case into one validated surface-neutral recipe with native and PyNvVideoCodec projections for codec, preset, rate control,

Compresses a single video file to stay under a user-specified max file size using FFmpeg. Prefers GPU encoders (NVENC / AMF / QSV) with VBR bitrate targeting; falls back…