Python 排行榜

VAAS is an inference-first, research-driven library for image integrity analysis. It integrates Vision Transformer Attention Mechanisms with patch-level self-consistency analysis to enable fine-grained localization and detection of visual inconsistencies across diverse image analysis tasks.

All-in-one UI for merged LLMs in Hugging Face

Generate README.md with GPT-3 few-shot learning

Advanced Coding AI Assistant that uses a Gradio interface to stream coding related responses. ChatRAG supports local and API inference and pulls context from GitHub Repos and local files.

Deterministic, read-only static auditor for GGUF models: behavioral chat-template backdoors + SSTI, tokenizer, config, and model-card surfaces - never renders, never loads weights. 192,032 repos, 137,698 templates analyzed, 0 reviewed false-positive FAILs.

wrapper for multiple linkml storage engines

🧠 Stop building AI that forgets. Master MCP (Model Context Protocol) with production-ready semantic memory, hybrid RAG, and the WARNERCO Schematica teaching app. FastMCP + LangGraph + Vector/Graph stores. Your AI assistant's long-term memory starts here.

分享高质量的AI项目

Transformer-based online speech recognition system with TensorFlow 2

[CVPR 2025] This is the official implementation of Keep the Balance: A Parameter-Efficient Symmetrical Framework for RGB+X Semantic Segmentation

A RAG system designed to process documents with multimodal content. It can generate factual, context-aware answers to user queries, based on the documents texts, tables, figures, ...

Official Repository for the paper 'MemeCLIP: Leveraging CLIP Representations for Multimodal Meme Classification' @ EMNLP 2024

Local NotebookLM for Claude Code via Google Antigravity (agy / Gemini 3.x): /agy:notebook turns a folder of documents into per-doc summaries + a relevance index + a cited synthesis + Q&A. Plus audio/video transcription, deep web research with citations & branded HTML reports. 13 commands, no Node runtime.

StreamUni is a framework that efficiently enables unified Large Speech-Language Models to accomplish streaming speech translation in a cohesive manner.

[AAAI 2026] Offical implementation of "Commonality in Few: Few-Shot Multimodal Anomaly Detection via Hypergraph-Enhanced Memory".

Code for Findings of ACL 2022 Paper "Sentiment Word Aware Multimodal Refinement for Multimodal Sentiment Analysis with ASR Errors"

100% local video dubbing on your desktop — dub videos in your own voice. Private AI dubbing with no cloud, no uploads, no time-stretching.

视频课程学习工作台：字幕提取、课程管理、AI 学习材料与 ASR 校正。Video course workspace for subtitles, course collections, AI study notes, and ASR correction.

Streaming ASR, audio captioning and speech QA over a whisper-style encoder with pluggable LLM backends

Acoustic and language models for minorised languages.