Projects

Overview: This project is an official implementation of "Commonality in Few: Few-Shot Multimodal Anomaly Detection via Hypergraph-Enhanced Memory" (AAAI 2026). The paper focuses on few-shot multimodal industrial anomaly detection, addressing the challenge of insufficient training samples in few-shot settings. Key features: - CIF (Commonality in Few): A novel few-shot unsupervised multimodal industrial anomaly detection method based on structural commonality. - Hypergraph: Used to model higher-order correlations and extract intra-class structural information. - Memory bank: Stores intra-class structural prior for test sample updates. - Hyperedge-guided memory search: Utilizes structural information to reduce false positive rates. Tech stack: Python Why it matters: This project is significant for researchers and developers working on few-shot anomaly detection, offering a practical solution for quickly adapting to complex industrial scenarios. Repository: Sunny5250/CIF Primary language: Python GitHub stars: 28 GitHub description: Official implementation of "Commonality in Few: Few-Shot Multimodal Anomaly Detection via Hypergraph-Enhanced Memory" (AAAI 2026).

### Overview: The WaveSpeed Python SDK provides a comprehensive and efficient interface for interacting with the WaveSpeed inference platform, enabling developers to generate images, videos, and 3D models through the WaveSpeed AI API. This SDK simplifies the process of integrating WaveSpeed into projects, making it easier to leverage the powerful AI capabilities of WaveSpeed in Python applications. ### Key Features: - **Image Generation**: Utilizes the `wavespeed-ai/z-image/turbo` model to generate high-quality images. - **Video Generation**: Supports the `wavespeed-ai/z-video/turbo` model for creating engaging videos. - **3D Modeling**: Offers the `wavespeed-ai/z-3d/turbo` model for generating detailed 3D models. - **API Client**: Simplifies the process of invoking the WaveSpeed API with a straightforward API client. - **Authentication**: Supports both environment variable and direct API key configuration for secure access. - **Timeouts**: Allows setting a maximum wait time for tasks, with options to customize read timeouts for HTTP requests. - **Sync Mode**: Enables synchronous mode for better result tracking and error handling. - **Upload Files**: Facilitates the uploading of images, videos, and audio files for processing. - **Local Development**: Includes scripts for running tests and managing environment variables. ### Tech Stack: The WaveSpeed Python SDK is built on Python, utilizing the official SDK for seamless integration with the WaveSpeed platform. ### Why It Matters: The WaveSpeed Python SDK streamlines the process of integrating WaveSpeed into Python projects, making

Overview: This is an official pytorch implementation for the paper "A Unified Shape-Aware Foundation Model for Time Series Classification" (AAAI-26). Key features: - Incorporates a shape-aware adapter that adaptively aggregates multiscale discriminative subsequences (shapes) into class tokens. - Introduces a prototype-based pretraining module for instance- and shape-level representation learning. - Pre-trained on a large-scale multi-domain time series dataset with 1.89 million samples. - Achieves state-of-the-art classification performance across diverse target domains. Tech stack: Python, PyTorch, and other standard deep learning libraries. Why it matters: UniShape provides a unified approach to time series classification by focusing on both shape-aware feature extraction and prototype-based representation learning, making it highly effective for various time series datasets and domains.

Overview: Qwen-Image 3.0 API 中文文档：提供模型 ID、每张图片 $0.0206 计费、图像参数与调用示例，包含 CURL 和 Python 代码以及 OpenAI 兼容接口说明。 Key features: - 模型 ID - 每张图片 $0.0206 计费 - 图像参数与调用示例 - Python 代码示例 - OpenAI 兼容接口说明 Tech stack: C++/Python Why it matters: 提供了模型 ID、每张图片的费用以及详细的调用示例，方便开发者快速上手使用 Qwen-Image 3.0 API。 Repository: apimart-1sww/qwen-image-3-api-cn GitHub stars: 28

Overview: Seedream 5.0 Pro API 中文文档提供模型 ID、每张图片价格及调用示例，包含通过 APIMart 调用的详细说明。模型支持 1K 分层、1K 分层和 2K 分层档位，按量计费，最低 1 美元起充。 Key features: - 每张 $0.0146（1K-layer）按量计费 - 同一套 base URL 与鉴权头可访问 Seedream 5.0 Pro 以及目录里 300 多个图像、视频、语言模型 - 1 美元起充、按量付费 - 账单在响应里，花多少当场可见 - 异步任务设计，提交后获取 `task_id`，轮询任务状态 - 模型 ID 与接口参数详细说明 Tech stack: Python Why it matters: 通过 APIMart 调用 Seedream 5.0 Pro API，用户可以快速获取高质量图像生成服务，按需付费，无需订阅或预付，账单透明，支持多种调用方式，包括 Python 和 OpenAI 兼容接口。 Repository: apimart-ww1/seedream-5-api-cn Primary language: Unknown GitHub stars: 28

Overview: This project implements a fine-tuning of BERT for Aspect-Based Sentiment Analysis (ABSA) using the paper "Utilizing BERT Intermediate Layers for Aspect Based Sentiment Analysis and Natural Language Inference" (arXiv:2002.04815). Key features: - Fine-tuning of BERT for ABSA - Utilizes intermediate layers of BERT for improved performance - Supports three classes (default) or four classes (with "conflict" class) - Provides options for different models (linear, LSTM, attention) - Supports various datasets (laptop, restaurant, Twitter) Tech stack: Python Why it matters: This implementation aims to improve upon the results reported in the paper, providing a more accurate and superior performance in ABSA tasks.

### Overview: 本项目旨在收集和整理中文指令数据集，以方便大家对中文语言模型进行fine-tuning。目前开源的中文指令数据集非常有限，且大部分数据集是英文翻译而来。随着需求的增加，我们相信会有更多高质量的中文指令数据集出现。 ### Key features: - 收集和整理中文指令数据集 - 提供多种中文指令数据集，包括Guanaco Dataset、Alpaca Chinese Dataset、BelleGroup 数据集等 - 数据集来源多样，涵盖多个领域，如数学、对话等 - 数据集质量较高，经过人工校验和机器翻译 ### Tech stack: Python ### Why it matters: 随着中文语言模型的发展，对高质量中文数据集的需求日益增长。本项目通过收集和整理中文指令数据集，为开发者提供更丰富的训练资源，有助于提高模型的性能和应用效果。

Overview: This project is a desktop application that translates live streaming subtitles in real-time using Google Translate API, with support for 23 languages recognized by VOSK. Key features: - Real-time subtitle translation - Support for 23 languages recognized by VOSK - Automatic recognition of live streaming in 23 languages - Compatible with Python-based GUI frameworks (PysimpleGUI and Tkinter) Tech stack: The application is built using PySimpleGUI and Tkinter, with the speech recognition module VOSK and Google Translate API. Why it matters: This project offers a practical solution for real-time subtitle translation of live streaming content, making it useful for language learners, translators, and anyone who needs to follow live events in multiple languages. Repository: botbahlul/pyvosklivesubtitle Primary language: Python GitHub stars: 28 GitHub description: PySimpleGUI based DESKTOP APP that can RECOGNIZE any LIVE STREAMING in 23 languages that supported by VOSK then TRANSLATE (using unofficial online Google Translate API) and display it as LIVE CAPTION / LIVE SUBTITLE Installation: Simply install the required dependencies and run the application with the command "pyvosklivesubtitle". Update Notes: The script has been updated to use "mypyinstaller.bat" for compiling into a single executable file, and instructions have been provided for running it on different environments like Termux and Proot-Distro.

### Overview: This repository provides information and resources related to open source speech datasets, offering diverse and high-quality speech data across various domains such as conversational, academic, political, and more. These datasets are widely used for tasks like automatic speech recognition (ASR), speaker identification, emotion recognition, and other speech processing applications. ### Key features: - Casual Conversations - Common Voice ### Tech stack: Unknown ### Why it matters: These datasets are crucial for researchers and developers looking to improve speech processing algorithms and applications. They provide a rich resource for training models and testing their performance across different domains, making them essential for advancing the field of speech technology.

Overview: Cluaiz is a Rust-based local AI engine that supports running GGUF and ONNX models for various tasks such as chat, vision, speech, and embeddings. It automatically places models based on available hardware and supports OpenAI-compatible APIs. Key features: - Runs GGUF models through a fork of llama.cpp - Supports ONNX models through ONNX Runtime - A placement planner that decides where models run, context size, and KV cache type - Supports MoE models larger than GPU and RAM - Provides APIs for existing clients and a CEP protocol - Tools for agents, including skills, plugins, and MCP servers Tech stack: Rust Why it matters: Cluaiz simplifies the deployment of AI models by providing a unified solution that can run on local hardware, ensuring optimal performance and resource utilization. Repository: cluaiz/cluaiz GitHub stars: 28

Overview: This project involves scraping fraudulent emails from an anti-fraud website, deduplicating the dataset using MinHash and LSH, and fine-tuning a GPT-2 model on the deduplicated dataset. Key features: - Web scraping of scam emails - Deduplication using MinHash and LSH - Fine-tuning GPT-2 on a scam dataset Tech stack: Python Why it matters: This project aims to create a new dataset of fraudulent emails that can be used to advance research on intelligent email assistants.

### Overview: This is a patched native-Windows build of vLLM, featuring three specific fixes for Windows environments: CPU-relay for Gloo, Qwen3 reasoning parser fix, and wildcard model name support. It includes prebuilt wheels for Ampere/Ada and Blackwell GPUs, and a matching Qwen3.6-enhanced chat template. ### Key features: - **CPU-relay for Gloo collectives** - **Qwen3 reasoning parser fix** - **Wildcard model name support** ### Tech stack: - Python ### Why it matters: This patched build of vLLM is optimized for Windows environments, ensuring smooth performance and compatibility with Windows-specific tools and libraries.

Overview: This project is designed to automatically generate an audio-structured corpus for Automatic Speech Recognition (ASR) systems using pseudo-labeling techniques. Key features: - Integrates with YouTube or remote servers to collect content. - Supports direct links to videos or audio files. - Collects metadata including loudness, language detection, audio language detection, and SRMR ratio. - Provides options to export labeled data using whisper, wav2vec2, or NeMo as an ASR backend. - Supports multiple ASR models such as Whisper, Wav2Vec2, and NeMo. Tech stack: Python Why it matters: This tool simplifies the process of creating a corpus for ASR systems, making it easier for developers to test and improve their models without manual annotation.

Overview: This project records microphone audio, transcribes it locally with OpenAI Whisper, and copies the result to the clipboard. Key features: - Speech-to-text functionality - Integration with GNOME Wayland - Local transcription using Python and Whisper - Automatic paste to clipboard Tech stack: Python, Whisper, ffmpeg Why it matters: This project provides a practical solution for speech-to-text functionality on Linux, making it useful for developers and users who need to quickly transcribe audio recordings.

### Overview: This project introduces a speech recognition model for the Uyghur language, utilizing a transformer-based approach. The model is trained and tested using a dataset and pretrained model provided. ### Key Features: - **Training:** Uses Cross Entropy loss and CTC loss for training. - **Recognition:** Utilizes a pretrained model for recognition, with detailed output showing model performance metrics. ### Tech Stack: - Python ### Why It Matters: This project offers a practical solution for speech recognition in the Uyghur language, contributing to the development of language technology in the region.

### Overview: LawBotics v2 is an advanced legal technology platform that combines artificial intelligence with legal expertise to streamline contract review processes. The platform utilizes fine-tuned language models trained on the CUAD dataset to identify and extract key contract clauses, helping legal professionals save time and reduce errors in contract analysis. ### Key Features: - **AI-Powered Contract Analysis**: Automated clause identification and extraction from legal contracts. - **Multi-Format Support**: Processes contracts in PDF and text formats. - **Real-time Analysis**: Instant contract review with immediate results. - **Clause Categorization**: Identifies 41+ different types of legal clauses. - **Interactive UI**: Modern, responsive web interface built with Next.js 15. ### Tech Stack: TypeScript ### Why it Matters: LawBotics v2 leverages advanced AI and machine learning models to automate legal document review and clause extraction, making it an essential tool for legal professionals looking to streamline their contract analysis processes. Repository: hasnaintypes/lawbotics Primary language: TypeScript GitHub stars: 28 GitHub description: LawBotics v2 is an AI-powered legal contract analysis platform that combines machine learning with modern web technologies to automate legal document review and clause extraction.

### Overview: Vectorizer is a high-performance, in-memory vector database and search engine written in Rust, designed for semantic search and AI-driven applications. It ships as a Cargo workspace with binary RPC and HTTP transports, a React dashboard, and native SDKs for Rust, Python, TypeScript, Go, and C#. The database is optimized for speed, with SIMD acceleration and Metal GPU support, and it offers 4-5x faster search performance than Qdrant. It supports various storage formats, including `.vecdb` unified format, memory-mapped storage, and product and scalar quantization for efficient storage and retrieval. ### Key Features: - **Transport & API**: - **VectorizerRPC** (default, port `15503`) — binary MessagePack over TCP, multiplexed connection pool. - **REST API** (port `15002`) — universal HTTP fallback, powers the dashboard and any caller that doesn’t speak raw TCP. - **gRPC** — Qdrant-compatible service. - **GraphQL** — full REST parity with async-graphql + GraphiQL playground. - **MCP** — 31 focused tools for AI model integration (Cursor, Claude Desktop, etc.). - **UMICP Protocol** — native JSON types + tool discovery endpoint. - **Performance**: - **SIMD acceleration** — AVX2-optimized vector ops with runtime CPU detection (5-10x faster). - **Metal GPU** — macOS Apple Silicon via `hive-gpu

Overview: h-codex is a semantic code search tool designed for intelligent, cross-repo context retrieval, utilizing advanced techniques like AST-based chunking, embedding & semantic search, and efficient vector database storage. Key features: - AST-Based Chunking: Optimal code parsing using Abstract Syntax Trees. - Embedding & Semantic Search: Leveraging OpenAI's `text-embedding-3-small` model. - Vector Database: PostgreSQL with pgvector extension for efficient similarity search. - Multi-Language Support: TypeScript, JavaScript, and extensible for other languages. - Multi-Project Support: Index and search multiple projects. - MCP Integration: Seamlessly connects with AI coding assistants through Model Context Protocol. Tech stack: TypeScript Why it matters: h-codex offers advanced semantic code search capabilities, making it an invaluable tool for developers looking to enhance their productivity and understanding of code across projects. Repository: hpbyte/h-codex GitHub stars: 28 GitHub description: A semantic code search tool for intelligent, cross-repo context retrieval.

### Overview: This project presents a novel symmetric parameter-efficient fine-tuning framework for multimodal semantic segmentation, specifically addressing the challenges of high computational costs and limited transferability in RGB-based pre-trained models. The method, "Keep the Balance," aims to enhance the capabilities of pre-trained models to both RGB and X modalities by utilizing modality-aware prompting and adaptation, and dynamic sparse cross-modality fusion. ### Key features: - **Symmetric Parameter-Efficient Fine-Tuning Framework**: The method enables simultaneous adaptation of a powerful pre-trained model to both RGB and X modalities. - **Modality-Aware Prompting and Adaptation Scheme**: This scheme enhances the model's ability to learn from a diverse set of modalities. - **Dynamic Sparse Cross-Modality Fusion Module**: This module facilitates effective and efficient cross-modality fusion, mitigating the noise introduced by the attention mechanism. - **Self-Teaching Training Strategy**: The method leverages accurately predicted dual-modality results to self-teach single-modality outcomes, further strengthening the model. ### Tech stack: Python ### Why it matters: This framework addresses the limitations of traditional RGB-based segmentation methods by leveraging additional modalities effectively, thereby improving computational efficiency and broadening the model's transferability across different modalities. The method's ability to enhance the capabilities of pre-trained models to both RGB and X modalities makes it particularly valuable in applications requiring high accuracy and low computational cost.

Overview: SwiftLet is a lightweight Python framework designed for local execution of open-source Large Language Models (LLMs) using safetensors. Key features: - Local execution of supported LLMs - Minimal dependencies, easy to understand - Clean architecture for adding more models - Designed for research, prototyping, and educational use - Open for contributions and experiments Tech stack: Python Why it matters: SwiftLet provides a simple and educational way to run and experiment with various LLMs locally, making it ideal for learning and research purposes.