🦄🦄🦄AI赋能股票分析：AI加持的股票分析/选股工具。股票行情获取，AI热点资讯分析，AI资金/财务分析，涨跌报警推送。支持A股，港股，美股。支持市场整体/个股情绪分析，AI辅助选股等。数据全部保留在本地。支持DeepSeek，OpenAI， Ollama，LMStudio，AnythingLLM，硅基流动，火山方舟，阿里云百炼等平台或模型。

A Privacy First PDF Toolkit

一个基于nano banana pro🍌的原生AI PPT生成应用，迈向真正的＂Vibe PPT＂; 支持上传任意模板图片；上传任意素材&智能解析；一句话/大纲/页面描述自动生成PPT；口头修改指定区域、一键导出 - An AI-native PPT generator based on nano banana pro🍌

"Paper2Slides: From Paper to Presentation in One Click"

Templates and workflow for generating PRDs, Tech Designs, and MVP and more using LLMs for AI IDEs

[CVPR 2025] "A Distractor-Aware Memory for Visual Object Tracking with SAM2"

This script allows you to download VS Code extensions as VSIX files directly from the Visual Studio Marketplace.

🔥 Latest advances in Video Object Segmentation (VOS) – papers, datasets, and projects.

ICCV25 highlight

Simple python script to compress PDF

[ICLR 2025 Oral🔥] SD-LoRA: Scalable Decoupled Low-Rank Adaptation for Class Incremental Learning

Official code for our ICCV2025 paper "SDMatte: Grafting Diffusion Models for Interactive Matting"

[SIGGRAPH2025] Generative Video Matting

Reference PyTorch implementation and models for DINOv3

[Fully open] [Encoder-free MLLM] Vision as LoRA

Official code for ReLoRA from the paper Stack More Layers Differently: High-Rank Training Through Low-Rank Updates

GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projection

Instant voice cloning by MIT and MyShell. Audio foundation model.

The official repository of the dots.vlm1 instruct models proposed by rednote-hilab.

A Survey on Benchmarks of Multimodal Large Language Models

CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image

[TPAMI 2026 & ICML 2024 Oral] Official repository of the SparseTSF paper: "SparseTSF: Modeling Long-term Time Series Forecasting with 1k Parameters". This work is developed by the Lab of Professor …

Tongyi Deep Research, the Leading Open-source Deep Research Agent

[CVPR'25 Oral] LoRASculpt: Sculpting LoRA for Harmonizing General and Specialized Knowledge in Multimodal Large Language Models

[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.

Implementation of "Rapid Salient Object Detection with Difference Convolutional Neural Networks"

TradingAgents: Multi-Agents LLM Financial Trading Framework

MokA: Multimodal Low-Rank Adaptation for MLLMs

本人的科研经验

The official implementation of [CVPR 2025] "5%>100%: Breaking Performance Shackles of Full Fine-Tuning on Visual Recognition Tasks".