Accelerate your Stable Diffusion inference with the library's universal C/C++ framework design, powered by ONNXRuntime & across platforms.

Oh yeah, we have image cache uses IndexedDB!

Spring Boot接口响应处理解决方案，提供统一返回值封装、全局异常处理、自定义异常错误码、参数校验增强、断言增强等功能

[ECCV 2024] Efficient Inference of Vision Instruction-Following Models with Elastic Cache

[MM'24 Oral] Prior Knowledge Integration via LLM Encoding and Pseudo Event Regulation for Video Moment Retrieval

即迅在线会议系统，web在线会议，研讨会议，支持视频会议、麦克风交互、协同白板、屏幕共享、会议录制、会议资料、语音识别、实时语音转写等功能，支持国产化服务器与客户端

AI-First Album: Chat with your gallery using plain language! LLM Vision + RAG + Album/Gallery.

The Official Implementation of PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling

[IJCAI 2022, Official Code] for paper "Rethinking Image Aesthetics Assessment: Models, Datasets and Benchmarks". Official Weights and Demos provided. 首个面向多主题场景的美学评估数据集、算法和benchmark.

Large language model fine-tuned to mimic LIHKG users' behavior

The source code of INFless，a native serverless platform for AI inference.

A work list of recent human video generation method. This repository focus on half/full body human video generation method, The Nerf, Gaussian splashing, Motion Pose, and talking head/Portrait is n…

Closed-loop multi-ability evaluation of end-to-end autonomous driving algorithms

generate resume and cover letter

Medical Multimodal LLMs

MIXQ: Taming Dynamic Outliers in Mixed-Precision Quantization by Online Prediction

一款用于检测jsonp及cors漏洞的burp插件

Code for ACL 2024 long paper: Are AI-Generated Text Detectors Robust to Adversarial Perturbations?

AvaTaR: Optimizing LLM Agents for Tool-Assisted Knowledge Retrieval (https://arxiv.org/abs/2406.11200)

Easyest and lazyest way for building multi-agent LLMs applications.

Knowledge Graph Fine-Tuning with Open-World Knowledge

A code repository designed to show the best GitHub has to offer.

The official implementation of Self-Play Preference Optimization (SPPO)