Stars
AI外呼系统,基于自然语言处理(NLP)、语音识别(ASR)、语音合成(TTS)和通讯(freeswitch)技术,实现自动语音应答,听说状态的实时切换,用自然逼真的对话与客户沟通。
工作流引擎对内提供单位/机关流程管理规则和内部业务流程的数字化落地实践;对外提供自动化地第三方业务驱动、接口接入和算法单元驱动能力。工作流引擎在提供底层驱动引擎的同时对全局透明监控、安全防御和国产化特色功能进行充分考虑,是内部流程管理和业务算法驱动的不二之选。
sdlc_python 是一个基于python语言构建的devsecops平台,旨在促进 DevSecOps 和安全开发生命周期 (SDLC) 实践。它通过模拟常见漏洞来增强开发人员的安全意识(对应sdlc中对开发人员的安全培训),并且使用了大模型进行代码安全审计(对应sdlc中代码审计阶段),帮助企业进行安全左移。除了用于 DevSecOps 实践外,sdlc_python 还可以用于学习…
⭐ Dynamically generate stats SVG from your Github, LeetCode, Steam, and more in #Cyberpunk style :)
[arXiv 2024] An official source code for paper "FlipAttack: Jailbreak LLMs via Flipping".
The "virtual_human_stream" project is a real-time digital human system supporting audio-video dialogue. It integrates models like ernerf, musetalk, and wav2lip for voice cloning, video stitching, a…
This includes the original implementation of CtrlA: Adaptive Retrieval-Augmented Generation via Inherent Control.
[Preprint] Resolving Multi-Condition Confusion for Finetuning-Free Personalized Image Generation
Mixed precision inference by Tensorrt-LLM
Unleashing the Power of Distributed Content Management and Transformation
FAST-LIVO2: Fast, Direct LiDAR-Inertial-Visual Odometry
A system demo based on Retrival Argument Generation to answer buddism question
High performance minimalism async-io(proactor) networking for Golang.
4th Place Solution for the Kaggle Competition: LMSYS - Chatbot Arena Human Preference Predictions
数据标注是一款专门对文本数据进行处理和标注的工具,通过简化快捷的文本标注流程和动态的算法反馈,支持用户快速标注关键词并能通过算法持续减少人工标注的成本和时间。数据标注的过程先由人工标注构筑基础,再由自动标注反哺人工标注,最后由人工标注进行纠偏,从而大幅度提高标注的精准度和高效性。数据标注是一个完全开源的项目,无商业版,但是需要依赖开源的数字底座进行人员岗位管控。各类词库结果会定期在本平台公开。
EAGLE: Exploring The Design Space for Multimodal LLMs with Mixture of Encoders
Controllable Text Generation for Large Language Models: A Survey
EOS is a dual-core operating system designed specifically for embodied intelligence, suitable for robots, drones, satellites or other scenarios requiring real-time and general capabilities.
Recipes to train reward model for RLHF.
RoboTwin: Dual-Arm Robot Benchmark with Generative Digital Twins
3DTopia-XL: High-Quality 3D PBR Asset Generation via Primitive Diffusion
A comprehensive survey on Internal Consistency and Self-Feedback in Large Language Models.
Video-Inpaint-Anything: This is the inference code for our paper CoCoCo: Improving Text-Guided Video Inpainting for Better Consistency, Controllability and Compatibility.
This repository contains the core methods and models described in the paper “Represent Code as Action Sequence for Predicting Next Method Call.” It uses action sequence modeling to predict method c…