robot model inference in C/C++

Portable Codex skills, including the Daily AI Papers workflow.

BackdoorAgent is a stage-aware framework and benchmark that instruments LLM-agent workflows (planning, memory, tools) to systematically inject, track, and evaluate backdoor triggers across multi-st…

将博导十年科研经验炼化为可直接调用的 AI 技能。从 Idea 构思到论文投稿，你的 AI 科研副导师。

Ai-LaTex: A local-first LaTeX editor with PDF compilation, AI Agent collaboration, Codex/Claude Code support, and fine-grained academic writing assistance.

Awesome-LLMs-for-AI-Research is a collection of state-of-the-art, novel, and representative works on large language models for AI research, covering data engineering, model design and optimization,…

一套为研究生和学术研究者设计的完整AI Prompt库 📖 包含内容： ✨ 40+ 精心设计的AI Prompt ✨ 论文选题系统方法（生成、评估、论证） ✨ 论文查找快速方案（8个不同方案） ✨ 文献综述框架和工具 ✨ Excel自动评估表格 ✨ 3个完整的论证模板 🚀 核心优势： ⚡ 节省时间 50-70%（选题3-5天而不是2-3周） 🎯 科学方法（基于系统的5维度评估体系） 💡 即插…

本项目旨在为致力于进入VLA(Vision-Language-Action)领域的算法工程师提供一份全中文、实战导向的学习/面试手册。 不同于通用的 CV/NLP 面试指南，本项目聚焦于 Robotics 特有的挑战

Now, Stronger AI Pushes Frontiers, Stronger Our Shared Future.

Verify BibTeX citations with Google Scholar to detect AI hallucinations and fake references.

Official code for CVPR 2026 paper "BlackMirror: Black-Box Backdoor Detection for Text-to-Image Models via Instruction-Response Deviation"

Fast and streamable Excalidraw MCP App

Elevate your AI research writing, no more tedious polishing ✨

An interactive attention visualization and intervention tool for LLM Decode Stage.

[NeurIPS'25] A work to improve CLIP's visual detail capturing ability by inverting the unCLIP generative model.

[ICLR2025] Detecting Backdoor Samples in Contrastive Language Image Pretraining

[NeurIPS 2023] Text data, code and pre-trained models for paper "Improving CLIP Training with Language Rewrites"

📹 A more flexible framework that can generate videos at any resolution and creates videos from images.

CVPRW 2025 paper Progressive Autoregressive Video Diffusion Models: https://arxiv.org/abs/2410.08151

Hunyuan-GameCraft: High-dynamic Interactive Game Video Generation with Hybrid History Condition

The open-sourced Python toolbox for backdoor attacks and defenses.

JoPano: Unified Panorama Generation via Joint Modeling

This is an official code repository for CVPR 2025 paper BadVision.

Repository of paper 'DeDe: Detecting Backdoor Samples for SSL Encoders via Decoders'

Backdoor Stuff in AI/ ML domain

The official repository of NodeRAG