🤝 Top Collaborators
.png&w=640&q=75)
🤓 Latest Submissions
AMD Multimodal Defect Agent
AMD Multimodal Defect Agent: Intelligent Industry Copilot In high-speed modern manufacturing environments, identifying a defective assembly part is only half the operational challenge. When an automated inspection camera flags an anomaly, factory operators often face critical delays trying to determine why the failure occurred. Manual troubleshooting leads to prolonged operational downtime, increased scrap rates, and high maintenance overhead. The AMD Multimodal Defect Agent bridges the critical gap between visual computer vision inspection and operational intelligence. Our solution integrates real-time visual anomaly detection with dynamic Retrieval-Augmented Generation (RAG) across historical maintenance logs to deliver an end-to-end industrial copilot. Key System Capabilities: Real-Time Visual Anomaly Analysis: Processes live part feeds against baseline reference images using OpenCV differential analysis to compute dynamic defect severity scores. Contextual Root-Cause Retrieval: Automatically queries local machine maintenance records (maintenance_logs.txt) whenever anomaly scores exceed safety thresholds. Actionable Copilot Guidance: Correlates visual defect patterns with historical mechanical logs (e.g., guide rail misalignment, belt vibration) to provide line operators with immediate, actionable repair recommendations. Hardware Architecture Strategy for AMD: Architected for edge-to-cloud deployment across the AMD hardware ecosystem, the pipeline runs natively on x86 architectures. It is specifically designed to be deployed on AMD Kria™ K26 SOMs and AMD Ryzen™ AI PCs at the factory edge for sub-millisecond, low-latency visual defect inference without cloud dependency. Furthermore, the PyTorch-compatible computer vision engine scales seamlessly onto AMD Radeon™ and AMD Instinct™ GPUs via AMD ROCm™ for high-throughput multi-camera industrial environments.
18 Oct 2026
KnowFlow AI — AI-Powered Document Q&A
KnowFlow AI is an AI workplace assistant that transforms static, dense documents into interactive knowledge sources using Retrieval-Augmented Generation (RAG). People often lose hours manually searching through PDFs, manuals, and reports, and standard AI chatbots risk hallucinating facts when they lack real document grounding. KnowFlow AI solves this by letting users upload PDF or text documents, which are automatically parsed, chunked, embedded, and indexed for fast semantic search. Users can then ask natural-language questions and receive concise, accurate answers with citations pointing directly to the source document and excerpt, so every answer is verifiable. The app features secure authentication with per-user data isolation, a document management dashboard with processing status tracking, persistent chat history, and a clean, responsive UI. Under the hood, the frontend is built with React, TypeScript, and Vite, styled with Tailwind CSS and shadcn/ui. The backend runs entirely on Supabase — using Postgres with pgvector for vector storage and semantic search, Supabase Storage for document files, Supabase Auth for secure login, and Supabase Edge Functions for server-side processing. Embeddings and chat completions are powered by the AIML API (OpenAI-compatible), using text-embedding-3-small and GPT-4o-mini. The result is a fast, secure, and genuinely useful tool for anyone who needs instant, trustworthy answers from their own documents.
10 Aug 2026
Smart Traffic
SmartTraffic operates on the innovative concept of dynamically adjusting traffic light signals based on the density of vehicles on the road. By intelligently monitoring traffic flow and adapting signal timings accordingly, the system aims to optimize the efficiency of urban transportation networks. When there are fewer vehicles on the road, SmartTraffic strategically switches traffic lights to green, capitalizing on the lower probability of congestion and minimizing the likelihood of traffic jams. This proactive approach not only helps to keep traffic moving smoothly but also contributes to reducing overall travel times and enhancing the overall driving experience for commuters. Through its ability to respond in real-time to changing traffic conditions, SmartTraffic represents a forward-thinking solution that holds great promise for creating more fluid and sustainable urban mobility systems in cognitive cities.
7 Mar 2024
