Aliff Thoha@iiTzThoha
1
Events attended
1
Submissions made
Malaysia
1 year of experience
About me
Hi, I'm Thoha, a Year 1, Semester 2 student pursuing a Bachelor of Engineering Technology (Robotics) with Honours at UniKL MFI. I'm still early in my degree, but I'm trying to grab every opportunity I can to get real experience outside the classroom. Hackathons, certifications, side projects, anything that lets me build and learn by doing instead of just sitting through theory. Robotics is my main focus, but AI and software have pulled me in too, and I like figuring out how the two connect. The AMD Developer Hackathon: Act II is part of that. I'm competing in Track 2 (Video Captioning Agent), building a pipeline that watches video clips and generates styled captions using the Fireworks AI platform. It's honestly been a solid crash course in Docker, debugging containerized apps, and working with LLM APIs, stuff I hadn't really touched before this. Still early in the journey, but always looking to learn, build, and pick up a few certificates along the way. Feel free to connect
🤝 Top Collaborators
.png&w=640&q=75)
🤓 Latest Submissions
UniKL - AMD ViXion
Video Caption Agent is an AI powered tool that watches video clips and generates captions in four distinct styles: formal, sarcastic, humorous_tech, and humorous_non_tech. Built for the AMD Developer Hackathon: Act II Track 2, this agent uses Fireworks AI's minimax-m3 model to understand video content through native video input. The pipeline follows a two-stage approach: 1. Video Understanding: The model watches the video directly and produces a detailed factual description of the setting, subjects, actions, and mood. 2. Style Generation: The description is rewritten into each requested caption style in a single API call, with intelligent key normalization to handle variations in model output. Key optimizations include: - Single-pass generation requiring only 2 API calls per video - Automatic handling of common misspellings without retries - Graceful failure handling that continues processing remaining tasks The agent processes videos in a Docker container, reading tasks from /input/tasks.json and writing results to /output/results.json, making it easily deployable and scalable. Features: - Supports four caption styles: formal, sarcastic, tech-humour, non-tech humour - Handles videos up to 2 minutes in length - Native video understanding without frame extraction - Fast processing with optimized API calls - Robust error handling and fallback mechanisms The project demonstrates efficient use of multimodal AI models for video understanding and creative text generation, all packaged in a production-ready container.
13 Jul 2026
