Skip to content
View bencejdanko's full-sized avatar
3 followers · 5 following

Achievements

Achievement: Pull Sharkx2Achievement: YOLO

Achievements

Achievement: Pull Sharkx2Achievement: YOLO

Organizations

@rcc-sjsu @ai-ml-club-sjsu

Block or report bencejdanko

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
bencejdanko/README.md

Hello, I'm Bence 👋

I'm a Master's student in Applied Data Intelligence at San Jose State University. B.Sc in Computer Science, San Jose State (May 2024).

I build generative and deep learning AI models, agentic AI workflows and evaluations. I've built full stack applications, including for a non-profit organization. I'm currently interested in edge AI hardware acceleration, collaborating on applied research with Nuvoton for their NuMicro® M55M1 microcontroller series and Arm Ethos-U55 NPU. In my free time, you can find me on the Jetson AI Lab Research Community applying my Nvidia AGX Orin, and managing my kubernetes/ArgoCD self-hosted applications.

Pinned Loading

  1. unified-medical-scenario-benchmark-adaptive-routing-reinforcement-learning unified-medical-scenario-benchmark-adaptive-routing-reinforcement-learning Public

    A unified multi-scenario medical domain benchmark using the Common Unified Benchmark Environments (CUBE) wrapper, and an implementation of RL training an adaptive routing system with a novel reward…

    HTML

  2. sign-language-translation sign-language-translation Public

    video-to-text sign language translation with a modified SAM-3D-Body library fork, evaluated on How2Sign

    Jupyter Notebook

  3. image-restoration-convolution-mla100-optq-qat image-restoration-convolution-mla100-optq-qat Public

    Image Restoration task on the MLA100 NPU. We maintain PSNR gains while quantizing to INT8 by ablating quantization methods, and using OPTQ and QAT techniques on convolutional neural networks.

    Python

  4. m55m1-ElevatorCounting-YOLOv8n m55m1-ElevatorCounting-YOLOv8n Public

    People-counting from top-down elevator views. Using the Nuvoton M55M1 and its Ethos-U55 NPU, the system runs optimized ML models directly on the device.

    Python 1

  5. gemma-2b-fine-tuning-dolly-15k gemma-2b-fine-tuning-dolly-15k Public

    Fine-tuning Google's Gemma 2B on the Databricks Dolly 15k dataset using Hugging Face Transformers. This project implements full parameter fine-tuning with rigorous evaluation using LLM-as-a-judge (…

    Jupyter Notebook

  6. wixqa-rag wixqa-rag Public

    Building and evaluating Retrieval-Augmented Generation system for the WixQA dataset with Cerebras and gpt-oss-120b. We evaluate different chunking and retrieval strategies k={1,3,5,10}, chunks={300…

    Jupyter Notebook