Techforhumans

company

Verified

https://www.techforhumans.com.br

tech4ai

Activity Feed Request to join this org

AI & ML interests

None defined yet.

Recent Activity

annajuliaasf updated a dataset 7 days ago

tech4humans/Audio-Transcription-Models-Comparison-PT-BR

annajuliaasf published a dataset about 1 month ago

tech4humans/Audio-Transcription-Models-Comparison-PT-BR

samuellimabraz new activity 2 months ago

tech4humans/br-doc-extraction:🚩 Report: Illegal or restricted content

View all activity

annajuliaasf

updated a dataset 7 days ago

tech4humans/Audio-Transcription-Models-Comparison-PT-BR

Viewer • Updated 7 days ago • 135 • 136 • 2

samuellimabraz

posted an update 21 days ago

Post

182

Quantum Assistant: Multimodal VLMs for Quantum Computing

I've open-sourced my undergraduate thesis work on specializing vision-language models for quantum computing with Qiskit.

Existing quantum code assistants (like IBM's Qiskit Code Assistant

Qiskit ) only process text, ignoring visual representations—circuit diagrams, Bloch spheres, histograms

What I built:
- A synthetic data generation pipeline that extracts content from Qiskit documentation, papers, codes transcribes images via VLM, generates validate input and output pairs, and validates all code through automated unit tests
- The first public multimodal dataset for quantum computing: 8,366 samples (45% with images) across function completion, code generation, and Q&A tasks
- Fine-tuned Qwen3-VL-8B using LoRA (rsLoRA r=32), achieving +11pp on Qiskit HumanEval (32.45% → 43.71%) and +17.9pp on multimodal samples vs text-only
- Interactive demo with chat interface and code challenges

Results: The model achieves 63.39% Pass@1 on visual samples—it learned to extract circuit topology from diagrams and infer parameters from visual annotations.

Everything is Apache 2.0:
- Dataset: samuellimabraz/quantum-assistant
- Models: https://huggingface.co/collections/samuellimabraz/quantum-assistant
- Code & Pipeline: https://github.com/samuellimabraz/quantum-assistant
- Demo: samuellimabraz/quantum-assistant

The synthetic pipeline is modular and can be adapted for other technical domains.

This work was inspired by the Qiskit team's work on code generation ([arXiv:2405.19495](https://arxiv.org/abs/2405.19495)) by @cbjuan @ndupuis

Built with ms-swift, transformers, vLLM, PEFT, and Qiskit. grateful for the open-source ecosystem that makes projects like this possible.