deb-kit2

Hi! I'm Deb.

Debjyoti Mondal

My name is Debjyoti Mondal. I'm a Research and Development Engineer at Samsung.
And I like a lot of things.


Work Experience

Samsung Research Institute, Bangalore March 2025 – Present

Lead Research Engineer, Natural Language Intelligence

Studying non-euclidean ML and Graph Neural Networks.
Designed the Device Assist QA feature introduced in Galaxy S26, and scaled it to 10M+ queries/day using efficient retrieval and LangChain. I had incredible fun building this! 😁
Enabling multi-objective alignment in Language Models with focus on Safety and Helpfulness, any model can handle multiple objectives with < 1% drop on general benchmarks.

Samsung Research Institute, Bangalore June 2022 – Feb 2025

Research Engineer, Natural Language Understanding

Enabled multi-modal reasoning with GNNs, published at AAAI 2024 — smallest model beat the baseline by ≥10%, new SoTA on ScienceQA.
Developed an LLM safety module for Bixby and GalaxyAI pipelines (on-device + cloud), handling 12 locales and 9 languages, scaled to 10M+ calls/day.
Maintained key modules in the Bixby pipeline, improving production performance to 95%.
How are we doing? Can't say much, but check this out.

Samsung Research Institute, Bangalore May – July 2021

Student Trainee 📜

Worked on the interpretability of Language Models for Intent Classification and Slot Tagging tasks.
Used Language Interpretability Tool (LIT) and Local Interpretable Model-agnostic Explanations (LIME).

NxTechWorks Consulting Pvt. Ltd., Pune Dec 2020 – Jan 2021

Machine Learning Intern 📜

I developed a generic object detection and localization framework.
And also some OCR apps for template based info extraction.
Hehe, this was fun - implemented deskew and denoise for scans using Hough transform and Thresholding.

Education

Indian Institute of Technology (ISM), Dhanbad July 2018 – May 2022

Bachelor of Technology in Electronics and Communication Engineering

Publications

SmoGVLM: A Small, Graph-Enhanced Vision-Language Model 📄

A super-fast method to inject knowledge into Small Language Models!

ICASSP 2026

Can Safety Emerge from Weak Supervision? A Systematic Analysis of Small Language Models 📄

We devise a pipeline for aligning an LLM with as many objectives as you want.
**With < 1% performance degradation on general tasks.**
We show it's effectiveness on Small Models with a focus on Safety and Helpfulness.

arXiv 2026

RG-VQA: Leveraging Retriever-Generator Pipelines for Knowledge Intensive Visual Question Answering 📄

Work done in collaboration with IIT-Bombay.

EMNLP Findings 2025

From Perception to Reasoning: Enhancing Vision-Language Models for Mobile UI Understanding 📄

Work done in collaboration with IIT-Bombay. We setup a new benchmark with some really complex queries, that need screen understanding and UI grounding.

ACL Findings 2025

KAM-CoT: Knowledge Augmented Multimodal Chain-of-Thoughts Reasoning 📄

We introduce knowledge graphs as a new modality, keeping the graph structure intact.
With 2 graph convolutional layers as the KGEncoder, our method gains a deeper contextual understanding of text, therefore reducing hallucinations and enhancing the quality of answers.

AAAI 2024

Seg-HGNN: Unsupervised and Light-Weight Image Segmentation using Hyperbolic GNNs 📄

We exploit the properties of Hyperbolic Spaces to do segmentation tasks in very low dimensions.
With the extracted image features, we build a graph in the Lorentz space, and perform unsupervised clustering to get semantically similar regions.

BMVC 2024

Beyond Work

Some cool projects

Modeling Chaotic Epidemic Models on FPGAs

A general procedure to implement Chaotic Models. Used Euler's Forward method to discretize continuous-time differential equations, then generated RTL Schematics and compared the resources used. Ahaa! And using this, I studied period-doubling bifurcations & got to the Feigenbaum constant with the logistic map and the Genesio-Tesi attractor. Be sure to watch this. It's pretty.

Bachelor's Thesis

FraJuVis - Julia Fractals on Android

An interactive Android app for visualizing Julia fractals in real time. Tap anywhere on the screen to set the complex parameter c in p(z) = z² + c, dynamically generating fractal patterns. Efficiently computes and renders using recursive iteration.

Android

Deep Dream

Implementation of the DeepDream algorithm. Extracts features from InceptionV3, and using gradient ascent over iterations, enhances 😵‍💫 patterns in the input image.