About News Publications Experience Teaching Projects Education

Sanyam Jain

I am a PhD student in Generative AI at the Department of Dentistry and Oral Health, Aarhus University, Denmark (2024 - present), working with Prof. Ruben Pauwels, Prof. Alexandros Iosifidis, and Dr. Bruna Neves de Freitas. My PhD project is on Synthetic Dental Radiography using Generative AI.

Previously, I completed my MSc in Applied Computer Science (2022 - 2024) at Østfold University of Applied Sciences, Norway, advised by Prof. Stefano Nichele, where I worked on Artificial Life, Cellular Automata, and emergent complexity in Lenia. I was also a Summer Intern at NTNU Gjovik (2024) and OsloMet (2023). Earlier, I was a Junior Research Fellow at IIT Jodhpur (2020 - 2022), part of the VANETs Lab and the QIC group, and I received my BTech in Computer Science from UPES Dehradun (2015 - 2019).

My research interests include Representation Learning, Generative Models, Computer Vision, and Medical Imaging, with current focus on diffusion models for dental radiography.

Email  /  CV  /  LinkedIn  /  GitHub  /  Google Scholar  /  Twitter


Water Your Repo, Grow Your Greens!

Sanyam's Github chart
News
  • [Sep '26] [Conference] Delivered an oral presentation and a poster of our work Brain2VLM at the ECCV 2026 workshop on Multimodal Reasoning and Slow Thinking in the Large Model Era, in Malmo, Sweden. The work analyses how cortical representations align with the latent spaces of pretrained diffusion-based vision-language models for brain-to-image reconstruction. preprint | project page | code (post)
  • [Jul '26] [Conference] Presented a poster for our short paper CarDiff: Anatomically-Aware Dental Caries Synthesis using Diffusion at the 30th Medical Image Understanding and Analysis (MIUA) 2026 conference in Dublin, Ireland (20-22 July). The work is on segmentation-conditioned synthesis with diffusion models for dental caries, which improved the Medium Caries class by +24% with 5x data augmentation. An extended version will be released as a preprint. (post)
  • [Apr '26] [Talk] Gave a talk at the University of Jyvaskyla (JYU), Finland, on my PhD topic Synthetic Dental Imaging using Generative Artificial Intelligence, hosted by Prof. Jenni Raitoharju. This also wrapped up my three-month PhD stay abroad at Tampere University, where we investigated model robustness for lifelong learning. (post)
  • [Feb '26] [New Role] Started as a Visiting PhD Student at Tampere University, Finland, with Prof. Alexandros Iosifidis and Prof. Ruben Pauwels. (post)
  • [Sep '25] [Paper] New preprint led by Johan Andreas Balle Rubak: Impact of Labeling Inaccuracy and Image Noise on Tooth Segmentation in Panoramic Radiographs using Federated, Centralized and Local Learning. (post)
  • [Mar '25] [Talk] Invited as guest speaker on PhD in AI for the Lecture Session at the International Women's Day Workshop, Indian Institute of Technology Roorkee, organised by the Department of Computer Science and Engineering. (post)
  • [Feb '25] [Paper] Our article Pano-GAN: A Deep Generative Model for Panoramic Dental Radiographs was published in Journal of Imaging, 11(2), 41 - a bachelor's project that grew into a new research direction on synthetic data generation in Dentistry and Oral Health. (post)
  • [Jan '25] [Talk] Gave my first presentation at Aarhus University, titled Synthetic Generation of Panoramic Radiographs, as part of PhD Day 2025. (post)
  • [Dec '24] [Paper] Our paper Shaving Beard or Applying Eye Makeup? Analysing How Frequently Pretrained VLMs Fail was accepted as a short paper at VISAPP 2025 (Porto, Portugal). The work came out of my summer internship at the Educational Technology Research Laboratory, NTNU, with Dr. Vijeta Sharma and Prof. Deepti Mishra. (post)
  • [Sep '24] [New Role] Started as a PhD Student at the Department of Dentistry and Oral Health, Aarhus University, Denmark. (post)
  • [Aug '24] [Outreach] Visited the Career Development Cell at the Indian Institute of Technology Dharwad to mentor students on emerging directions in Machine Learning and AI. (post)
  • [Jul '24] [New Role] Happy to share that I will start my PhD at Aarhus University on Generative Deep Learning for Medical Imaging, after finishing my MSc in Applied Computer Science at Ostfold University of Applied Sciences, Norway. (post)
  • [May '24] [Conference] Attended and presented at ICAPAI 2024 in Halden, Norway (16 April), and wrote up a summary of the talks and the conference. Thanks to the ICAPAI committee, HiOf and IFE Halden for organising. (post)
  • [Mar '24] [Paper] Two of my single-author papers were accepted at ICAPAI 2024, published in IEEE conference proceedings (Level 1 in the Norwegian system): Adversarial Attack on YOLOv5 for Traffic and Road Sign Detection and DeepSeaNet: Improving Underwater Object Detection using EfficientDet. (post)
Publications
Brain2VLM Brain2VLM: Hierarchical Alignment Between Cortical Representations and Vision-Language Latent Spaces
N A A Pritam, J S O, S Jain
MARS2 Workshop, ECCV 2026
paper | project page | code | poster

Shows that brain-to-latent alignment is hierarchical: early visual cortex maps to Stable Diffusion's structural latent almost linearly, while higher visual areas need a nonlinear decoder to reach CLIP space (+0.48 correlation against +0.06). Improving only the decoder, with the generator left frozen, lifts semantic reconstruction quality across four NSD subjects.

PanoDiff-SR PanoDiff-SR: Synthesizing Dental Panoramic Radiographs using Diffusion and Super-resolution
S Jain, S Pedersen, R Pauwels
arXiv Preprint, 2025
paper

Proposes a two-stage pipeline combining a latent diffusion model with super-resolution to synthesize high-resolution panoramic dental radiographs, addressing data scarcity in dental imaging while preserving anatomical fidelity.

PanoGAN Pano-GAN: A Deep Generative Model for Panoramic Dental Radiographs
S Pedersen, S Jain, M Chavez, V Ladehoff, B N de Freitas, R Pauwels
Journal of Imaging, 11(2), 41, 2025
paper

Develops a generative adversarial network for synthesizing panoramic dental radiographs, evaluated for clinical realism by dental experts. The work demonstrates the potential of GAN-based synthesis for augmenting limited medical imaging datasets.

DeepSeaNet DeepSeaNet: Improving Underwater Object Detection using EfficientDet
S Jain
4th International Conference on Applied Artificial Intelligence (ICAPAI), 2024
paper | portal

Investigates underwater object detection on Denmark's Brackish dataset using a modified EfficientDet. The proposed approach achieves 88.54% IoU with five-fold cross-validation, outperforming prior baselines on the dataset.

GradCAM YOLO Adversarial Attack on YOLOv5 for Traffic and Road Sign Detection
S Jain
4th International Conference on Applied Artificial Intelligence (ICAPAI), 2024
paper | code

Studies the robustness of YOLOv5 on traffic sign detection under a range of adversarial attacks including L-BFGS, FGSM, C&W, BIM, PGD, One Pixel Attack, and Universal Adversarial Perturbations, and analyzes their effect on detection accuracy.

Lenia Capturing Emerging Complexity in Lenia
S Jain, A Shrestha, S Nichele
Italian Workshop on Artificial Life and Evolutionary Computation (WIVACE), 2023
paper | portal

Explores emergent complexity in Lenia, a continuous cellular automaton, using evolutionary fitness measures based on Variance over Time (VoT), Autoencoder reconstruction (AE), and a combined AEVoT criterion to discover novel life-like patterns.

Selected Experiences
PhD Student, Department of Dentistry and Oral Health, Aarhus University
Supervisors: Prof. Ruben Pauwels, Prof. Alexandros Iosifidis, Dr. Bruna Neves de Freitas
Sep 2024 - Present · Aarhus, Denmark

AI in Health at the School of Dentistry (Tandlægeskolen), part of the IOOS Intelligent Systems – ML Group. Working on Synthetic Dental Radiography using Generative AI: diffusion and GAN-based models for panoramic radiograph synthesis, super-resolution, simulation of rare anatomies, and downstream clinical evaluation.

Tampere
University
Visiting PhD Student, Tampere University
With Prof. Alexandros Iosifidis
Feb 2026 - Apr 2026 · Tampere, Finland

Three-month research stay investigating model robustness for lifelong learning, alongside an invited talk at the University of Jyväskylä.

Summer Research Intern, NTNU
Educational Technology Research Laboratory, Department of Computer Science
Jul 2024 - Aug 2024 · Remote

Computer Vision and Vision-Language Models for educational applications, with Dr. Vijeta Sharma and Prof. Deepti Mishra. Led to a short paper at VISAPP 2025 on how frequently pretrained VLMs fail on fine-grained action recognition.

Research Assistant (Forskningsassistent), Østfold University of Applied Sciences
Supervisor: Prof. Stefano Nichele
Oct 2022 - Jun 2023 and Mar 2024 - Jun 2024 · Halden, Norway

Open-endedness, Artificial General Intelligence and biologically inspired AI paradigms. Research across discrete and continuous cellular automata using evolutionary computation, alongside the MSc programme.

Research Assistant, TKD/IT, OsloMet – Oslo Metropolitan University
Supervisor: Prof. Stefano Nichele
Jun 2023 - Aug 2023 (full-time), Sep 2023 - Mar 2024 (part-time) · Oslo, Norway

Studying and analysing complexity in discrete cellular automata and capturing emergent behaviour using evolutionary computation, extending into Lenia and Neural CA.

Junior Research Fellow and Teaching Assistant, IIT Jodhpur
Coursework with Dr. Mayank Vatsa, Dr. Richa Singh; part of VANETs Lab under Dr. Debasis Das
Aug 2020 - Jul 2022 · Jodhpur, India

Fellowship awarded through GATE 2020. Research in Machine Learning, Deep Learning, Generative Adversarial Networks and Explainable / Dependable AI, in the Quantum Information and Computation group.

Earlier Industry Experience
  • Alexa Developer, Keyring Corp (AWS Activate startup), 2019 - Aug 2020, Mumbai, India. Voice-driven AI and conversational interfaces; published Alexa skills reaching 100k+ users, and custom Alexa Skills / Google Actions for businesses.
  • RPA Consultant (self-employed), Feb 2019 - Jul 2020, India. UiPath Advanced Certified (UiRPA, UiARD); built learning plans, certification guidance and RPA automation setups for startups and professionals.
  • Data Analysis Trainee, Fiserv, Jul 2019 - Sep 2019, Bengaluru, India. Campus placement from UPES Dehradun.
  • Software Engineering Intern, YellowAnt, May 2018 - Jul 2018, Bangalore, India.
  • Remote Intern, IBM Watson Offline, May 2018 - Jul 2018.
  • Technical Team Lead, UPES ACM Student Chapter, Oct 2016 - Sep 2017, Dehradun, India.
Teaching & Mentoring
Teaching Assistant, IIT Jodhpur
Machine Learning · Winter 2022 (Jan 2022 - May 2022)
Course instructor: Dr. Richa Singh

Prepared assignments and quizzes covering decision trees, information gain, Bayesian inference and model evaluation.

Foundations of Quantum Information and Computation · Aug 2021 - Dec 2021
Course instructors: Dr. Subhashish Banerjee, Dr. Atul Kumar, Dr. V. Narayan
Invited Lecture, IIT Roorkee
International Women's Day Workshop, Department of Computer Science and Engineering · March 2025

Guest speaker on PhD in AI, hosted by Prof. Sugata Gangopadhyay and sponsored by the Ministry of Electronics and Information Technology (MeitY), Government of India.

Research Mentoring

I supervise and collaborate with students on medical-imaging and generative-modelling projects, from framing the research question through experiments to manuscript preparation. Recent work includes Brain2VLM and SkinGenBench with N A Adarsh Pritam, master's theses on medical image segmentation, and mentoring at IIT Roorkee on machine learning fundamentals, GANs and diffusion models.

Outreach

Mentored students on emerging directions in Machine Learning and AI at the Career Development Cell, IIT Dharwad (Aug 2024), and wrote up conference summaries from ICAPAI 2024 for the wider community.

Selected Projects
Brain2VLM Project Page ( portal | paper | code )

Interactive page for Brain2VLM, with a clickable cortex explorer that contrasts the linear and nonlinear decoding regimes, a step-through of the reconstruction pipeline, a drag-to-compare view of reconstructions from subj01, and live ablation and latent-space plots drawn from the paper's own data.

EvoLenia Portal ( portal | paper )

Interactive portal for exploring emergent creatures discovered in the Lenia cellular automaton via evolutionary search. Built with HTML/JS to visualize evolution runs, fitness landscapes, and discovered patterns.

DeepSeaNet Portal ( portal | paper )

Project page for DeepSeaNet, presenting underwater object detection results on Denmark's Brackish dataset using EfficientDet with cross-validation and qualitative comparisons across baselines.

MNCA Portal - Frequency Histogram Coarse Graining ( portal | paper )

Studies complexity and emergent behaviour in elementary CA, discrete CA, and 2D Multi-Neighborhood Cellular Automata, with a frequency histogram based coarse-graining method to characterize pattern formation.

GradCAM YOLO ( code )

Implementation of Grad-CAM visualizations for YOLOv5 and analysis of how several adversarial attacks (FGSM, PGD, BIM, C&W, One Pixel, UAP) shift the network's attention on traffic and road sign detection.

Education
PhD in Generative AI (Dentistry and Oral Health)
(2024 - Present) Aarhus University, Denmark
Project: Synthetic Dental Radiography using Generative Artificial Intelligence
MSc in Applied Computer Science
(Aug 2022 - Jun 2024) Østfold University of Applied Sciences, Halden, Norway · Grade 8.32 / 10
Thesis: AI Generating Algorithms with Self-Organizing Neural Cellular Automata, supervised by Prof. Stefano Nichele
  • Coursework: Scientific Methods in Computer Science; Machine Learning (Roland Olsson, Stefano Nichele); Applied Computer Science Project (A); Advanced Topics in Machine Learning (A); Evolutionary Computation (A).
Direct PhD Programme, Quantum Information and Computation (discontinued)
(Aug 2020 - Jul 2022) Indian Institute of Technology Jodhpur, India · Grade 7.8 / 10
Admitted through GATE 2020; left to take up the MSc in Norway.
  • Coursework: Machine Learning (Dr. G. Harit); Advanced Machine Learning (Dr. M. Vatsa, A); Deep Learning (Dr. M. Vatsa); Dependable AI (Dr. R. Singh, A-); Artificial Intelligence (Dr. D. Mishra); Graph Theory and Applications (Dr. A. Mishra); Cryptography (Dr. S. Sanadhya); Financial Engineering (Dr. V. Vijay, A-); ML for Economics (Dr. D. Brahma).
  • Course projects: theoretical analysis of the BB84 QKD protocol and quantum attacks on blockchain (Qiskit); analysing and improving StyleGAN2 image quality on the HELEN Eye and Fashion datasets; Random Multimodel Deep Learning for classification; study of adversarial attacks and the effect of data augmentation on robustness.
BTech in Computer Science and Engineering
(2015 - 2019) University of Petroleum and Energy Studies (UPES), Dehradun, India · Grade 7.75 / 10
  • Best Project award for Compariso, a WhatsApp bot for comparing e-commerce prices.
  • Best Project award, Project Parliament 2018, for facial recognition in cybersecurity.
  • Top 10 in R.I.S.E. UPES with KidExa, supervised by Dr. Ravi Tomar.
  • Second prize, North India Cyber Security Hackathon (WIC Dehradun), for 4FactorAuthentication.
  • Third prize, IBM ICE campus hackathon, for real-time traffic analysis.
Danish, Module 3 (Danskuddannelse 3)
(Oct 2024 - Present) A2B Sprogskole, Aarhus, Denmark
Modules passed: Du3.1 (Jun 2025), Du3.2 (Dec 2025), Du3.3 (Aug 2026).
Certifications
  • IBM Generative AI Engineering Specialization · IBM, 2026. Sixteen-course programme covering generative AI foundations and applications, LLM architecture and data preparation, language modelling with transformers, fine-tuning and advanced fine-tuning for LLMs, RAG and LangChain, AI agents, deep learning with Keras, and Python for data science.
  • Graduate Aptitude Test in Engineering (GATE 2020) · IIT Delhi, 2020.
  • NVIDIA DLI · Building Transformer-Based Natural Language Processing Applications (2021); Fundamentals of Deep Learning (2021).
  • Automation Anywhere Certified Advanced RPA Professional (Automation 360), 2022.
  • UiPath RPA · UiPath, 2019.
  • Second Position, Cyber Security Hackathon · Learning Links Foundation, 2018.
Base template inspired by Nithish Kannen, thanks!