Ayan Das, PhD

Curriculum Vitae

Published

September 8, 2024

Contact Information

Office Address: Lighthouse King’s cross office space, 1 King’s Cross Bridge, London N1 9NW, UK
Personal Email: ayan05das [at] gmail.com
Work Email: ayan.das [at] mtkresearch.com
Social Media: [at] dasayan05

Research Interests

  • Diffusion Models – Theory & Applications
  • Continuous-time models, dynamical systens and their applications
  • Vector graphics synthesis – intersection of vision & graphics

Work Experiences

  1. Senior AI Researcher at MediaTek Research 1
    • Full-time position (March 2023 – Present)
    • Part-time Internship (June 2022 – February 2023)
  2. Teaching Assistant (TA)2 at University of Surrey, UK
  3. Junior Project Officer3 at Electrical Dept., IIT Kharagpur, India

1 Part of the Cambridge UK team

2 Graduate course on Image processing and Deep Learning

3 Worked on Medical Image Compression, funded by Intel India

Education

  1. Doctor of Philosophy (PhD)4 from University of Surrey UK.
  2. Bachelor of Technology (BTech)5 from IEM Kolkata

4 From October 2019 to February 2024

5 Studied Electronics & Communication

Research Experiences

Topic Context
Diffusion Models Currently working on theoretical fundamentals at MediaTek Research. Also worked on appled problems during PhD
Vector sketch generation Worked on modelling free-hand vector sketches during PhD. In the intersection of vision & graphics
Medical Imaging Worked on compression architectures for medical images like mammograms etc. during my time as JPO at IIT Kharagpur
Evolutionary computation Worked on MOO and Genetic algorithm during my time as an intern at ECSU, ISI Kolkata
Handwritten recognition Worked extensively during my undergrad, with several publications, while an intern at CSE dept., IIT Roorkee

Publications

Title Author
CreativeSeg: Semantic Segmentation of Creative Sketches Yixiao Zheng, Kaiyue Pang, Ayan Das, Dongliang Chang, Yi-Zhe Song, Zhanyu Ma
Modelling complex vector drawings with stroke-clouds Alexander Ashcroft, Ayan Das, Yulia Gryaditskaya, Zhiyu Qu, Yi-Zhe Song
Doodle Your 3D: From Abstract Freehand Sketches to Precise 3D Shapes Hmrishav Bandyopadhyay, Subhadeep Koley, Ayan Das, Ayan Kumar Bhunia, Aneeshan Sain, Pinaki Nath Chowdhury, Tao Xiang, Yi-Zhe Song
Building Diffusion Model’s theory from ground up Ayan Das
Score Normalization for a Faster Diffusion Exponential Integrator Sampler Guoxuan Xia, Duolikun Danier, Ayan Das, Stathi Fotiadis, Farhang Nabiei, Ushnish Sengupta, Alberto Bernacchia
Image generation with Shortest Path Diffusion Ayan Das, Stathi Fotiadis, Anil Batra, Farhang Nabiei, FengTing Liao, Sattar Vakili, Da-shan Shiu, Alberto Bernacchia
ChiroDiff: Modelling chirographic data with Diffusion Models Ayan Das, Yongxin Yang, Timothy Hospedales, Tao Xiang, Yi-Zhe Song
SketchODE: Learning neural sketch representation in continuous time Ayan Das, Yongxin Yang, Timothy Hospedales, Tao Xiang, Yi-Zhe Song
Cloud2Curve: Generation and Vectorization of Parametric Sketches Ayan Das, Yongxin Yang, Timothy Hospedales, Tao Xiang, Yi-Zhe Song
Pixelor: A Competitive Sketching AI Agent. So you think you can sketch? Ayan Kumar Bhunia, Ayan Das, Umar Riaz Muhammad, Yongxin Yang, Timothy Hospedales, Tao Xiang, Yulia Gryaditskaya, Yi-Zhe Song
BézierSketch: A generative model for scalable vector sketches Ayan Das, Yongxin Yang, Timothy Hospedales, Tao Xiang, Yi-Zhe Song
Feature weighting and selection with a Pareto-optimal trade-off between relevancy and redundancy Ayan Das, Swagatam Das
HMM-based Indic handwritten word recognition using zone segmentation Partha Pratim Roy, Ayan Kumar Bhunia, Ayan Das, Prasenjit Dey, Umapada Pal
No matching items

Professional & Voluntary works

  • Serving as reviewer for top conferences (NeurIPS, ICLR, ICML, CVPR, ICCV, ECCV, BMVC, ACM SIGGRAPH, SIGGRAPH Asia) and journals (T-PAMI, Elsevier NN, TMLR).
  • Recognized as a “Top Reviewer” (i.e. top 10% of reviewers) at NeurIPS 2023
  • Supervised two MSc student projects (one was nominated for best project prize)
  • Served as Intel Student Ambassador (Asia Pacific & Japan) for Artificial Intelligence (A.I.)

Talks

Title/Topic Where?
Diffusion Model fundamentals and applications Invited talk at DataHour series, Analytics Vidhya
Two-house session on Diffusion Models SketchX Lab meet, CVSSP, University of Surrey
Diffusion Models: fundamentals and applications Invited talk at PRIS Lab, BUPT, China
Talk on Diffusion Model theory Invited talk at CS dept., University of Manchester UK
Foundation of continuous-depth models SketchX Lab meet, CVSSP, University of Surrey
No matching items

Prominent skills

Topic Skilset
Programming Languages C, C++, Python, Julia
ML/DL Frameworks PyTorch, PyTorch Lightning
Mathematics Linear Algebra, Probability, Calculus, Statistics
Infrastructure Cluster management, MPI, Distributed training
Web Front-end and back-end basics, Flask, Gradio
Miscellaneous Linux, LaTeX, Typst, Git, CUDA