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
- Senior AI Researcher at MediaTek Research 1
- Full-time position (March 2023 – Present)
- Part-time Internship (June 2022 – February 2023)
- Teaching Assistant (TA)2 at University of Surrey, UK
- 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
- Doctor of Philosophy (PhD)4 from University of Surrey UK.
- Worked on generative models for free-hand vector sketches.
- Thesis Title: “Learning natural vector sketch models”
- 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
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 |