Skip to content
View dasayan05's full-sized avatar
💭
Reject negativity. Stay positive. Use ReLU.
💭
Reject negativity. Stay positive. Use ReLU.
111 followers · 78 following

Achievements

Achievement: Public SponsorAchievement: Pull Sharkx2Achievement: StarstruckAchievement: Arctic Code Vault Contributor

Achievements

Achievement: Public SponsorAchievement: Pull Sharkx2Achievement: StarstruckAchievement: Arctic Code Vault Contributor

Highlights

  • Pro

Block or report dasayan05

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Please don't include any personal information such as legal names or email addresses. Maximum 100 characters, markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
dasayan05/README.md

Hello 👋, I am Ayan Das (@dasayan05)

I am a full-time Senior AI Research Scientist at MediaTek Research UK, working on Diffusion Models & Generative AI in general. I am also about to finish my Ph.D. (writing thesis) at SketchX Lab, University of Surrey working in the field of Vision and Graphics. My focus is on analysing and modelling human sketches and drawings from a computational as well as theretical perspective.

⚡️ Me in a nutshell:

  • Love programming: C/C++, Python for daily job & Lisp, Julia, Web Technologies (moderate-level) for fun.
  • Fond of Math: Daily research work involves lot of maths like Linear Algebra, Probabilities and Optimization.
  • Love to teach: Eager to share knowledge; publish full-fledged (comprehensive) blogs/articles on various research topics.
  • Voluntary: Serving as reviewer at top conferences (NeurIPS, CVPR, ECCV, ICCV, BMVC, SIGGRAPH) and journals (TMLR, Elsevier NN).
  • Extra: Love Music, Junk foods and Animals (specially Cats).

📝 Portfolio:

Research Papers Projects Blogs/Articles
1. DEIS-SN: Score normalization .. 1. A modular Deep RL library 1. Score & Diffusion Models ..
2. Shortest-Path Diffusion 2. Typst-AI-conf-templates 2. Differentiable Programming: Computing ..
3. ChiroDiff: Modelling chirographic data ... 3. anyx (in progress) 3. Energy Based Models (EBMs) ..
4. SketchODE: Learning sketch representation .. 4. Probabilistic Programming ..
Full List .. More ..

Go through my personal website "ayandas.me" to know more about me and my work. Want to contact me? Check out the Contact Page.

Pinned Loading

  1. mtkresearch/shortest-path-diffusion mtkresearch/shortest-path-diffusion Public

    Official code for the paper "Image generation with shortest path diffusion" accepted at ICML 2023.

    Python 21 5

  2. chirodiff chirodiff Public

    ChiroDiff: Modelling chirographic data with Diffusion Models

    Python 14 2

  3. sketchode sketchode Public

    Code repo for "SketchODE: Learning neural sketch representation in continuous time" published in ICLR 2022

    Python 10 4

  4. stroke-ae stroke-ae Public

    Bezier AE approach to sketch generation

    Python 31 7

  5. typst-ai-conf-templates typst-ai-conf-templates Public

    AI conference templates in Typst

    24 1