Skip to content
View ludekcizinsky's full-sized avatar
26 followers · 7 following

Block or report ludekcizinsky

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.

Maximum 250 characters. Please don't include any personal information such as legal names or email addresses. 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
ludekcizinsky/README.md

I am primarily interested in the application and development of state-of-the-art methods in the machine learning field. I have previous experience with LLMs, Graph Neural Networks as well as RL mainly through course work and collaborations with labs. My current focus is on dynamic scene reconstruction from monocular video which combines classical CV tasks (e.g. depth estimation) with capabalities of generative models (e.g. video diffusion).

Here are some of the most relevant projects I have done in the past:

Generative modelling (diffusion)

  • 🔗 / 2025 / HyperNCA: Fast texture synthesis using NCA
  • 🔗 / 2025 / GarmentDiffusion: Garment Texture Completion in UV space using Diffusion

Low Level (CUDA, MPI)

  • 🔗 / 2025 / Acceleration of Tsunami Simulation Time using MPI or CUDA
  • 🔗 / 2025 / Fast Conjugade Gradient Solver using MPI and CUDA

RL

  • 🔗 / 2025 / RL-Renaissance: Generating kinetic models using RL

(L)LMs

  • 🔗 / 2024 / A Data-Centric Approach to Fine-Tuning Phi3-mini
  • 🔗 / 2023 / Benchmarking SOT Feature Transforms for Biomedical Few-Shot Learning Tasks
  • 🔗 / 2023 / Advancing Homepage2Vec with LLM-Generated Datasets for Multilingual Website Classification

GNNs

  • 🔗 / 2025 / Spatio-Temporal Graph Modeling for EEG-Based Seizure Detection

Pinned Loading

  1. rl-renaissance rl-renaissance Public

    Generation of kinetic models using RL.

    Python 1

  2. hypernca hypernca Public

    HyperNCA: fast synthesis of novel textures using hyper networks and neural cellular automata.

    Python 1

  3. tsunami-simulation tsunami-simulation Public

    Simulating tsunami using shallow water equations (SWE) using either MPI or CUDA to enable fast simulation time.

    C++

  4. fast-cg-solver fast-cg-solver Public

    Implementation of Conjugate Gradient (CG) algorithm for solving sparse linear systems using MPI and CUDA.

    C

  5. mega-sam mega-sam Public

    Forked from mega-sam/mega-sam

    Code for the project "MegaSaM: Accurate, Fast and Robust Structure and Motion from Casual Dynamic Videos"

    Python 7 1