Skip to content
View ludekcizinsky's full-sized avatar

Block or report ludekcizinsky

Report abuse

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

Report abuse
ludekcizinsky/README.md

My main focus is on developing models capable of extracting interesting information from video. With this being said, I have also done large variety of projects going from low level writing of CUDA kernel for tsunami simulation to developing RL model for kinetic parameter generation. I list the most interesting projects (that I was allowed to open-source) below.

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

Reconstruction

  • πŸ”— / 2025 / Monocular 4D reconstruction of the human-centric scene (master-thesis)

Generative modelling (diffusion)

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

Low Level (CUDA, MPI)

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

RL

  • πŸ”— / 2025 / RL-Renaissance: Generating kinetic models using RL

(L)LMs

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

GNNs

  • πŸ”— / 2025 / Spatio-Temporal Graph Modeling for EEG-Based Seizure Detection

Pinned Loading

  1. master-thesis master-thesis Public

    Monocular 4D reconstruction of human-centric scenes

    Python

  2. tsunami-simulation tsunami-simulation Public

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

    C++

  3. rl-renaissance rl-renaissance Public

    Generation of kinetic models using RL.

    Python 1

  4. hypernca hypernca Public

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

    Python 1

  5. fast-cg-solver fast-cg-solver Public

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

    C