The Tooploox team delivers research and development services for innovative startups and world-leading companies to tackle their challenges in a way unseen before.
Research & Development
Whether you are an innovative startup, an enterprise-level world-changer, or anything in between, the power of reaching for the unknown is at your disposal. For our clients, the Tooploox team supports and facilitates creating world-changing solutions from scratch, where new discoveries and scientific breakthroughs are required. Disrupting your market was never that easy.
Let our team outthink your challenges
Your idea is unseen before? Your vision is bold on the verge of impossibility? You need your product to be built from scratch, using unseen technologies? Or maybe you dare to solve problems deemed unsolvable? We are with you.
Meet Our Team
With professors, PhDs, and PhD candidates we will get support you in breaking the rules and reaching for what was seen as unreachable before. We have a whole scientific institute ready to challenge reality for you.
Tomasz Trzciński, Prof.
Chief Scientist
Ivona Tautkute-Rustecka, PhD
Senior AI Engineer
Maciej Zięba, Prof.
Head of R&D
Rafał Topolnicki, PhD
Senior ML Engineer
Rafał Nowak, PhD
ML/AI Researcher
Paweł Lorek, Prof.
Data Scientist
Joanna Kaczmar-Michalska, PhD candidate
Senior ML Engineer & Researcher
Adam Słucki, PhD candidate
ML Engineer
Mateusz Kobos, PhD
ML Engineer
Mirek Korzeniowski, PhD
Data Scientist
Bartłomiej Kuchnowski, MD
ML/AI Researcher
Szymon Stoma, PhD
Co-founder Tooploox Research
Our works
Our works bridge the gap between academia and business, focusing on applying cutting-edge technology to transform people’s daily lives.
Hypernetworks for Image Recontextualization
- Novel approach to using AI for recontextualizing images
- The technique requires no fine-tuning to work properly
- The system delivers more accurate adjustments
- Based on Low-Rank Adaptation and Hypernetworks
Possible applications:
- E-commerce, fashion, and apparel industries to reduce the cost of photomanipulation
Divide and not forget: Ensemble of selectively trained experts in Continual Learning
Overcoming the catastrophic forgetting in continual learning
- A novel approach to overcoming catastrophic forgetting
- The technique leverages the Mixture of Experts to make training the neural network easier
- The technique injects new skills into the network while keeping its capabilities untouched
Possible applications:
- Reducing the time and cost required to upskill an existing neural network
Hypernetworks for Image Recontextualization
- Novel approach to using AI for recontextualizing images
- The technique requires no fine-tuning to work properly
- The system delivers more accurate adjustments
- Based on Low-Rank Adaptation and Hypernetworks
Possible applications:
- E-commerce, fashion, and apparel industries to reduce the cost of photomanipulation
Divide and not forget: Ensemble of selectively trained experts in Continual Learning
Overcoming the catastrophic forgetting in continual learning
- A novel approach to overcoming catastrophic forgetting
- The technique leverages the Mixture of Experts to make training the neural network easier
- The technique injects new skills into the network while keeping its capabilities untouched
Possible applications:
- Reducing the time and cost required to upskill an existing neural network
Modeling Uncertainty in Personalized Emotion Prediction with Normalizing Flows
Detecting hate speech with more accuracy
Enhancing sentiment analysis with context detection
- The model is capable of building the user profile from its messages and later taking it into account when analyzing the next messages.
- The approach significantly reduces false positives and false negatives when detecting hate speech on digital platforms.
Possible applications:
- Hate speech detection
- Sentiment analysis
HyperShot: Few-Shot Learning by Kernel HyperNetworks
Secondary title: Tackling the lack of labeled data
- A novel approach for few-shot problems that combines the benefits of using hypernetworks and kernel methods
- The role of the hypernetwork is to produce weights dedicated to the considered task
- The model can be applied to image classification problems where only a few examples are labeled
- The model works well both for in- and cross-domain problems
Possible applications
- Working in industries with a scarcity of labeled data, for example healthcare and life sciences
Diffused Heads: Diffusion Models Beat GANs on Talking-Face Generation
Secondary title: Transforming stating images into heads talking accordingly to audio.
- Our solution is capable of hallucinating head movements, facial expressions, such as blinks, and preserving a given background.
Possible applications
- Media
- Entertainment
- Education
PluGeN: Multi-Label Conditional Generation From Pre-Trained Models
Secondary title: Manipulating the parameters of latent space to get desired results
- A novel approach for attribute manipulation in images, but not just this – we also modify proteins
- The model works as a plug-in – we can link it with large pretrained generative models
- The model is tiny and can be easily trained on a single GPU, but it is able to cooperate with large generative models, like StyleGan
Possible applications
- Delivering precisely defined images by manipulating parameters for the sake of advertising, art or product development
Unleashing the potential of digital pathology data by training computer-aided diagnosis models without human annotations
Secondary title: Eliminating the need for a manual healthcare data annotation
- A novel approach to eliminate the need for manual annotations to train computer-aided diagnosis tools in digital pathology
- Application of mixed Deep Learning techniques with histopathological data
- Automatic analysis of clinical data including imagery and text
Possible applications
- Boosting the AI-powered diagnostics development process
FlowHMM: Flow-based continuous hidden Markov models
Secondary title: Improving the hidden Markov models in uncertainty modelling
- A novel approach for modeling sequential data
- Hidden Markow Models enriched with normalizing flows to model high non-Gaussian distributions for different states
- Two techniques for training the model that depend on the data’s nature were proposed
- The model can be applied to various sequence modeling tasks, including speaker separation, activity recognition, part-of-speech tagging, and many others
Possible applications
- Delivering better predictions for time series data
- Modeling risk in the energy sector, utilities
- Predicting stock prices
On Analyzing Generative and Denoising Capabilities of Diffusion-based Deep Generative Models
Secondary title: Pushing the boundaries of generative models
- A heavy modification of the existing generative model that enrich the diffusion paradigm
- The impact of noise in diffusion models is examined using various experimental settings
- Gaining more insights into how diffusion models work and at which point they switch from generating structure with noise, to pure denoising
Possible applications
- Boosting generative AI capabilities for design or art
Continual Learning with Guarantees via Weight Interval Constraints
Secondary title: Overcoming catastrophic forgetting
- A new training paradigm for continual learning
- The approach assumes the hyperrectangle weight allocation of upcoming tasks
- The proposed method overcomes the catastrophic forgetting problem while training the model in an incremental setting
Possible applications
- Boosting overall ML model performance
- Reducing the time and cost of training and maintaining ML models
Multiband VAE: Latent Space Alignment for Knowledge Consolidation in Continual Learning
Secondary title:
- A new method for unsupervised generative continual learning through the realignment of Variational Autoencoder’s latent space
- Controlled forgetting of new samples allows the reduction of the reconstruction error in generative models
- Multiband VAE is the first method to show forward and backward knowledge transfer in generative continual learning
Possible applications
- General model performance improvement
CoNeRF: Controllable Neural Radiance Fields
Secondary title:
- We extend neural 3D representations to allow for intuitive and interpretable user control beyond novel view rendering (i.e. camera control)
- We show a first time novel view and novel attribute re-rendering of scenes from a single video
Possible applications
- Entertainment
- Movie production
- Advertising business
Two-headed eye-segmentation approach for biometric identification
Secondary title: Improving AI-powered iris recognition
- We delivered architecture tailored for eye segmentation, done purely for person-identification purposes
- Quality was ensured by evaluating segmentation to learn the informative segmentation needed for identification
Possible applications
- Security
- Person-identification
General hypernetwork framework for creating 3D point clouds
Secondary title: Generating meshes from point cloud data
- A new generative model for 3D point clouds that introduces the concept of HyperFlows
- Set of practical methods that enable the generation of high-quality meshes using only point cloud data during training
- The framework may be applied to generate complex 3D objects
Possible applications
- Industrial design
- 3D processing
Non-Gaussian Gaussian Processes for Few-Shot Regression
Secondary title: Predicting the unpredictable with a combination of Gaussian process and Normalizing Flows
- Model that Predicts using only a few examples for a given task
- Compared to most works, we are focused on regression problems (continuous outputs)
- Since giving precise output values based on few labeled observations is not a good approach, we postulate to also model the uncertainty of the output (probabilistic regression)
- The model can be used in many applications, including head pose trajectory modeling, power consumption prediction, or EEG signal analysis
Possible applications
- Demand forecasting in retail
- Stock price changes
- Accurate estimations of power consumption
UCSG-Net–Unsupervised Discovering of Constructive Solid Geometry Tree
Secondary title: Using AI to boost 3D modeling
- The model takes 3D shapes and decomposes them into simple geometrical shapes called primitives
- The model also delivers a roadmap (Constructive Solid Geometry Tree) that tells us how to construct a complex shape using the primitives
- The model is trained in an unsupervised manner, which practically means that it observes only 3D shapes without any information about the true primitives
Possible applications
- Automated manipulation of scanned 3D objects
- Preprojection of parts in a larger 3D system
- Reducing super-complex structures (for example anatomy) into easier, engineerable parts for further analysis
- The model can tell you how to deconstruct furniture to deliver it to a client
Hypernetwork approach to generating point clouds
Secondary title: Using hypernetworks to generate and process point cloud data
- A generative model for 3D point clouds
- Using hypernetworks to generate 3D objects represented by various numbers of point clouds
- The approach can learn to create meshes through seeing only point cloud data during training
- The proposed approach may be used as a component for complex 3D scene generation
Possible applications
- 3D modeling
- Reducing the computational cost of 3D and LIDAR data processing
Adversarial Autoencoders for Compact Representations of 3D Point Clouds
Secondary title: A set of tools for classifying, coding, and generating 3D shapes in unsupervised mode.
- Framework for complex 3D point cloud processing
- The set of models for complex 3D modeling includes point cloud:
- generation
- representation
- retrieval
- clustering
- The model can learn compact binary representations for point clouds
Possible applications
- Working with 3D point cloud data
- Autonomous vehicles
- Industrial scanning
Conditional invertible flow for point cloud generation
Secondary title: reduce point clouds to vector and reverse
- A novel approach for generating 3D objects represented by point cloud
- We can quickly create point clouds with various densities and details
- The model is based on discrete normalizing flows and can be trained for a variety of objects and shapes
Possible applications
- The method may be helpful in 3D design, virtual reality, and related topics
- Transferring 3D point clouds
- Storage optimization
- AI-powered processing of point-cloud shapes
Bingan: Learning compact binary descriptors with a regularized GAN
Secondary title: Reducing images to binary representations
- A model for representing images using a minimal number of bits
- We can search for similar images in a database more efficiently
- The model is trained entirely in an unsupervised manner (no labels needed) and has high retrieval accuracy
- We make use of the discriminator of the regularized GAN to obtain an informative binary representation
Possible applications
- Reducing the carbon footprint of image-reliant operations
- Optimizing the performance of image-heavy workflows
Quantitative spatial analysis of hematopoiesis-regulating stromal cells in the bone marrow microenvironment through 3D microscopy
Secondary title: AI simplifying bone marrow cell classification
- A novel approach to quantifying microscopy data in the immune system
- 3D segmentation of bone marrow tissue samples after applying tissue-clearing techniques
- Application of spatial statistics to characterize the organization of the biological system
Possible applications
- Healthcare, diagnosis, medtech research
Long-term tracking of budding yeast cells in brightfield microscopy: CellStar and the Evaluation Platform
Secondary title: Single-cell observation made easier
- A novel algorithm to segment yeast cells based on raycasting
- Benchmark for evaluating SOTA methods
- Automatic Evaluation Platform for scoring cell based segmentation assays
Possible applications
- Diagnostics
- Research in biology, pharmacology, chemistry, etc.
- Microscopic observations
01 01
Our grants
Tooploox has experience in grant funded research with Academic and Industrial partners. Over the last 10 years we have sought grant funding to leverage our research and development (R&D) activities and help advance project and technology development in strategic directions. Grants allow our staff to gain exposure to unique expertise and resources and to participate in cutting edge research with world renowned institutions. This helps Tooploox bring new products, services, and technologies to our clients faster as well as lower the costs of developing new technologies by employing public funding.
Tooploox’s exposure to grant-funded R&D projects is close to 1,5M EUR in secured funding, among these are:
How was Tooploox Research established?
At Tooploox we believe no one is a lonely island. Collaboration, support for one another, and the willingness to share knowledge are values we consider to be essential for growth. That’s why, in 2019, we joined forces with Microscope IT – a dev shop providing AI and R&D services for Life Science, Healthcare and Medtech. This partnership advanced our AI skills to make us even more competitive and gave us, as a company but also as AI experts, the possibility to develop and reach the next level of expertise.
Formally, MicroscopeIT and Tooploox AI labs were connected together and from 2020 have been called Tooploox Research. We are proud to work together and we believe this merger not only makes us stronger but also helps us to fulfill our mission to improve lives through cutting-edge products and solutions.
Success stories
Computer-Aided Design pioneer
Machine learning in the Oil and Gas industry – 2054 years of professional training
AI headshot generator
AI headshot generator built with generative AI
Spire Health
Tooploox Partners featuring Spire Health
Let our specialists solve the problems and tackle the challenges that hold you from conquering the world.
Let’s talk