About

Eugenio Culurciello is a Professor of Biomedical Engineering at Purdue University. His research focuses on biomedical engineering, with particular interests in imaging instrumentation, neuroengineering and neurotechnology, and engineered biomaterials and biomechanics. As a faculty member, he contributes to advancing knowledge in these areas through his teaching and research activities, supporting the development of innovative biomedical solutions.

Research topics

• Computer Science
• Artificial Intelligence
• Machine Learning
• Theoretical computer science
• Computer engineering
• Engineering
• Parallel computing

Selected publications

• Semantically complex audio to video generation with audio source separation

  Engineering Applications of Artificial Intelligence · 2025-03-13

  article
  PublisherDOI

• The Evolution of Multimodal Model Architectures

  arXiv (Cornell University) · 2024-05-28 · 4 citations

  preprintOpen accessSenior author

  This work uniquely identifies and characterizes four prevalent multimodal model architectural patterns in the contemporary multimodal landscape. Systematically categorizing models by architecture type facilitates monitoring of developments in the multimodal domain. Distinct from recent survey papers that present general information on multimodal architectures, this research conducts a comprehensive exploration of architectural details and identifies four specific architectural types. The types are distinguished by their respective methodologies for integrating multimodal inputs into the deep neural network model. The first two types (Type A and B) deeply fuses multimodal inputs within the internal layers of the model, whereas the following two types (Type C and D) facilitate early fusion at the input stage. Type-A employs standard cross-attention, whereas Type-B utilizes custom-designed layers for modality fusion within the internal layers. On the other hand, Type-C utilizes modality-specific encoders, while Type-D leverages tokenizers to process the modalities at the model's input stage. The identified architecture types aid the monitoring of any-to-any multimodal model development. Notably, Type-C and Type-D are currently favored in the construction of any-to-any multimodal models. Type-C, distinguished by its non-tokenizing multimodal model architecture, is emerging as a viable alternative to Type-D, which utilizes input-tokenizing techniques. To assist in model selection, this work highlights the advantages and disadvantages of each architecture type based on data and compute requirements, architecture complexity, scalability, simplification of adding modalities, training objectives, and any-to-any multimodal generation capability.

  PublisherOA PDFDOI

• OneCAD: One Classifier for All image Datasets using multimodal learning

  arXiv (Cornell University) · 2023-05-11

  preprintOpen accessSenior author

  Vision-Transformers (ViTs) and Convolutional neural networks (CNNs) are widely used Deep Neural Networks (DNNs) for classification task. These model architectures are dependent on the number of classes in the dataset it was trained on. Any change in number of classes leads to change (partial or full) in the model's architecture. This work addresses the question: Is it possible to create a number-of-class-agnostic model architecture?. This allows model's architecture to be independent of the dataset it is trained on. This work highlights the issues with the current architectures (ViTs and CNNs). Also, proposes a training and inference framework OneCAD (One Classifier for All image Datasets) to achieve close-to number-of-class-agnostic transformer model. To best of our knowledge this is the first work to use Mask-Image-Modeling (MIM) with multimodal learning for classification task to create a DNN model architecture agnostic to the number of classes. Preliminary results are shown on natural and medical image datasets. Datasets: MNIST, CIFAR10, CIFAR100 and COVIDx. Code will soon be publicly available on github.

  PublisherOA PDFDOI

• Reinforcement Learning Approach for Mapping Applications to Dataflow-Based Coarse-Grained Reconfigurable Array

  arXiv (Cornell University) · 2022 · 4 citations

  Senior authorCorresponding
  • Computer Science
  • Computer Science
  • Artificial Intelligence

  The Streaming Engine (SE) is a Coarse-Grained Reconfigurable Array which provides programming flexibility and high-performance with energy efficiency. An application program to be executed on the SE is represented as a combination of Synchronous Data Flow (SDF) graphs, where every instruction is represented as a node. Each node needs to be mapped to the right slot and array in the SE to ensure the correct execution of the program. This creates an optimization problem with a vast and sparse search space for which finding a mapping manually is impractical because it requires expertise and knowledge of the SE micro-architecture. In this work we propose a Reinforcement Learning framework with Global Graph Attention (GGA) module and output masking of invalid placements to find and optimize instruction schedules. We use Proximal Policy Optimization in order to train a model which places operations into the SE tiles based on a reward function that models the SE device and its constraints. The GGA module consists of a graph neural network and an attention module. The graph neural network creates embeddings of the SDFs and the attention block is used to model sequential operation placement. We show results on how certain workloads are mapped to the SE and the factors affecting mapping quality. We find that the addition of GGA, on average, finds 10% better instruction schedules in terms of total clock cycles taken and masking improves reward obtained by 20%.

  PublisherOA PDFDOI

• CERN openlab Technical Workshop

  CERN Document Server (European Organization for Nuclear Research) · 2021-01-01

  other1st authorCorresponding

  <!--HTML-->We present Micron Inc. Deep Learning Accelerator (DLA), its software development kits, compiler and applications. We introduce current and future DLA versions, and plans for additional software tools and support. We also present a summary of current Micron collaboration and DLA-based activities with CERN.

  Publisher

• Continual reinforcement learning in 3D non-stationary environments

  2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · 2020 · 38 citations

  • Computer Science
  • Computer Science
  • Artificial Intelligence

  High-dimensional always-changing environments constitute a hard challenge for current reinforcement learning techniques. Artificial agents, nowadays, are often trained off-line in very static and controlled conditions in simulation such that training observations can be thought as sampled i.i.d. from the entire observations space. However, in real world settings, the environment is often non-stationary and subject to unpredictable, frequent changes. In this paper we propose and openly release CRLMaze, a new benchmark for learning continually through reinforcement in a complex 3D non-stationary task based on ViZDoom and subject to several environmental changes. Then, we introduce an end-to-end model-free continual reinforcement learning strategy showing competitive results with respect to four different baselines and not requiring any access to additional supervised signals, previously encountered environmental conditions or observations.

  PublisherDOI

• Continual Reinforcement Learning in 3D Non-stationary Environments

  2020-06-01 · 5 citations

  preprintOpen access

  High-dimensional always-changing environments constitute a hard challenge for current reinforcement learning techniques. Artificial agents, nowadays, are often trained off-line in very static and controlled conditions in simulation such that training observations can be thought as sampled i.i.d. from the entire observations space. However, in real world settings, the environment is often non-stationary and subject to unpredictable, frequent changes. In this paper we propose and openly release CRLMaze, a new benchmark for learning continually through reinforcement in a complex 3D non-stationary task based on ViZDoom and subject to several environmental changes. Then, we introduce an end-to-end model-free continual reinforcement learning strategy showing competitive results with respect to four different baselines and not requiring any access to additional supervised signals, previously encountered environmental conditions or observations.

  PublisherOA PDFDOI

• Augmented Curiosity: Depth and Optical Flow Prediction for Efficient Exploration

  Lecture notes in computer science · 2019-01-01 · 1 citations

  book-chapterSenior author
  PublisherDOI

• Understanding Complex Single Molecule Emission Patterns with Deep Learning

  Biophysical Journal · 2019-02-01 · 1 citations

  articleOpen access
  PublisherOA PDFDOI

• Deep neural networks compiler for a trace-based accelerator

  Journal of Systems Architecture · 2019-11-05 · 3 citations

  articleSenior author
  PublisherDOI

Recent grants

• IDBR: High-Throughput Instrumentation for Lipid Bilayers and Patch-clamp

  NSF · $679k · 2011–2014

• A Lightweight Event-Driven Network of Biomimetic Image Sensors

  NSF · $288k · 2006–2009

• IDBR: High-Performance Integrated Patch Clamp Amplifiers

  NSF · $560k · 2007–2010

• High-Speed, wide field fluorescent imaging of cortex in freely moving animals

  NIH · $3.7M · 2009–2017

• NIH Grant R56NS065110

  NIH · $495k · 2012

Frequent coauthors

• Andreas G. Andreou

  22 shared

• Wei Tang

  18 shared

• Berin Martini

  Purdue University West Lafayette

  16 shared

• Ayşegül Dündar

  Bilkent University

  16 shared

• Jonghoon Jin

  15 shared

• Joon Hyuk Park

  Jeju National University Hospital

  15 shared

• Vincent A. Pieribone

  John B. Pierce Laboratory

  15 shared

• Pujitha Weerakoon

  Yale University

  14 shared

Education

• Ph.D., Electrical Engineering

  University of California, San Diego

  2005

• M.S., Electrical Engineering

  University of California, San Diego

  2002

• B.S., Electrical Engineering

  University of California, San Diego

  2000