Programming Light Propagation for Efficient Artificial Intelligence

Chat with Graph Search

Ask any question about EPFL courses, lectures, exercises, research, news, etc. or try the example questions below.

DISCLAIMER: The Graph Chatbot is not programmed to provide explicit or categorical answers to your questions. Rather, it transforms your questions into API requests that are distributed across the various IT services officially administered by EPFL. Its purpose is solely to collect and recommend relevant references to content that you can explore to help you answer your questions.

Computing has long been central to technological advancements, where each leap in compute power has catalyzed applications once thought impossible, such as smartphones. Recently, the exponential growth in the compute demand of artificial intelligence (AI) ...

Having a single neural network to handle a wide and varied range of tasks and modalities has been a long-standing goal. Such a model brings notable advantages, such as test-time computational efficiency, modality fusion, and reduced model size. Our goal in ...

Machine translation (MT) systems and language models (LMs) have demonstrated impressive performance in recent years, driven by advances in architecture, algorithms, and the scaling of parameters and training data. Despite the ability of these models to int ...

In this concise contribution, it is demonstrated that Recurrent Neural Networks (RNNs) based on Gated Recurrent Unit (GRU) architecture, possess the capability to learn the complex dynamics of rate-and-state friction (RSF) laws from synthetic data. The dat ...

Segmenting brain tumors is a critical task in medical imaging that relies on advanced deep-learning methods. However, effectively handling complex tumor regions requires more comprehensive and advanced strategies to overcome challenges such as computationa ...

Finding proper collective variables for complex systems and processes is one of the most challenging tasks in simulations, which limits the interpretation of experimental and simulated data and the application of enhanced sampling techniques. Here, we prop ...

Research in speech processing has largely focused on source-system modeling, where vocal fold vibrations serve as the source and the vocal cavity's articulations as the system. Nonetheless, speech production includes a complex combination of physiological ...

In this study, we employed traditional methods and deep learning models to improve resolution and quality of low-resolution AFM images made under standard ambient scanning. Both traditional methods and deep learning models were benchmarked and quantified r ...

Sign languages are rich visual languages that use both manual features like handshape, movement, and location and non-manual features such as facial expressions, head movements, and body posture to convey information. Sign language learning technologies ha ...

The ESA Euclid mission will survey more than 14 000 deg2 of the sky in visible and near-infrared wavelengths, mapping the extragalactic sky to constrain our cosmological model of the Universe. Although the survey focusses on regions further than 15 from th ...

In supervised learning, the regularization path is sometimes used as a convenient theoretical proxy for the optimization path of gradient descent initialized from zero. In this paper, we study a modification of the regularization path for infinite-width 2- ...

The emergence of van der Waals (vdW) materials resulted in the discovery of their high optical, mechanical, and electronic anisotropic properties, immediately enabling countless novel phenomena and applications. Such success inspired an intensive search fo ...

We present GigaPose, a fast, robust, and accurate method for CAD-based novel object pose estimation in RGB images. GigaPose first leverages discriminative "templates", rendered images of the CAD models, to recover the out-of-plane rotation and then uses pa ...

We investigate the degradation mechanisms of In0.2Ga0.8N/GaN light emitting diodes through combined experimental analysis and simulations. The devices were submitted to constant current stress at 100 mA. Depending on the measuring current level, two degrad ...

Motivated by the substantial achievements of Large Language Models (LLMs) in the field of natural language processing, recent research has commenced investigations into the application of LLMs for complex, long-horizon sequential task planning challenges i ...

Programming Light Propagation for Efficient Artificial Intelligence

Chat with Graph Search

Optical Processors for AI Computing and Networking

Scaling the Modalities in Multimodal Foundation Models

From Preprocessing to Evaluation: The Role of External Knowledge in Advancing Language Models and Machine Translation

Data-driven dynamic friction models based on Recurrent Neural Networks

LIU-NET: lightweight Inception U-Net for efficient brain tumor segmentation from multimodal 3D MRI images

Inherent Structural Descriptors Via Machine Learning

Towards Integrated Processing of Physiological Signals and Speech

Deep learning for enhancement of low-resolution and noisy scanning probe microscopy images

Advancing Phonology-Based Sign Language Assessment: From Learner to Machine-Generated Videos

Euclid: Detecting Solar System objects in Euclid images and classifying them using Kohonen self-organising maps

On the Effect of Initialization: The Scaling Path of 2-Layer Neural Networks

Exploring van der Waals materials with high anisotropy: geometrical and optical approaches

GigaPose: Fast and Robust Novel Object Pose Estimation via One Correspondence

Investigation and modeling of the role of interface defects in the optical degradation of InGaN/GaN LEDs

ISR-LLM: Iterative Self-Refined Large Language Model for Long-Horizon Sequential Task Planning