Related papers: Tutorial: $\varphi$-Transductions in OpenFst via t…

We propose a) a Language Agnostic end-to-end Speech Translation model (LAST), and b) a data augmentation strategy to increase code-switching (CS) performance. With increasing globalization, multiple languages are increasingly used…

In contemporary deep learning, a prevalent and effective workflow for solving low-data problems is adapting powerful pre-trained foundation models (FMs) to new tasks via parameter-efficient fine-tuning (PEFT). However, while empirically…

Multimodal classification is a core task in human-centric machine learning. We observe that information is highly complementary across modalities, thus unimodal information can be drastically sparsified prior to multimodal fusion without…

Performing inference in statistical models with an intractable likelihood is challenging, therefore, most likelihood-free inference (LFI) methods encounter accuracy and efficiency limitations. In this paper, we present the implementation of…

Since the advent of reasoning-based large language models, many have found great success from distilling reasoning capabilities into student models. Such techniques have significantly bridged the gap between reasoning and standard LLMs on…

We present a parallel FFT algorithm for SIMD systems following the `Transpose Algorithm' approach. The method is based on the assignment of the data field onto a 1-dimensional ring of systolic cells. The systolic array can be universally…

Transducers extend finite state automata with outputs, and describe transformations from strings to strings. Sequential transducers, which have a deterministic behaviour regarding their input, are of particular interest. However, unlike…

The Parameter-Efficient Fine-Tuning (PEFT) method, which adjusts or introduces fewer trainable parameters to calibrate pre-trained models on downstream tasks, has become a recent research interest. However, existing PEFT methods within the…

Extremely large-scale multiple-input multiple-output (XL-MIMO) systems, operating in the near-field region due to their massive antenna arrays, are key enablers of next-generation wireless communications but face significant challenges in…

This paper proposes a multivariable extremum seeking scheme using Fast Fourier Transform (FFT) for a network of subsystems working towards optimizing the sum of their local objectives, where the overall objective is the only available…

Large language models (LLMs) are popular around the world due to their powerful understanding capabilities. As the core component of LLMs, accelerating Transformer through parallelization has gradually become a hot research topic. Mask…

We present an in-place implementation of the cryptographic permutation \textbf{Gimli}, a NIST round 2 candidate for lightweight cryptography, and provide an upper bound for the required quantum resource in depth and gate-counts. In…

This paper describes the conversion of a Hidden Markov Model into a sequential transducer that closely approximates the behavior of the stochastic model. This transformation is especially advantageous for part-of-speech tagging because the…

The algorithm behind the Fast Fourier Transform has a simple yet beautiful geometric interpretation that is often lost in translation in a classroom. This article provides a visual perspective which aims to capture the essence of it.

Full fine-tuning is a popular approach to adapt Transformer-based pre-trained large language models to a specific downstream task. However, the substantial requirements for computational power and storage have discouraged its widespread…

Non-differentiable and constrained optimization play a key role in machine learning, signal and image processing, communications, and beyond. For high-dimensional minimization problems involving large datasets or many unknowns, the…

While multilingual pretrained language models (LMs) fine-tuned on a single language have shown substantial cross-lingual task transfer capabilities, there is still a wide performance gap in semantic parsing tasks when target language…

Parallel algorithms relying on synchronous parallelization libraries often experience adverse performance due to global synchronization barriers. Asynchronous many-task runtimes offer task futurization capabilities that minimize or remove…

The Transformer architecture is shown to provide a powerful machine transduction framework for online handwritten gestures corresponding to glyph strokes of natural language sentences. The attention mechanism is successfully used to create…

Tunnel ionization (TI) underlies many important ultrafast processes, such as high-harmonic generation and strong-field ionization. Among the existing theories for TI, many-electron weak-field asymptotic theory (ME-WFAT) is by design capable…