Related papers: Tutorial: $\varphi$-Transductions in OpenFst via t…
Speech-to-text translation (ST), which translates source language speech into target language text, has attracted intensive attention in recent years. Compared to the traditional pipeline system, the end-to-end ST model has potential…
Graph translation is very promising research direction and has a wide range of potential real-world applications. Graph is a natural structure for representing relationship and interactions, and its translation can encode the intrinsic…
PHAST is a software package written in standard Fortran, with MPI and CUDA extensions, able to efficiently perform parallel multicanonical Monte Carlo simulations of single or multiple heteropolymeric chains, as coarse-grained models for…
Achieving brain-like density and performance in neuromorphic computers necessitates scaling down the size of nanodevices emulating neuro-synaptic functionalities. However, scaling nanodevices results in reduction of programming resolution…
We propose a novel approach for channel state information (CSI) compression in multiple-input multiple-output orthogonal frequency division multiplexing (MIMO-OFDM) systems, where the frequency-domain channel matrix is treated as a…
The widespread application of artificial intelligence in health research is currently hampered by limitations in data availability. Distributed learning methods such as federated learning (FL) and shared learning (SL) are introduced to…
The experimental evaluation of fault-tolerance studies relies on tools that inject errors while programs are running, and then monitor the execution and the output for faulty execution. In particular, the established methodology in…
Table structure recognition is a crucial part of document image analysis domain. Its difficulty lies in the need to parse the physical coordinates and logical indices of each cell at the same time. However, the existing methods are…
Improving Transformer efficiency has become increasingly attractive recently. A wide range of methods has been proposed, e.g., pruning, quantization, new architectures and etc. But these methods are either sophisticated in implementation or…
Supervised fine-tuning (SFT) is a fundamental post-training strategy to align Large Language Models (LLMs) with human intent. However, traditional SFT often ignores the one-to-many nature of language by forcing alignment with a single…
We present the Fast Newton Transform (FNT), an algorithm for performing $m$-variate Newton interpolation in downward closed polynomial spaces with time complexity $\mathcal{O}(|A|m\overline{n})$. Here, $A$ is a downward closed set of…
In this study, we introduce an innovative methodology for the design of mm-Wave passive networks that leverages knowledge transfer from a pre-trained synthesis neural network (NN) model in one technology node and achieves swift and reliable…
We study Transformers on the task \emph{program trace generation} (PTG), where models produce step-by-step execution traces for synthetic programs. Unlike existing algorithmic problems, PTG externalizes reasoning through long traces where…
Many interesting and fundamentally practical optimization problems, ranging from optics, to signal processing, to radar and acoustics, involve constraints on the Fourier transform of a function. It is well-known that the {\em fast Fourier…
This paper presents a framework based on Weighted Finite-State Transducers (WFST) to simplify the development of modifications for RNN-Transducer (RNN-T) loss. Existing implementations of RNN-T use CUDA-related code, which is hard to extend…
A new method is presented for solving Poisson's equation inside an open-ended rectangular pipe. The method uses Fast Fourier Transforms (FFTs) to perform mixed convolutions and correlations of the charge density with the Green function.…
Large-scale text-to-image (T2I) diffusion models excel at open-domain synthesis but still struggle with precise text rendering, especially for multi-line layouts, dense typography, and long-tailed scripts such as Chinese. Prior solutions…
Simultaneous speech translation (SST) takes streaming speech input and generates text translation on the fly. Existing methods either have high latency due to recomputation of input representations, or fall behind of offline ST in…
Transliterating related languages that use different scripts into a common script is effective for improving crosslingual transfer in downstream tasks. However, this methodology often makes pretraining a model from scratch unavoidable, as…
Speech processing requires very efficient methods and algorithms. Finite-state transducers have been shown recently both to constitute a very useful abstract model and to lead to highly efficient time and space algorithms in this field. We…