Related papers: FlexCTC: GPU-powered CTC Beam Decoding With Advanc…
Beam search is the go-to method for decoding auto-regressive machine translation models. While it yields consistent improvements in terms of BLEU, it is only concerned with finding outputs with high model likelihood, and is thus agnostic to…
Conditional text generation often requires lexical constraints, i.e., which words should or shouldn't be included in the output text. While the dominant recipe for conditional text generation has been large-scale pretrained language models…
Recent advances in text-guided image compression have shown great potential to enhance the perceptual quality of reconstructed images. These methods, however, tend to have significantly degraded pixel-wise fidelity, limiting their…
The rise of Generative AI introduces a new class of HPC workloads that integrates lightweight LLMs with traditional high-throughput applications to accelerate scientific discovery. The current design of HPC clusters is inadequate to support…
The F-statistic is an established method to search for continuous gravitational waves from spinning neutron stars. Prix et al. (2011) introduced a variant for transient quasi-monochromatic signals. Possible astrophysical scenarios for such…
Simulation of x-ray projection images plays an important role in cone beam CT (CBCT) related research projects. A projection image contains primary signal, scatter signal, and noise. It is computationally demanding to perform accurate and…
Deep learning has brought significant improvements to the field of cross-modal representation learning. For tasks such as text-to-speech (TTS), voice conversion (VC), and automatic speech recognition (ASR), a cross-modal fine-grained…
Convolutional neural networks have become an essential element of spatial deep learning systems. In the prevailing architecture, the convolution operation is performed with Fast Fourier Transforms (FFT) electronically in GPUs. The…
Generative retrieval has emerged as a powerful paradigm for LLM-based recommendation. However, industrial recommender systems often benefit from restricting the output space to a constrained subset of items based on business logic (e.g.…
Standard transformer-based language models, while powerful for general text, often struggle with the fine-grained syntax and entity relationships in complex technical, engineering documents. To address this, we propose the Contextual Graph…
Neural machine translation (NMT) is nowadays commonly applied at the subword level, using byte-pair encoding. A promising alternative approach focuses on character-level translation, which simplifies processing pipelines in NMT…
Realizing the full potential of quantum computation requires quantum error correction (QEC), with most recent breakthrough demonstrations of QEC using the surface code. QEC codes use multiple noisy physical qubits to encode information in…
This article proposes a convenient tool for decoding the output of neural networks trained by Connectionist Temporal Classification (CTC) for handwritten text recognition. We use regular expressions to describe the complex structures…
As the basis of generative AI, an autoregressive model requires the generation of a new token depending on all the previously generated tokens, which brings high quality but also restricts the model to generate tokens one by one, forming a…
This paper describes NCRF++, a toolkit for neural sequence labeling. NCRF++ is designed for quick implementation of different neural sequence labeling models with a CRF inference layer. It provides users with an inference for building the…
The end-to-end nature of neural machine translation (NMT) removes many ways of manually guiding the translation process that were available in older paradigms. Recent work, however, has introduced a new capability: lexically constrained or…
FPGA-based hardware accelerators for convolutional neural networks (CNNs) have obtained great attentions due to their higher energy efficiency than GPUs. However, it is challenging for FPGA-based solutions to achieve a higher throughput…
CG-Kit is a new code generation toolkit that we propose as a solution for portability and maintainability for scientific computing applications. The development of CG-Kit is rooted in the urgent need created by the shifting landscape of…
We consider the problem of transposing tensors of arbitrary dimension and describe TTC, an open source domain-specific parallel compiler. TTC generates optimized parallel C++/CUDA C code that achieves a significant fraction of the system's…
We compare the fast training and decoding speed of RETURNN of attention models for translation, due to fast CUDA LSTM kernels, and a fast pure TensorFlow beam search decoder. We show that a layer-wise pretraining scheme for recurrent…