相关论文: Generalizing the Paige-Tarjan Algorithm by Abstrac…

The automation of ab initio simulations is essential in view of performing high-throughput (HT) computational screenings oriented to the discovery of novel materials with desired physical properties. In this work, we propose algorithms and…

Decompilation converts machine code into human-readable form, enabling analysis and debugging without source code. However, fidelity issues often degrade the readability and semantic accuracy of decompiled output. Existing methods, such as…

Simulation of quantum chemistry is expected to be a principal application of quantum computing. In quantum simulation, a complicated Hamiltonian describing the dynamics of a quantum system is decomposed into its constituent terms, where the…

Fine-grained object retrieval aims to learn discriminative representation to retrieve visually similar objects. However, existing top-performing works usually impose pairwise similarities on the semantic embedding spaces or design a…

Designers of statistical machine translation (SMT) systems have begun to employ tree-structured translation models. Systems involving tree-structured translation models tend to be complex. This article aims to reduce the conceptual…

Recently, pre-trained language representation flourishes as the mainstay of the natural language understanding community, e.g., BERT. These pre-trained language representations can create state-of-the-art results on a wide range of…

The Transformer model is widely successful on many natural language processing tasks. However, the quadratic complexity of self-attention limit its application on long text. In this paper, adopting a fine-to-coarse attention mechanism on…

Two major sources of training data exist for post-training modern language models: online (model-generated rollouts) data, and offline (human or other-model demonstrations) data. These two types of data are typically used by approaches like…

In many areas of science and engineering, computer simulations are widely used as proxies for physical experiments, which can be infeasible or unethical. Such simulations can often be computationally expensive, and an emulator can be…

It has been suggested that large language models such as GPT-4 have acquired some form of understanding beyond the correlations among the words in text including some understanding of mathematics as well. Here, we perform a critical inquiry…

GPT is an auto-regressive Transformer-based pre-trained language model which has attracted a lot of attention in the natural language processing (NLP) domain due to its state-of-the-art performance in several downstream tasks. The success…

Imaginary-time evolution, an important technique in tensor network and quantum Monte Carlo algorithms on classical computers, has recently been adapted to quantum computing. In this study, we focus on probabilistic imaginary-time evolution…

Abstraction is a commonly used process to represent some low-level system by a more coarse specification with the goal to omit unnecessary details while preserving important aspects. While recent work on abstraction in the situation…

We investigate the capability of a transformer pretrained on natural language to generalize to other modalities with minimal finetuning -- in particular, without finetuning of the self-attention and feedforward layers of the residual…

To obtain accurate results in numerical computation, high-precision arithmetic is a straightforward approach. However, most processors lack hardware support for floating-point formats beyond double precision (FP64). Double-word arithmetic…

We introduce Probabilistic Guarded Kleene Algebra with Tests (ProbGKAT), an extension of GKAT that allows reasoning about uninterpreted imperative programs with probabilistic branching. We give its operational semantics in terms of special…

Generative Pre-trained Transformer models, known as GPT or OPT, set themselves apart through breakthrough performance across complex language modelling tasks, but also by their extremely high computational and storage costs. Specifically,…

The transformer extends its success from the language to the vision domain. Because of the stacked self-attention and cross-attention blocks, the acceleration deployment of vision transformer on GPU hardware is challenging and also rarely…

Two important enhanced sampling algorithms, simulated (ST) and parallel (PT) tempering, are commonly used when ergodic simulations may be hard to achieve, e.g, due to a phase space separated by large free-energy barriers. This is so for…

This paper describes an abstract machine for linguistic formalisms that are based on typed feature structures, such as HPSG. The core design of the abstract machine is given in detail, including the compilation process from a high-level…