Related papers: Automatic Guide Generation for Stan via NumPyro

We introduce SPAN, a cross-calendar temporal reasoning benchmark, which requires LLMs to perform intra-calendar temporal reasoning and inter-calendar temporal conversion. SPAN features ten cross-calendar temporal reasoning directions, two…

LLMs have demonstrated commendable performance across diverse domains. Nevertheless, formulating high-quality prompts to assist them in their work poses a challenge for non-AI experts. Existing research in prompt engineering suggests…

We formalize the problem of prompt compression for large language models (LLMs) and present a framework to unify token-level prompt compression methods which create hard prompts for black-box models. We derive the distortion-rate function…

We introduce Support Decomposition Variational Inference (SDVI), a new variational inference (VI) approach for probabilistic programs with stochastic support. Existing approaches to this problem rely on designing a single global variational…

Prompt engineering is a new paradigm for enhancing the performance of trained neural network models. For optimizing text-style prompts, existing methods usually individually operate small portions of a text step by step, which either breaks…

Prompt engineering, as an efficient and effective way to leverage Large Language Models (LLM), has drawn a lot of attention from the research community. The existing research primarily emphasizes the importance of adapting prompts to…

Statistical models serve as the cornerstone for hypothesis testing in empirical studies. This paper introduces a new cross-platform Python-based package designed to utilise different likelihood prescriptions via a flexible plug-in system.…

As deep learning models grow, sparsity is becoming an increasingly critical component of deep neural networks, enabling improved performance and reduced storage. However, existing frameworks offer poor support for sparsity. Specialized…

Gaussian state space models have been used for decades as generative models of sequential data. They admit an intuitive probabilistic interpretation, have a simple functional form, and enjoy widespread adoption. We introduce a unified…

Training deep learning (DL) models across Graphics Processing Unit (GPU) clusters is technically challenging. One aspect is that users have to compose command lines to adapt to the heterogeneous launchers, schedulers, affinity options, DL…

Optimizing an expensive-to-query function is a common task in science and engineering, where it is beneficial to keep the number of queries to a minimum. A popular strategy is Bayesian optimization (BO), which leverages probabilistic models…

A natural language database interface (NLDB) can democratize data-driven insights for non-technical users. However, existing Text-to-SQL semantic parsers cannot achieve high enough accuracy in the cross-database setting to allow good…

We use a c-GAN (convolutional generative adversarial) neural network to analyze transliterated text fragments of extant, dead comprehensible, and one dead non-deciphered (Cypro-Minoan) language to establish linguistic affinities. The paper…

Software developers use Application Programming Interfaces (APIs) of libraries and frameworks extensively while writing programs. In this context, the recommendations provided in code completion pop-ups help developers choose the desired…

Large language models (LLMs) can perform a wide range of tasks by following natural language instructions, without the necessity of task-specific fine-tuning. Unfortunately, the performance of LLMs is greatly influenced by the quality of…

Neural language models (LMs) have achieved impressive results on various language-based reasoning tasks by utilizing latent knowledge encoded in their own pretrained parameters. To make this reasoning process more explicit, recent works…

This manuscript provides step-by-step instructions for implementing Bayesian functional regression models using Stan. Extensive simulations indicate that the inferential performance of the methods is comparable to that of state-of-the-art…

While many mainstream languages such as Java, Python, and C# increasingly incorporate functional APIs to simplify programming and improve parallelization/performance, there are no effective techniques that can be used to automatically…

The proposed method, Discriminator Guidance, aims to improve sample generation of pre-trained diffusion models. The approach introduces a discriminator that gives explicit supervision to a denoising sample path whether it is realistic or…

To enhance developer productivity, all modern integrated development environments (IDEs) include code suggestion functionality that proposes likely next tokens at the cursor. While current IDEs work well for statically-typed languages,…