Related papers: nelli: a lightweight frontend for MLIR

The Message-Passing Interface (MPI) and C++ form the backbone of high-performance computing, but MPI only provides C and Fortran bindings. While this offers great language interoperability, high-level programming languages like C++ make…

Neural program embeddings have demonstrated considerable promise in a range of program analysis tasks, including clone identification, program repair, code completion, and program synthesis. However, most existing methods generate neural…

Data assimilation is crucial in a wide range of applications, but it often faces challenges such as high computational costs due to data dimensionality and incomplete understanding of underlying mechanisms. To address these challenges, this…

Multimodal Large Language Models (MLLMs) achieve versatility by reformulating diverse tasks into a unified instruction-following framework via instruction tuning. However, real-world deployment requires continuous adaptation to emerging…

Large language models (LLMs) are renowned for their extensive linguistic knowledge and strong generalization capabilities, but their high computational demands make them unsuitable for resource-constrained environments. In contrast, small…

As the capabilities of quantum computing hardware continue to rise, algorithms that exploit them are becoming increasingly complex. These developments increase the need for sophisticated compilation frameworks that translate high-level…

WebAssembly (Wasm) is a portable bytecode format that serves as a compilation target for high-level languages, enabling their secure and efficient execution across diverse platforms, including web browsers and embedded systems. To improve…

PiML (read $\pi$-ML, /`pai`em`el/) is an integrated and open-access Python toolbox for interpretable machine learning model development and model diagnostics. It is designed with machine learning workflows in both low-code and high-code…

Mixed Integer Linear Programming (MILP) is essential for modeling complex decision-making problems but faces challenges in computational tractability and requires expert formulation. Current deep learning approaches for MILP focus on…

We motivate the design and implementation of a platform-neutral compute intermediate language (PENCIL) for productive and performance-portable accelerator programming.

The ability of neural networks to represent more features than neurons makes interpreting them challenging. This phenomenon, known as superposition, has spurred efforts to find architectures that are more interpretable than standard…

Multimodal Large Language Models (MLLMs) are evaluated on various benchmarks, such as image captioning, visual question answering, and reasoning. However, many of these benchmarks include overly simple or uninformative samples, complicating…

Writing high-performance code requires significant expertise in the programming language, compiler optimizations, and hardware knowledge. This often leads to poor productivity and portability and is inconvenient for a non-programmer…

While large language models demonstrate remarkable capabilities at task-specific applications through fine-tuning, extending these benefits across diverse languages is essential for broad accessibility. However, effective cross-lingual…

Implicit Neural Representations (INRs) aim to parameterize discrete signals through implicit continuous functions. However, formulating each image with a separate neural network~(typically, a Multi-Layer Perceptron (MLP)) leads to…

Language model (LM) pretraining has led to consistent improvements in many NLP downstream tasks, including named entity recognition (NER). In this paper, we present T-NER (Transformer-based Named Entity Recognition), a Python library for…

Over the past few decades, neuroscience experiments have become increasingly complex and naturalistic. Experimental design has in turn become more challenging, as experiments must conform to an ever-increasing diversity of design…

Mechanistic interpretability is an emerging diagnostic approach for neural models that has gained traction in broader natural language processing domains. This paradigm aims to provide attribution to components of neural systems where…

Semantic word embeddings represent the meaning of a word via a vector, and are created by diverse methods. Many use nonlinear operations on co-occurrence statistics, and have hand-tuned hyperparameters and reweighting methods. This paper…

With the push towards Exascale computing and data-driven methods, problem sizes have increased dramatically, increasing the computational requirements of the underlying algorithms. This has led to a push to offload computations to general…