Related papers: nelli: a lightweight frontend for MLIR
Presolving has become an essential component of modern MIP solvers both in terms of computational performance and numerical robustness. In this paper, we present PaPILO, a new C++ header-only library that provides a large set of presolving…
Quantum Intermediate Representation (QIR) is a Microsoft-developed, LLVM-based intermediate representation for quantum program compilers. QIR aims to provide a general solution for quantum program compilers independent of front-end…
The scaling of large language models (LLMs) is currently bottlenecked by the rigidity of distributed programming. While high-performance libraries like CuBLAS and NCCL provide optimized primitives, they lack the flexibility required for…
We propose the Limited Multi-Label (LML) projection layer as a new primitive operation for end-to-end learning systems. The LML layer provides a probabilistic way of modeling multi-label predictions limited to having exactly k labels. We…
The paradigm of Multimodal Large Language Models (MLLMs) offers a promising blueprint for advancing the electromagnetic (EM) domain. However, prevailing approaches often deviate from the native MLLM paradigm, instead using task-specific or…
One way to write fast programs is to explore the potential parallelism and take advantage of the high number of cores available in microprocessors. This can be achieved by manually specifying which code executes on which thread, by using…
The main alternatives nowadays to deal with sequences are Recurrent Neural Networks (RNN), Convolutional Neural Networks (CNN) architectures and the Transformer. In this context, RNN's, CNN's and Transformer have most commonly been used as…
Large Language Models (LLMs) have demonstrated exceptional proficiency in text understanding and embedding tasks. However, their potential in multimodal representation, particularly for item-to-item (I2I) recommendations, remains…
Modern data analytics workloads combine relational data processing with machine learning (ML). Most DBMS handle these workloads by offloading these ML operations to external specialized ML systems. While both DBMS and ML systems go to great…
Spiking neural networks and neuromorphic hardware platforms that simulate neuronal dynamics are getting wide attention and are being applied to many relevant problems using Machine Learning. Despite a well-established mathematical…
Polyhedral optimisation, a methodology that views nested loops as polyhedra and searches for their optimal transformation regarding specific objectives (parallelism, locality, etc.), sounds promising for mitigating difficulties in…
Data oriented applications, usually written in a high-level, general-purpose programming language (such as Java) interact with database through a coarse interface. Informally, the text of a query is built on the application side (either via…
Creating high-quality, large-scale datasets for large language models (LLMs) often relies on resource-intensive, GPU-accelerated models for quality filtering, making the process time-consuming and costly. This dependence on GPUs limits…
Representation learning is currently a very hot topic in modern machine learning, mostly due to the great success of the deep learning methods. In particular low-dimensional representation which discriminates classes can not only enhance…
A wide range of transformer-based language models have been proposed for information retrieval tasks. However, including transformer-based models in retrieval pipelines is often complex and requires substantial engineering effort. In this…
The development of high-quality text embeddings is increasingly drifting toward an exclusionary future, defined by three critical barriers: prohibitive computational costs, a narrow linguistic focus that neglects most of the world's…
Mixed integer linear programming (MILP) solvers expose hundreds of parameters that have an outsized impact on performance but are difficult to configure for all but expert users. Existing machine learning (ML) approaches require training on…
In this paper, we present Hexagon-MLIR,an open-source compilation stack that targets Qualcomm Hexagon Neural Processing Unit (NPU) and provides unified support for lowering Triton kernels and PyTorch models . Built using the MLIR framework,…
I present the most fundamental features of an implemented system designed to manipulate representations of regular languages. The system is structured into two layers, allowing regular languages to be represented in an increasingly compact,…
Integer Linear Programming (ILP) has a broad range of applications in various areas of artificial intelligence. Yet in spite of recent advances, we still lack a thorough understanding of which structural restrictions make ILP tractable.…