Related papers: nelli: a lightweight frontend for MLIR

Data augmentation is an effective solution to data scarcity in low-resource scenarios. However, when applied to token-level tasks such as NER, data augmentation methods often suffer from token-label misalignment, which leads to…

Machine learning interatomic potentials (MLIPs) enable atomistic simulations with near ab initio accuracy at significantly reduced computational cost, but their broader adoption is often limited by fragmented tooling, limited scalability,…

The proliferation of Large Language Models (LLMs) has opened new frontiers in computing, yet controlling and orchestrating their capabilities beyond simple text generation remains a challenge. Current methods, such as function/tool calling…

Transformer-based language models have revolutionized the field of natural language processing (NLP). However, using these models often involves navigating multiple frameworks and tools, as well as writing repetitive boilerplate code. This…

Vision-language pre-training like CLIP has shown promising performance on various downstream tasks such as zero-shot image classification and image-text retrieval. Most of the existing CLIP-alike works usually adopt relatively large image…

Getting the best performance from the ever-increasing number of hardware platforms has been a recurring challenge for data processing systems. In recent years, the advent of data science with its increasingly numerous and complex types of…

This paper describes Mull, an open-source tool for mutation testing based on the LLVM framework. Mull works with LLVM IR, a low-level intermediate representation, to perform mutations, and uses LLVM JIT for just-in-time compilation. This…

The Deep Learning (DL) community sees many novel topologies published each year. Achieving high performance on each new topology remains challenging, as each requires some level of manual effort. This issue is compounded by the…

Reasoning-Intensive Retrieval (RIR) targets retrieval settings where relevance is mediated by latent inferential links between a query and supporting evidence, rather than semantic similarity. Motivated by the emergent reasoning abilities…

Recently proposed modifications of the standard particle-in-cell (PIC) method resolve long-standing limitations such as exact preservation of physically conserved quantities and unbiased ensemble down-sampling. Such advances pave the way…

Multitier programming languages reduce the complexity of developing distributed systems by developing the distributed system in a single coherent code base. The compiler or the runtime separate the code for the components of the distributed…

We present a neural approach called IRNet for complex and cross-domain Text-to-SQL. IRNet aims to address two challenges: 1) the mismatch between intents expressed in natural language (NL) and the implementation details in SQL; 2) the…

The community is increasingly exploring linear RNNs (LRNNs) as language models, motivated by their expressive power and parallelizability. While prior work establishes the expressivity benefits of LRNNs over transformers, it is unclear what…

The combination of multilingual pre-trained representations and cross-lingual transfer learning is one of the most effective methods for building functional NLP systems for low-resource languages. However, for extremely low-resource…

High-level frameworks for spiking neural networks are a key factor for fast prototyping and efficient development of complex algorithms. Such frameworks have emerged in the last years for traditional computers, but programming neuromorphic…

Text Simplification is an ongoing problem in Natural Language Processing, solution to which has varied implications. In conjunction with the TSAR-2022 Workshop @EMNLP2022 Lexical Simplification is the process of reducing the lexical…

Code optimization is a crucial task that aims to enhance code performance. However, this process is often tedious and complex, highlighting the necessity for automatic code optimization techniques. Reinforcement Learning (RL) has emerged as…

Machine Learning (ML) code, particularly within notebooks, often exhibits lower quality compared to traditional software. Bad practices arise at three distinct levels: general Python coding conventions, the organizational structure of the…

Tensor kernels in machine learning (ML) often correspond to pure mathematical expressions, making term rewriting an attractive strategy for optimization and mapping to specialized hardware accelerators. However, existing ML intermediate…

Meta-compiler frameworks, such as RPython and Graal/Truffle, generate high-performance virtual machines (VMs) from interpreter definitions. Although they generate VMs with high-quality just-in-time (JIT) compilers, they still lack an…