Related papers: Deegen: A JIT-Capable VM Generator for Dynamic Lan…

Encoder-decoder transformer models have achieved great success on various vision-language (VL) tasks, but they suffer from high inference latency. Typically, the decoder takes up most of the latency because of the auto-regressive decoding.…

Traditionally, designs are written in Verilog hardware description language (HDL) and debugged by hardware engineers. While this approach is effective, it is time-consuming and error-prone for complex designs. Large language models (LLMs)…

I describe an approach to compiling common idioms in R code directly to native machine code and illustrate it with several examples. Not only can this yield significant performance gains, but it allows us to use new approaches to computing…

The integration of converter-interfaced generation (CIG) from renewable energy sources poses challenges to the stability and transient behavior of electric power systems. Understanding the dynamic behavior of low-inertia power systems is…

Large language model (LLM) agents often suffer from high reasoning overhead, excessive token consumption, unstable execution, and inability to reuse past experiences in complex tasks like business queries, tool use, and workflow…

Cost of serving large language models (LLM) is high, but the expensive and scarce GPUs are poorly efficient when generating tokens sequentially, unless the batch of sequences is enlarged. However, the batch size is limited by some…

Large Language Models (LLMs) have shown remarkable progress in automated code generation. Yet, LLM-generated code may contain errors in API usage, class, data structure, or missing project-specific information. As much of this…

Verbal and non-verbal human reaction generation is a challenging task, as different reactions could be appropriate for responding to the same behaviour. This paper proposes the first multiple and multimodal (verbal and nonverbal)…

Recently, there has been a surging interest in using large language models (LLMs) for Verilog code generation. However, the existing approaches are limited in terms of the quality of the generated Verilog code. To address such limitations,…

Jjodel is a cloud-based reflective platform designed to address the challenges of Model-Driven Engineering (MDE), particularly the cognitive complexity and usability barriers often encountered in existing model-driven tools. This article…

Data-intensive applications, ranging from large-scale retrieval systems to advanced data pipelines, are increasingly bottlenecked by the processing of highly redundant text corpora. We present Merlin, a local-first, agnostic,…

Just-in-time (JIT) compilers are used by many modern programming systems in order to improve performance. Bugs in JIT compilers provide exploitable security vulnerabilities and debugging them is difficult as they are large, complex, and…

In computer science, students are encouraged to learn various programming languages such as Python, C++, and Java, equipping them with a broad range of technical skills and problem-solving capabilities. Nevertheless, the design of objective…

Automated code generation is a pivotal capability of large language models (LLMs). However, assessing this capability in real-world scenarios remains challenging. Previous methods focus more on low-level code generation, such as model…

Traditional compilers operate on a single generic intermediate representation (IR). These IRs are usually low-level and close to machine instructions. As a result, optimizations relying on domain-specific information are either not possible…

The growing proliferation of FPGAs and High-level Synthesis (HLS) tools has led to a large interest in designing hardware accelerators for complex operations and algorithms. However, existing HLS toolflows typically require a significant…

We present a multi-level quantum-classical intermediate representation (IR) that enables an optimizing, retargetable, ahead-of-time compiler for available quantum programming languages. To demonstrate our architecture, we leverage our…

Automated reverse engineering of HTML/CSS code from UI screenshots is an important yet challenging problem with broad applications in website development and design. In this paper, we propose a novel vision-code transformer (ViCT) composed…

Large language models (LLMs) have demonstrated impressive capabilities across various NLP tasks. Additionally, LLMs are also highly valuable in supporting software engineering tasks, particularly in the field of code generation. Automatic…

The emergence of machine learning, image and audio processing on edge devices has motivated research towards power efficient custom hardware accelerators. Though FPGAs are an ideal target for energy efficient custom accelerators, the…