Related papers: Live Objects All The Way Down: Removing the Barrie…

We demonstrate the utility of the Multi-Level Intermediate Representation (MLIR) for quantum computing. Specifically, we extend MLIR with a new quantum dialect that enables the expression and compilation of common quantum assembly…

Do we still need to represent objects explicitly in multimodal large language models (MLLMs)? To one extreme, pre-trained encoders convert images into visual tokens, with which objects and spatiotemporal relationships may be implicitly…

As language models continue to scale, Large Language Models (LLMs) have exhibited emerging capabilities in In-Context Learning (ICL), enabling them to solve language tasks by prefixing a few in-context demonstrations (ICDs) as context.…

Large language models promise a broad set of functions, but when not given a specific objective, they default to generic results. We demonstrate that inferring the user's in-the-moment objective, then rapidly optimizing for that singular…

Mobile edge clouds (MECs) bring the benefits of the cloud closer to the user, by installing small cloud infrastructures at the network edge. This enables a new breed of real-time applications, such as instantaneous object recognition and…

Medical AI systems face two fundamental limitations. First, conventional vision-language models (VLMs) perform single-pass inference, yielding black-box predictions that cannot be audited or explained in clinical terms. Second, iterative…

Large Language Models (LLMs) have become integral to software engineering workflows, yet their effectiveness degrades significantly in multi-turn conversations. Recent studies demonstrate an average 39% performance drop when instructions…

Large Language Models (LLMs) have demonstrated remarkable capabilities across a variety of software engineering and coding tasks. However, their application in the domain of code and compiler optimization remains underexplored. Training…

Advances in large language models (LLMs) and real-time speech recognition now make it possible to issue any graphical user interface (GUI) action through natural language and receive the corresponding system response directly through the…

High-level applications, such as machine learning, are evolving from simple models based on multilayer perceptrons for simple image recognition to much deeper and more complex neural networks for self-driving vehicle control systems.The…

Streamliner constraints reduce the search space of combinatorial problems by ruling out portions of the solution space. We adapt the StreamLLM approach, which uses Large Language Models (LLMs) to generate streamliners for Constraint…

Retrieval-Augmented Generation (RAG) systems combine vector similarity search with large language models (LLMs) to deliver accurate, context-aware responses. However, co-locating the vector retriever and the LLM on shared GPU infrastructure…

With the rapid advance of machine learning (ML) technology, large language models (LLMs) are increasingly explored as an intelligent tool to generate program code from natural language specifications. However, existing evaluations of LLMs…

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…

This paper is about the interface between languages which use a garbage collector and those which use fancy types for safe manual memory management. Garbage collection is the traditional memory management scheme for functional languages,…

Large Language Models (LLMs) can help robots reason about abstract task specifications. This requires augmenting classical representations of the environment used by robots, such as point-clouds and meshes, with natural language-based…

Recent advancements in 3D Large Language Models (LLMs) have demonstrated promising capabilities for 3D scene understanding. However, previous methods exhibit deficiencies in general referencing and grounding capabilities for intricate scene…

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…

Large language models (LLMs) have shown remarkable abilities to generate code, however their ability to develop software for embedded systems, which requires cross-domain knowledge of hardware and software has not been studied. In this…

Metamorphic testing (MT) has proven to be a successful solution to automating testing and addressing the oracle problem. However, it entails manually deriving metamorphic relations (MRs) and converting them into an executable form; these…