An Infrastructure Software Perspective Toward Computation Offloading between Executable Specifications and Foundation Models
- URL: http://arxiv.org/abs/2501.02829v1
- Date: Mon, 06 Jan 2025 08:02:28 GMT
- Title: An Infrastructure Software Perspective Toward Computation Offloading between Executable Specifications and Foundation Models
- Authors: Dezhi Ran, Mengzhou Wu, Yuan Cao, Assaf Marron, David Harel, Tao Xie,
- Abstract summary: Foundation Models (FMs) have become essential components in modern software systems, excelling in computation tasks such as pattern recognition and unstructured data processing.<n>Their capabilities are complemented by the precision, verifiability, and deterministic nature of executable specifications, such as symbolic programs.<n>This paper explores a new perspective on offloading, proposing a framework that strategically distributes computational tasks between FMs and executable specifications based on their respective strengths.
- Score: 11.035290353039079
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Foundation Models (FMs) have become essential components in modern software systems, excelling in tasks such as pattern recognition and unstructured data processing. However, their capabilities are complemented by the precision, verifiability, and deterministic nature of executable specifications, such as symbolic programs. This paper explores a new perspective on computation offloading, proposing a framework that strategically distributes computational tasks between FMs and executable specifications based on their respective strengths. We discuss the potential design of an infrastructure software framework to enable this offloading, focusing on key mechanisms such as task decomposition, resource allocation, and adaptive optimization. Furthermore, we identify critical technical challenges, including semantic-gap resolution, reliability, and scalability, that must be addressed to realize this approach. By leveraging the complementary strengths of FMs and symbolic programs, this perspective lays the groundwork for advancing hybrid software systems that are both efficient and reliable.
Related papers
- Modeling and Performance Analysis for Semantic Communications Based on Empirical Results [53.805458017074294]
We propose an Alpha-Beta-Gamma (ABG) formula to model the relationship between the end-to-end measurement and SNR.
For image reconstruction tasks, the proposed ABG formula can well fit the commonly used DL networks, such as SCUNet, and Vision Transformer.
To the best of our knowledge, this is the first theoretical expression between end-to-end performance metrics and SNR for semantic communications.
arXiv Detail & Related papers (2025-04-29T06:07:50Z) - Semi-Automated Design of Data-Intensive Architectures [49.1574468325115]
This paper introduces a development methodology for data-intensive architectures.
It guides architects in (i) designing a suitable architecture for their specific application scenario, and (ii) selecting an appropriate set of concrete systems to implement the application.
We show that the description languages we adopt can capture the key aspects of data-intensive architectures proposed by researchers and practitioners.
arXiv Detail & Related papers (2025-03-21T16:01:11Z) - STAR: A Foundation Model-driven Framework for Robust Task Planning and Failure Recovery in Robotic Systems [5.426894918217948]
STAR (Smart Task Adaptation and Recovery) is a novel framework that synergizes Foundation Models (FMs) with dynamically expanding Knowledge Graphs (KGs)
FMs offer remarkable generalization and contextual reasoning, but their limitations hinder reliable deployment.
We show that STAR demonstrated an 86% task planning accuracy and 78% recovery success rate, showing significant improvements over baseline methods.
arXiv Detail & Related papers (2025-03-08T05:05:21Z) - Ten Challenging Problems in Federated Foundation Models [55.343738234307544]
Federated Foundation Models (FedFMs) represent a distributed learning paradigm that fuses general competences of foundation models as well as privacy-preserving capabilities of federated learning.
This paper provides a comprehensive summary of the ten challenging problems inherent in FedFMs, encompassing foundational theory, utilization of private data, continual learning, unlearning, Non-IID and graph data, bidirectional knowledge transfer, incentive mechanism design, game mechanism design, model watermarking, and efficiency.
arXiv Detail & Related papers (2025-02-14T04:01:15Z) - Take What You Need: Flexible Multi-Task Semantic Communications with Channel Adaptation [51.53221300103261]
This article introduces a novel channel-adaptive and multi-task-aware semantic communication framework based on a masked auto-encoder architecture.
A channel-aware extractor is employed to dynamically select relevant information in response to real-time channel conditions.
Experimental results demonstrate the superior performance of our framework compared to conventional methods in tasks such as image reconstruction and object detection.
arXiv Detail & Related papers (2025-02-12T09:01:25Z) - Toward Neurosymbolic Program Comprehension [46.874490406174644]
We advocate for a Neurosymbolic research direction that combines the strengths of existing DL techniques with traditional symbolic methods.
We present preliminary results for our envisioned approach, aimed at establishing the first Neurosymbolic Program framework.
arXiv Detail & Related papers (2025-02-03T20:38:58Z) - Towards a Probabilistic Framework for Analyzing and Improving LLM-Enabled Software [0.0]
Large language model (LLM)-enabled systems are a significant challenge in software engineering.
We propose a probabilistic framework for systematically analyzing and improving these systems.
arXiv Detail & Related papers (2025-01-10T22:42:06Z) - A Survey on Inference Optimization Techniques for Mixture of Experts Models [50.40325411764262]
MoE models offer enhanced model capacity and computational efficiency through conditional computation.<n>Deployment and inference of MoE models present substantial challenges in terms of computational resources, latency, and energy efficiency.<n>This survey systematically analyzes the current landscape of inference optimization techniques for MoE models across the entire system stack.
arXiv Detail & Related papers (2024-12-18T14:11:15Z) - Software Performance Engineering for Foundation Model-Powered Software (FMware) [6.283211168007636]
Foundation Models (FMs) like Large Language Models (LLMs) are revolutionizing software development.
This paper highlights the significance of Software Performance Engineering (SPE) in FMware.
We identify four key challenges: cognitive architecture design, communication protocols, tuning and optimization, and deployment.
arXiv Detail & Related papers (2024-11-14T16:42:19Z) - Towards Quantifying Requirements Technical Debt for Software Requirements concerning Veracity: A Perspective and Research Roadmap [3.763215468259125]
We present our perspective and the vision to apply the lens of RTD to software requirements concerning veracity.
Our goal is to cultivate awareness of veracity as an important concern and eventually support the management of RTD for software requirements concerning veracity.
arXiv Detail & Related papers (2024-06-29T10:10:03Z) - Fault-tolerant resource estimation using graph-state compilation on a modular superconducting architecture [30.01663013636363]
Development of fault-tolerant quantum computers (FTQCs) is gaining increased attention within the quantum computing community.
We present a resource estimation framework and software tool that estimates the physical resources required to execute specific quantum algorithms.
This tool can predict the size, power consumption, and execution time of these algorithms at as they approach utility-scale.
arXiv Detail & Related papers (2024-06-10T04:30:48Z) - Natural Language Processing for Requirements Traceability [47.93107382627423]
Traceability plays a crucial role in requirements and software engineering, particularly for safety-critical systems.
Natural language processing (NLP) and related techniques have made considerable progress in the past decade.
arXiv Detail & Related papers (2024-05-17T15:17:00Z) - Stability prediction of the software requirements specification [0.0]
This work presents the Bayesian network Requisites that predicts whether the requirements specification documents have to be revised.
We show how to validate Requisites by means of metrics obtained from a large complex software project.
arXiv Detail & Related papers (2024-01-23T10:40:29Z) - Requirements Analysis of Variability Constraints in a Configurable
Flight Software System [0.0]
We report on our experience with the variability-related requirements constraints of a flight software framework used by multiple space missions.
We propose a new software variability model, similar to a product-line feature model, in the flight software framework.
arXiv Detail & Related papers (2023-09-06T22:56:39Z) - Counterfactual Explanations as Interventions in Latent Space [62.997667081978825]
Counterfactual explanations aim to provide to end users a set of features that need to be changed in order to achieve a desired outcome.
Current approaches rarely take into account the feasibility of actions needed to achieve the proposed explanations.
We present Counterfactual Explanations as Interventions in Latent Space (CEILS), a methodology to generate counterfactual explanations.
arXiv Detail & Related papers (2021-06-14T20:48:48Z) - Offline Model-Based Optimization via Normalized Maximum Likelihood
Estimation [101.22379613810881]
We consider data-driven optimization problems where one must maximize a function given only queries at a fixed set of points.
This problem setting emerges in many domains where function evaluation is a complex and expensive process.
We propose a tractable approximation that allows us to scale our method to high-capacity neural network models.
arXiv Detail & Related papers (2021-02-16T06:04:27Z) - Reconfigurable Intelligent Surface Assisted Mobile Edge Computing with
Heterogeneous Learning Tasks [53.1636151439562]
Mobile edge computing (MEC) provides a natural platform for AI applications.
We present an infrastructure to perform machine learning tasks at an MEC with the assistance of a reconfigurable intelligent surface (RIS)
Specifically, we minimize the learning error of all participating users by jointly optimizing transmit power of mobile users, beamforming vectors of the base station, and the phase-shift matrix of the RIS.
arXiv Detail & Related papers (2020-12-25T07:08:50Z) - Edge-assisted Democratized Learning Towards Federated Analytics [67.44078999945722]
We show the hierarchical learning structure of the proposed edge-assisted democratized learning mechanism, namely Edge-DemLearn.
We also validate Edge-DemLearn as a flexible model training mechanism to build a distributed control and aggregation methodology in regions.
arXiv Detail & Related papers (2020-12-01T11:46:03Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.