Related papers: SkCC: Portable and Secure Skill Compilation for Cr…

We study compiled AI, a paradigm in which large language models generate executable code artifacts during a compilation phase, after which workflows execute deterministically without further model invocation. This paradigm has antecedents…

While model serving has unlocked unprecedented capabilities, the high cost of serving large-scale models continues to be a significant barrier to widespread accessibility and rapid innovation. Compiler optimizations have long driven…

Crary and Sullivan's Relaxed Memory Calculus (RMC) proposed a new declarative approach for writing low-level shared memory concurrent programs in the presence of modern relaxed-memory multi-processor architectures and optimizing compilers.…

In today's production machine learning (ML) systems, models are continuously trained, improved, and deployed. ML design and training are becoming a continuous workflow of various tasks that have dynamic resource demands. Serverless…

This paper introduces SGCode, a flexible prompt-optimizing system to generate secure code with large language models (LLMs). SGCode integrates recent prompt-optimization approaches with LLMs in a unified system accessible through front-end…

Existing multi-LLM collaboration systems often encounter scalability challenges when integrating new LLMs and tasks, leading to suboptimal performance. To address this, we propose SMCS, a Scalable Multi-LLM Collaboration System designed to…

Compiler optimization is crucial for enhancing program performance by transforming the sequence of optimization passes while maintaining correctness. Despite the promising potential of large language models (LLMs)-based agent for software…

Traditional language-conditioned manipulation agent sequential adaptation to new manipulation skills leads to catastrophic forgetting of old skills, limiting dynamic scene practical deployment. In this paper, we propose SkillsCrafter, a…

Solidity, the dominant smart contract language for Ethereum, has rapidly evolved with frequent version updates to enhance security, functionality, and developer experience. However, these continual changes introduce significant challenges,…

This paper introduces UniTranslator, a visionary framework that re-imagines code translation as a collaborative endeavor among multiple, compact LLMs. By orchestrating the interaction of specialized agents, each focused on different aspects…

Agent skills are increasingly used to extend LLM agents with task-specific instructions, executable scripts, and auxiliary resources. While improving reusability, this modular design also introduces a new supply-chain attack surface: a…

As the ubiquity and complexity of system-on-chip (SoC) designs increase across electronic devices, the task of incorporating security into an SoC design flow poses significant challenges. Existing security solutions are inadequate to…

We present four main contributions to enhance the performance of Large Language Models (LLMs) in generating domain-specific code: (i) utilizing LLM-based data splitting and data renovation techniques to improve the semantic representation…

The scarcity of data depicting dangerous situations presents a major obstacle to training AI systems for safety-critical applications, such as construction safety, where ethical and logistical barriers hinder real-world data collection.…

Joint source-channel coding (JSCC) is a promising paradigm for next-generation communication systems, particularly in challenging transmission environments. In this paper, we propose a novel standard-compatible JSCC framework for the…

The rapid deployment of Large Language Models (LLMs) requires careful consideration of their effect on cybersecurity. Our work aims to improve the selection process of LLMs that are suitable for facilitating Secure Coding (SC). This raises…

Open source software (OSS) is integral to modern product development, and any vulnerability within it potentially compromises numerous products. While developers strive to apply security patches, pinpointing these patches among extensive…

Modern DNNs often rely on edge-cloud model partitioning (MP), but widely used schemes fix shallow, static split points that underutilize edge compute and concentrate latency and energy on the server. The problem is exacerbated in…

The rise of AI agent frameworks has introduced agent skills, modular packages containing instructions and executable code that dynamically extend agent capabilities. While this architecture enables powerful customization, skills execute…

Large Language Model (LLM) agents tackle data-intensive tasks such as deep research and code generation. However, their effectiveness depends on frequent interactions with knowledge sources across remote clouds or regions. Such interactions…