Related papers: HarnessAPI: A Skill-First Framework for Unified St…
This paper aims to create a transition path from file-based IO to streaming-based workflows for scientific applications in an HPC environment. By using the openPMP-api, traditional workflows limited by filesystem bottlenecks can be overcome…
As LLM agents are increasingly built around reusable skills, a central challenge is no longer only whether agents can use provided skills, but whether they can generate correct, reusable, and executable skills from repositories and…
Serverless computing has emerged as a promising alternative to infrastructure- (IaaS) and platform-as-a-service (PaaS)cloud platforms for applications with ample parallelism and intermittent activity. Serverless promises greater resource…
Distributed dataflow systems like Apache Spark and Apache Hadoop enable data-parallel processing of large datasets on clusters. Yet, selecting appropriate computational resources for dataflow jobs -- that neither lead to bottlenecks nor to…
Finance LLM agents must simultaneously block prompt-induced unauthorized actions and approve legitimate multi-step business workflows. However, boundary filters often miss irreversible mid-trajectory tool calls, while post-hoc LLM judges…
AI-native software development is often evaluated at the level of individual models, prompts, or generated artifacts. This framing is insufficient for production environments where software must be continuously produced, verified, deployed,…
Access transparency means that both local and remote resources are accessed using identical operations. With transparency, unmodified single-machine applications could run over disaggregated compute, storage, and memory resources. Hiding…
Edge computing enables latency-critical applications to process data close to end devices, yet task heterogeneity and limited resources pose significant challenges to efficient orchestration. This paper presents a measurement-driven,…
We introduce a neural network layer API and library for sequence modeling, designed for easy creation of sequence models that can be executed both layer-by-layer (e.g., teacher-forced training) and step-by-step (e.g., autoregressive…
For decades, mainframe systems have been vital in enterprise computing, supporting essential applications across industries like banking, retail, and healthcare. To harness these legacy applications and facilitate their reuse, there is…
Multi-party computing (MPC) has been gaining popularity as a secure computing model over the past few years. However, prior works have demonstrated that MPC protocols still pay substantial performance penalties compared to plaintext,…
Efficient parallelization of Large Language Models (LLMs) with long sequences is essential but challenging due to their significant computational and memory demands, particularly stemming from communication bottlenecks in attention…
Proof-of-Work (PoW) blockchain consensus consumes vast computational resources without producing useful output, while the rapid growth of large language model (LLM) agents has created unprecedented demand for GPU computation. We present…
AI agents are entering high-risk production settings, where they use tools, retain context, follow policies, handle private data, and interact with users over multiple turns. Yet many evaluation methods still judge isolated outputs or…
Test-time skill evolving is regarded as a new paradigm for enhancing deployed agentic systems. Existing works mainly focus on hard-coded skill evolving strategies or parametric learning that rely on expensive parameter updates in the…
Website Fingerprinting (WFP) uses deep learning models to classify encrypted network traffic to infer visited websites. While historically effective, prior methods fail to generalize to modern web environments. Single-page applications…
Increased popularity of `intelligent' web services provides end-users with machine-learnt functionality at little effort to developers. However, these services require a decision threshold to be set which is dependent on problem-specific…
Building applications that perceive the world around them is challenging. A developer needs to (a) select and develop corresponding machine learning algorithms and models, (b) build a series of prototypes and demos, (c) balance resource…
Since the introduction of the Model Context Protocol (MCP), the number of available tools for Large Language Models (LLMs) has increased significantly. These task-specific tool sets offer an alternative to general-purpose tools such as web…
TensorFlow is an interface for expressing machine learning algorithms, and an implementation for executing such algorithms. A computation expressed using TensorFlow can be executed with little or no change on a wide variety of heterogeneous…