Related papers: Scalable Inference of System-level Models from Com…

We introduce computational causal inference as an interdisciplinary field across causal inference, algorithms design and numerical computing. The field aims to develop software specializing in causal inference that can analyze massive…

Computer architecture design space is vast and complex. Tools are needed to explore new ideas and gain insights quickly, with low efforts and at a desired accuracy. We propose Calipers, a criticality-based framework to model key…

Large language models (LLMs) have been a disruptive innovation in recent years, and they play a crucial role in our daily lives due to their ability to understand and generate human-like text. Their capabilities include natural language…

Scaling data and models has played a pivotal role in the remarkable progress of computer vision and language. Inspired by these domains, recent efforts in robotics have similarly focused on scaling both data and model size to develop more…

Software-intensive systems produce logs for troubleshooting purposes. Recently, many deep learning models have been proposed to automatically detect system anomalies based on log data. These models typically claim very high detection…

Automatic log analysis is essential for the efficient Operation and Maintenance (O&M) of software systems, providing critical insights into system behaviors. However, existing approaches mostly treat log analysis as training a model to…

Anomalies or failures in large computer systems, such as the cloud, have an impact on a large number of users that communicate, compute, and store information. Therefore, timely and accurate anomaly detection is necessary for reliability,…

Generative models typically sample outputs independently, and recent inference-time guidance and scaling algorithms focus on improving the quality of individual samples. However, in real-world applications, users are often presented with a…

Modern statistical machine learning (SML) methods share a major limitation with the early approaches to AI: there is no scalable way to adapt them to new domains. Human learning solves this in part by leveraging a rich, shared, updateable…

Large language models (LLMs) demonstrate strong reasoning abilities in solving complex real-world problems. Yet, the internal mechanisms driving these complex reasoning behaviors remain opaque. Existing interpretability approaches targeting…

This paper describes a way to improve the scalability of program synthesis by exploiting modularity: larger programs are synthesized from smaller programs. The key issue is to make each "larger-created-from-smaller" synthesis sub-problem be…

Remarkable achievements have been attained by deep neural networks in various applications. However, the increasing depth and width of such models also lead to explosive growth in both storage and computation, which has restricted the…

Multimodal large language models increasingly solve vision-centric tasks by calling external tools for visual inspection, OCR, retrieval, calculation, and multi-step reasoning. Current tool-using agents usually expose the executed tool…

Generative models have made significant impacts across various domains, largely due to their ability to scale during training by increasing data, computational resources, and model size, a phenomenon characterized by the scaling laws.…

Controllable image synthesis, which enables fine-grained control over generated outputs, has emerged as a key focus in visual generative modeling. However, controllable generation remains challenging for Visual Autoregressive (VAR) models…

System logs are some of the most important information for the maintenance of software systems, which have become larger and more complex in recent years. The goal of log-based anomaly detection is to automatically detect system anomalies…

For efficiency reasons, the software system designers' will is to use an integrated set of methods and tools to describe specifications and designs, and also to perform analyses such as dependability, schedulability and performance. AADL…

The behavior of LLMs does not depend solely on the model itself. Components of the inference system, such as the inference engine, attention backend, and hardware platform, subtly influence how inputs are processed. These components differ…

Intensive testing using model-based approaches is the standard way of demonstrating the correctness of automotive software. Unfortunately, state-of-the-art techniques leave a crucial and labor intensive task to the test engineer:…

Logs serve as a primary source of information for engineers to diagnose failures in large-scale online service systems. Log parsing, which extracts structured events from massive unstructured log data, is a critical first step for…