相关论文: PyGlove: Efficiently Exchanging ML Ideas as Code

Large language models (LLMs) are increasingly deployed in teams, yet existing coordination approaches often occupy two extremes. Highly structured methods rely on fixed roles, pipelines, or task decompositions assigned a priori. In…

The increasing size and complexity of machine learning (ML) models have driven the growing need for custom hardware accelerators capable of efficiently supporting ML workloads. However, the design of such accelerators remains a…

Pattern matching is a powerful tool for symbolic computations. Applications include term rewriting systems, as well as the manipulation of symbolic expressions, abstract syntax trees, and XML and JSON data. It also allows for an intuitive…

Software organizations are increasingly incorporating machine learning (ML) into their product offerings, driving a need for new data management tools. Many of these tools facilitate the initial development of ML applications, but…

Over past few years afterward the birth of ResNet, skip connection has become the defacto standard for the design of modern architectures due to its widespread adoption, easy optimization and proven performance. Prior work has explained the…

Recent years have witnessed the emergence of textual commonsense knowledge bases, aimed at providing more nuanced and context-rich knowledge. The integration of external commonsense into language models has been shown to be a key enabler in…

Large language models (LLMs) have shown to pose social and ethical risks such as generating toxic language or facilitating malicious use of hazardous knowledge. Machine unlearning is a promising approach to improve LLM safety by directly…

Many research directions in machine learning, particularly in deep learning, involve complex, multi-stage experiments, commonly involving state-mutating operations acting on models along multiple paths of execution. Although machine…

Learning quickly is of great importance for machine intelligence deployed in online platforms. With the capability of transferring knowledge from learned tasks, meta-learning has shown its effectiveness in online scenarios by continuously…

Teamwork is a central tenet of agile software development and various teamwork theories partially explain teamwork in that context. Big Five teamwork theory is one of the most influential teamwork theories, but prior research shows that the…

CodeCompose is an AI-assisted code authoring tool powered by large language models (LLMs) that provides inline suggestions to 10's of thousands of developers at Meta. In this paper, we present how we scaled the product from displaying…

Code quality is of paramount importance in all types of software development settings. Our work seeks to enable Machine Learning (ML) engineers to write better code by helping them find and fix instances of Data Leakage in their models.…

Memory-based self-evolution has emerged as a promising paradigm for coding agents. However, existing approaches typically restrict memory utilization to homogeneous task domains, failing to leverage the shared infrastructural foundations,…

Scene Graph Generation (SGG) has achieved significant progress recently. However, most previous works rely heavily on fixed-size entity representations based on bounding box proposals, anchors, or learnable queries. As each representation's…

Support for Machine Learning (ML) applications in networks has significantly improved over the last decade. The availability of public datasets and programmable switching fabrics (including low-level languages to program them) present a…

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…

Pattern matching is a powerful tool for symbolic computations, based on the well-defined theory of term rewriting systems. Application domains include algebraic expressions, abstract syntax trees, and XML and JSON data. Unfortunately, no…

Machine learning has been increasingly applied in climate modeling on system emulation acceleration, data-driven parameter inference, forecasting, and knowledge discovery, addressing challenges such as physical consistency, multi-scale…

Clouds gather a vast volume of telemetry from their networked systems which contain valuable information that can help solve many of the problems that continue to plague them. However, it is hard to extract useful information from such raw…

Success of machine learning (ML) in the modern world is largely determined by abundance of data. However at many industrial and scientific problems, amount of data is limited. Application of ML methods to data-scarce scientific problems can…