相关论文: Meek Models Shall Inherit the Earth

Machine learning models are increasingly used for software security tasks. These models are commonly trained and evaluated on large Internet-derived datasets, which often contain duplicated or highly similar samples. When such samples are…

Recent years have seen significant advancements in foundation models through generative pre-training, yet algorithmic innovation in this space has largely stagnated around autoregressive models for discrete signals and diffusion models for…

Recent LLMs have hundreds of billions of parameters consuming vast resources. Furthermore, the so called "AI scaling law" for transformers suggests that the number of parameters must scale linearly with the size of the data. In response, we…

Algorithmic fairness has emerged as a central issue in ML, and it has become standard practice to adjust ML algorithms so that they will satisfy fairness requirements such as Equal Opportunity. In this paper we consider the effects of…

Over the Eight decades, computing paradigms have shifted from large, centralized systems to compact, distributed architectures, leading to the rise of the Distributed Computing Continuum (DCC). In this model, multiple layers such as cloud,…

Task-based models of AI and labor hold organizational structure fixed. We introduce agent capital: AI that reduces coordination costs, expanding spans of control and enabling endogenous task creation. Five propositions characterize how…

When deployed in the wild, machine learning models are usually confronted with data and requirements that constantly vary, either because of changes in the generating distribution or because external constraints change the environment where…

The collaboration of large artificial intelligence (AI) models in mobile edge networks has emerged as a promising paradigm to meet the growing demand for intelligent services at the network edge. By enabling multiple devices to…

Most existing notions of algorithmic fairness are one-shot: they ensure some form of allocative equality at the time of decision making, but do not account for the adverse impact of the algorithmic decisions today on the long-term welfare…

The latest advancements in machine learning, specifically in foundation models, are revolutionizing the frontiers of existing software engineering (SE) processes. This is a bi-directional phenomona, where 1) software systems are now…

Data attribution, tracing a model's prediction back to specific training data, is an important tool for interpreting sophisticated AI models. The widely used TRAK algorithm addresses this challenge by first approximating the underlying…

Sustainable AI is a subfield of AI for concerning developing and using AI systems in ways of aiming to reduce environmental impact and achieve sustainability. Sustainable AI is increasingly important given that training of and inference…

Deep learning's recent history has been one of achievement: from triumphing over humans in the game of Go to world-leading performance in image classification, voice recognition, translation, and other tasks. But this progress has come with…

Today's intelligent computing environments, including Internet of Things, cloud computing and fog computing, allow many organizations around the world to optimize their resource allocation regarding time and energy consumption. Due to the…

Recently, small models with latent recursion have obtained promising results on complex reasoning tasks. These results are typically explained by the theory that such recursion increases a networks depth, allowing it to compactly emulate…

With the ever growing involvement of data-driven AI-based decision making technologies in our daily social lives, the fairness of these systems is becoming a crucial phenomenon. However, an important and often challenging aspect in…

Recent advances in general-purpose AI systems with attention-based transformers offer a potential window into how the neocortex and cerebellum, despite their relatively uniform circuit architectures, give rise to diverse functions and,…

Resource allocation systems provide the fundamental support for the normal functioning and well being of the modern society, and can be modeled as minority games. A ubiquitous dynamical phenomenon is the emergence of herding, where a vast…

Pretraining large language models (LLMs) is resource-intensive, often requiring months of training time even with high-end GPU clusters. There are two approaches of mitigating such computational demands: reusing smaller models to train…

In today's world, AI programs powered by Machine Learning are ubiquitous, and have achieved seemingly exceptional performance across a broad range of tasks, from medical diagnosis and credit rating in banking, to theft detection via video…