Related papers: Background and Intellectual Development: Supplemen…
We present Future-KL Influenced Policy Optimization (FIPO), a reinforcement learning algorithm designed to overcome reasoning bottlenecks in large language models. While GRPO style training scales effectively, it typically relies on…
Class-incremental learning (CIL) aims to develop a learning system that can continually learn new classes from a data stream without forgetting previously learned classes. When learning classes incrementally, the classifier must be…
The notion of concept drift refers to the phenomenon that the distribution generating the observed data changes over time. If drift is present, machine learning models may become inaccurate and need adjustment. Many technologies for…
Prior work on generating explanations in a planning and decision-making context has focused on providing the rationale behind an AI agent's decision making. While these methods provide the right explanations from the explainer's…
Scholarly communications have been rapidly integrated into digitised and networked open ecosystems, where preprint servers have played a pivotal role in accelerating the knowledge transfer processes. However, quantitative evidence is scarce…
Driven by the explosion of data and the impact of real-world networks, a wide array of mathematical models have been proposed to understand the structure and evolution of such systems, especially in the temporal context. Recent advances in…
At the end of the 19th century the logician C.S. Peirce coined the term "fallibilism" for the "... the doctrine that our knowledge is never absolute but always swims, as it were, in a continuum of uncertainty and of indeterminacy". In terms…
As IoT systems are given more responsibility and autonomy, they offer greater benefits, but also carry greater risks. We believe this trend invigorates an old challenge of software engineering: how to develop high-risk software-intensive…
There has been a long history of research into the structure and evolution of mankind's scientific endeavor. However, recent progress in applying the tools of science to understand science itself has been unprecedented because only recently…
Traditional massive multiple-input multiple-output (MIMO) information theory adopt non-physically consistent assumptions, including white-noised, scalar-quantity, far-field, discretized, and monochromatic EM fields, which mismatch the…
Several surveys and studies have noticed that cost, and quality problems result from mistakes that occurred in the early phases of the projects, for instance: poor definition of the project vision and respective value for the organization;…
One of the interesting and important problems of information diffusion over a large social network is to identify an appropriate model from a limited amount of diffusion information. There are two contrasting approaches to model information…
For fifty years, networking has fragmented whenever new workloads exposed hidden assumptions about time, ordering, failure, and trust. This paper argues that the current interconnect landscape -- NVLink, UALink, Ultra Ethernet,…
Autoregressive language models achieve remarkable performance, yet a unified theory explaining their internal mechanisms, how training shapes representations, and why these representations support complex behavior remains incomplete. We…
Students in introductory physics courses often rely on ineffective strategies, focusing on final answers rather than understanding underlying principles. Integrating scientific argumentation into problem-solving fosters critical thinking…
Open-domain multimodal document retrieval aims to retrieve specific components (paragraphs, tables, or images) from large and interconnected document corpora. Existing graph-based retrieval approaches typically rely on a uniform similarity…
Information theory is concerned with the study of transmission, processing, extraction, and utilization of information. In its most abstract form, information is conceived as a means of resolving uncertainty. Shannon and Weaver (1949) were…
Pioneered by the foundational information theory by Claude Shannon and the visionary framework of machine intelligence by Alan Turing, the convergent evolution of information and communication technologies (IT/CT) has created an unbroken…
Smoothed online learning has emerged as a popular framework to mitigate the substantial loss in statistical and computational complexity that arises when one moves from classical to adversarial learning. Unfortunately, for some spaces, it…
We present a general framework for training deep neural networks without backpropagation. This substantially decreases training time and also allows for construction of deep networks with many sorts of learners, including networks whose…