Brain-computer interfaces (BCIs) are finally having their ‘foundation model’ moment. Zyphra, a research lab focused on large-scale models, recently released ZUNA, a 380M-parameter foundation model specifically for EEG signals. ZUNA is a masked diffusion auto-encoder designed to perform channel infilling and super-resolution for any electrode layout. This release includes weights under an Apache-2.0 license and an MNE-compatible inference stack. The Problem with ‘Brittle’ EEG Models For decades, researchers have struggled with the ‘Wild West’ of EEG data. Different […]

Ver mais

Multi-agent reinforcement learning is a promising research area that extends established reinforcement learning approaches to problems formulated as multi-agent systems. Recently, a multitude of communication methods have been introduced to this field to address problems such as partially observable environments, non-stationarity, and exponentially growing action spaces. Communication further enables efficient cooperation among all agents interacting in an environment. This work aims at providing an overview of communication techniques in multi-agent reinforcement learning. By an in-depth analysis of 29 […]

Ver mais

The increasing adoption of contactless transactions has introduced new security challenges, particularly in protecting data from unauthorized access and fraudulent activities. This study presents a novel authentication framework designed to enhance the security of near-field communication (NFC) transactions while maintaining efficiency for real-time processing. By leveraging a lightweight cryptographic approach, the proposed system mitigates threats such as relay attacks and unauthorized skimming. Experimental analysis demonstrates improvements in authentication reliability and resistance to common attack vectors. This research contributes […]

Ver mais

The stark success of OpenAI’s GPT4 model surprised me shifting my view from “really good autocomplete” (roughly inline with intuitions here) to a dialog agent exhibiting a significant scope of reasoning and intelligence. Some of the MSR folks did a fairly thorough study of capabilities which seems like a good reference. I think of GPT4 as an artificial savant: super-John capable in some language-centric tasks like style and summarization with impressive yet more limited abilities in other domains […]

Ver mais

arXiv:2602.13804v1 Announce Type: cross Abstract: Large language models spend most of their inference cost on attention over long contexts, yet empirical behavior suggests that only a small subset of tokens meaningfully contributes to each query. We formalize this phenomenon by modeling attention as a projection onto the convex hull of key vectors and analyzing its entropic (softmax-like) relaxation. Our main theoretical contribution is a face-stability theorem showing that, under a strict complementarity margin (a support gap (Delta) certified […]

Ver mais

arXiv:2601.14263v1 Announce Type: new Abstract: The adaptation of Large-Scale Language Models (LLMs) to specific domains depends on high-quality fine-tuning datasets, particularly in instructional format (e.g., Question-Answer – Q&A). However, generating these datasets, particularly from unstructured sources such as call center audio recordings, poses a significant challenge due to the noisy and disorganized nature of the data. This paper presents a solution to this challenge by offering an end-to-end automated pipeline for generating Q&A instructional datasets from such recordings. […]

Ver mais

:::info Authors: James Truslow Angela Spillane Huiming Lin Katherine Cyr Adeeti Ullal Edith Arnold Ron Huang Laura Rhodes Jennifer Block Jamie Stark James Kretlow Alexis L. Beatty Andreas Werdich Deepali Bankar Matt Bianchi Ian Shapiro Jaime Villalpando Sharon Ravindran Irida Mance Adam Phillips John Earl Rahul C. Deo Sumbul A. Desai Calum A. MacRae ::: Abstract Physical activity or structured exercise is beneficial in a wide range of circumstances. Nevertheless, individual-level data on differential responses to various types […]

Ver mais

arXiv:2412.19217v4 Announce Type: replace-cross Abstract: The rapid expansion of citizen science initiatives has led to a significant growth of biodiversity databases, and particularly presence-only (PO) observations. PO data are invaluable for understanding species distributions and their dynamics, but their use in a Species Distribution Model (SDM) is curtailed by sampling biases and the lack of information on absences. Poisson point processes are widely used for SDMs, with Maxent being one of the most popular methods. Maxent maximises the […]

Ver mais

Early detection is a key tool for preventing wildfires. Modern machine learning algorithms integrated into large-scale monitoring systems enable automated surveillance of high-risk areas. However, single‑image detection methods that do not consider interframe dependencies and changes between consecutive images often fail to detect smoke plumes at the very early stage and at larger distances, critical for effective response, or they produce an increased number of false alarms. Biological vision is particularly sensitive to motion cues, and this translates […]

Ver mais