eLife

Stimulus dependencies—rather than next-word prediction—can explain pre-onset brain encoding in naturalistic listening designs

The ability to predict brain activity from words before they occur can be explained by information shared between neighbouring words, without requiring next-word prediction by the brain.
WinBuzzer

Microsoft Open-Sources Harrier Embedding Model, Tops MTEB

Microsoft's Bing team has open-sourced Harrier, an embedding model family that tops the multilingual MTEB v2 benchmark under an MIT license.
IEEE

BiFormer-Seg: Dual-Branch Visual Encoding and Text-Guided Decoding for Radiological Segmentation

Abstract: Accurate segmentation of pulmonary infection regions is critical for diagnosing respiratory diseases such as COVID-19 and pneumonia. Although recent deep learning approaches have achieved ...
GitHub

Brain-to-Text '25: Neural Speech Decoding

Deep learning models for decoding intracortical neural activity during attempted speech into text. This repository contains our team's implementation for the COMP 433 Fall 2025 course project, ...
IEEE

Incorporating contextual cross-attention into encoding-decoding architecture for single-image dehazing

Abstract: In deep learning-based dehazing strategies, attention mechanisms are widely used to refine feature representations and improve overall performance. However, conventional contextual attention ...