GitHub

Diffusion vs. Autoregressive Language Models: A Text Embedding Perspective

Diffusion Embedder is a simple recipe to train text encoders directly from diffusion LMs without the need of any transformation step. Diffusion LMs naturally possess bidirectional attention, which is ...
IEEE

O-Net: Bidirectional Encoding and Decoding Architecture for Infrared Small Target Detection

Abstract: Infrared small target detection (ISTD) faces significant challenges in effectively utilizing shallow and deep features while mitigating spatial detail degradation during sampling. To address ...
eLife

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

This paper tackles an important question: What drives the predictability of pre-stimulus brain activity? The authors challenge the claim that "pre-onset" encoding effects in naturalistic language data ...
GitHub

JS Text Encoding Builtins

JS String Builtins offered great performance improvements for interactions between Wasm and JS strings. However, de- and encoding was left for a follow-up proposal. This remains one of the most ...
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 ...