IEEE

Audio Word2vec: Sequence-to-Sequence Autoencoding for Unsupervised Learning of Audio Segmentation and Representation

Abstract: In text, word2vec transforms each word into a fixed-size vector used as the basic component in applications of natural language processing. Given a large collection of unannotated audio, ...
IEEE

ZeroNLG: Aligning and Autoencoding Domains for Zero-Shot Multimodal and Multilingual Natural Language Generation

Abstract: Natural Language Generation (NLG) accepts input data in the form of images, videos, or text and generates corresponding natural language text as output. Existing NLG methods mainly adopt a ...
GitHub

CRATE (Coding RAte reduction TransformEr)

Also, we have released a larger journal-length overview paper of this line of research, which contains a superset of all the results presented above, and also more results in NLP and vision SSL. We ...
GitHub

fastgs_training_3d_gaussian_splatting_in_100_seconds.md

description [CVPR2026][3D视觉][3D Gaussian Splatting] 提出 FastGS，一个基于多视角一致性的 3DGS 加速框架，通过多视角一致性密集化（VCD ...
C&EN

druGAN: An Advanced Generative Adversarial Autoencoder Model for de Novo Generation of New Molecules with Desired Molecular Properties in Silico

Article Views are the COUNTER-compliant sum of full text article downloads since November 2008 (both PDF and HTML) across all institutions and individuals. These metrics are regularly updated to ...
Microsoft

AI Interaction and Learning

The Augmented Learning and Reasoning group's mission is to augment AI models, technology, and people with new capabilities to transform what is possible. The group brings together expertise in ...