ImageNet Classification with Deep Convolutional Neural Networks
A deep convolutional network demonstrated how data, GPU computation and learned representations could transform visual recognition.
THE RESEARCH ATLAS
Qwen-Audio-Agent Technical Report
A foreground-background architecture separates voice interaction from asynchronous task execution, coordinating authorization, state and delivery.
Institution and location sources
Location refers to credited institutions or the listed organization, not author citizenship or an exhaustive collaboration list.
Why read this
Study the distinction between speech interruption and task cancellation; the reported task benchmark is in-house.
Citation
@misc{deng2026qwen,
title = {Qwen-Audio-Agent Technical Report},
author = {Chong Deng and Yunjie Ji and Yuxiang Kong and Xiangang Li and Xu Li and Binbin Zhang and Haina Zhu and Jianheng Zhuo},
year = {2026},
eprint = {2609.25195},
archivePrefix = {arXiv},
primaryClass = {eess.AS},
url = {https://arxiv.org/abs/2609.25195}
}Rights remain with the original authors. Refer to the original source for citations and licensing.
Related research
Attention Is All You Need
The Transformer replaces recurrent sequence processing with attention, creating a foundation for many later language and multimodal models.
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Masked-language pretraining learns bidirectional representations that can be adapted to language-understanding tasks.