Tootfinder

Designing Deep Learning Frameworks for LLMs:Challenges, Expectations, and Opportunities
Yanzhou Mu, Rong Wang, Juan Zhai, Chunrong Fang, Xiang Chen, Jiacong Wu, An Guo, Jiawei Shen, Bingzhuo Li, Zhenyu Chen
https://arxiv.org/abs/2506.13114

Designing Deep Learning Frameworks for LLMs:Challenges, Expectations, and Opportunities
Large language models (LLMs) drive significant advancements in real industry applications. LLMs rely on DL frameworks for efficient model construction, distributed execution, and optimized deployment. Their large parameter scale and long execution cycles place extreme demands on DL frameworks in terms of scalability, stability, and efficiency. Therefore, poor usability, limited functionality, and subtle bugs in DL frameworks may hinder development efficiency and cause severe failures or resourc…

Unique support from identity-based groups: Professional networks of women and LGBTQ physicists analyzed and compared by career sector
Chase Hatcher, Adrienne Traxler, Lily Donis, Madison Swirtz, Camila Manni, Justin Gutzwa, Charles Henderson, Ram\'on Barthelemy
https://arxiv.org/abs/2506.14752…

Unique support from identity-based groups: Professional networks of women and LGBTQ+ physicists analyzed and compared by career sector
This paper presents a social network analysis of the professional support networks of 100 LGBTQ+ and/or women PhD physicists, comparing the networks based on the career sectors of academia, industry, and government/nonprofit. The methods for constructing and analyzing the ego networks, which are novel in many ways, are explained in greater detail in an earlier publication (Hatcher et. al., 2025). We use statistical tests of independence to explore differences between sectors in terms of whole n…

This https://arxiv.org/abs/2505.21527 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_ees…

VietASR: Achieving Industry-level Vietnamese ASR with 50-hour labeled data and Large-Scale Speech Pretraining
Automatic speech recognition (ASR) has made remarkable progress but heavily relies on large-scale labeled data, which is scarce for low-resource languages like Vietnamese. While existing systems such as Whisper, USM, and MMS achieve promising performance, their efficacy remains inadequate in terms of training costs, latency, and accessibility. To address these issues, we propose VietASR, a novel ASR training pipeline that leverages vast amounts of unlabeled data and a small set of labeled data.…