607 citations · 3.5k across the 64 of their papers we have counts for
11 papers · 1 filter
FedLesScan: Mitigating Stragglers in Serverless Federated Learning
Mohamed Elzohairy, Mohak Chadha, Anshul Jindal +4
Federated Learning (FL) is a machine learning paradigm that enables the training of a shared global model across distributed clients while keeping the training data local. While mo…
f-DM: A Multi-stage Diffusion Model via Progressive Signal Transformation
Jiatao Gu, Shuangfei Zhai, Yizhe Zhang +2
Diffusion models (DMs) have recently emerged as SoTA tools for generative modeling in various domains. Standard DMs can be viewed as an instantiation of hierarchical variational au…
Migrating from Microservices to Serverless: An IoT Platform Case Study
Mohak Chadha, Victor Pacyna, Anshul Jindal +2
Microservice architecture is the common choice for developing cloud applications these days since each individual microservice can be independently modified, replaced, and scaled.…
Progressively-connected Light Field Network for Efficient View Synthesis
Peng Wang, Yuan Liu, Guying Lin +4
This paper presents a Progressively-connected Light Field network (ProLiF), for the novel view synthesis of complex forward-facing scenes. ProLiF encodes a 4D light field, which al…
Multilingual Neural Machine Translation with Deep Encoder and Multiple Shallow Decoders
Xiang Kong, Adithya Renduchintala, James Cross +3
Recent work in multilingual translation advances translation quality surpassing bilingual baselines using deep transformer models with increased capacity. However, the extra latenc…
Muffin: Testing Deep Learning Libraries via Neural Architecture Fuzzing
Jiazhen Gu, Xuchuan Luo, Yangfan Zhou +1
Deep learning (DL) techniques are proven effective in many challenging tasks, and become widely-adopted in practice. However, previous work has shown that DL libraries, the basis o…
Detection, Disambiguation, Re-ranking: Autoregressive Entity Linking as a Multi-Task Problem
Khalil Mrini, Shaoliang Nie, Jiatao Gu +3
We propose an autoregressive entity linking model, that is trained with two auxiliary tasks, and learns to re-rank generated samples at inference time. Our proposed novelties addre…
Unified Speech-Text Pre-training for Speech Translation and Recognition
Yun Tang, Hongyu Gong, Ning Dong +8
We describe a method to jointly pre-train speech and text in an encoder-decoder modeling framework for speech translation and recognition. The proposed method incorporates four sel…
IDPG: An Instance-Dependent Prompt Generation Method
Zhuofeng Wu, Sinong Wang, Jiatao Gu +4
Prompt tuning is a new, efficient NLP transfer learning paradigm that adds a task-specific prompt in each input instance during the model training stage. It freezes the pre-trained…
Enhanced Direct Speech-to-Speech Translation Using Self-supervised Pre-training and Data Augmentation
Sravya Popuri, Peng-Jen Chen, Changhan Wang +5
Direct speech-to-speech translation (S2ST) models suffer from data scarcity issues as there exists little parallel S2ST data, compared to the amount of data available for conventio…
data2vec: A General Framework for Self-supervised Learning in Speech, Vision and Language
Alexei Baevski, Wei-Ning Hsu, Qiantong Xu +3
While the general idea of self-supervised learning is identical across modalities, the actual algorithms and objectives differ widely because they were developed with a single moda…