607 citations · 3.5k across the 64 of their papers we have counts for
66 papers
Revealing Performance Issues in Server-side WebAssembly Runtimes via Differential Testing
Shuyao Jiang, Ruiying Zeng, Zihao Rao +3
WebAssembly (Wasm) is a bytecode format originally serving as a compilation target for Web applications. It has recently been used increasingly on the server side, e.g., providing…
Ditto: An Elastic and Adaptive Memory-Disaggregated Caching System
Jiacheng Shen, Pengfei Zuo, Xuchuan Luo +5
In-memory caching systems are fundamental building blocks in cloud services. However, due to the coupled CPU and memory on monolithic servers, existing caching systems cannot elast…
FaST-GShare: Enabling Efficient Spatio-Temporal GPU Sharing in Serverless Computing for Deep Learning Inference
Jianfeng Gu, Yichao Zhu, Puxuan Wang +2
Serverless computing (FaaS) has been extensively utilized for deep learning (DL) inference due to the ease of deployment and pay-per-use benefits. However, existing FaaS platforms…
BOOT: Data-free Distillation of Denoising Diffusion Models with Bootstrapping
Jiatao Gu, Shuangfei Zhai, Yizhe Zhang +2
Diffusion models have demonstrated excellent potential for generating diverse images. However, their performance often suffers from slow generation due to iterative denoising. Know…
PLANNER: Generating Diversified Paragraph via Latent Language Diffusion Model
Yizhe Zhang, Jiatao Gu, Zhuofeng Wu +3
Autoregressive models for text sometimes generate repetitive and low-quality output because errors accumulate during the steps of generation. This issue is often attributed to expo…
Single-Stage Diffusion NeRF: A Unified Approach to 3D Generation and Reconstruction
Hansheng Chen, Jiatao Gu, Anpei Chen +4
3D-aware image synthesis encompasses a variety of tasks, such as scene generation and novel view synthesis from images. Despite numerous task-specific methods, developing a compreh…
Control3Diff: Learning Controllable 3D Diffusion Models from Single-view Images
Jiatao Gu, Qingzhe Gao, Shuangfei Zhai +3
Diffusion models have recently become the de-facto approach for generative modeling in the 2D domain. However, extending diffusion models to 3D is challenging due to the difficulti…
MAST: Masked Augmentation Subspace Training for Generalizable Self-Supervised Priors
Chen Huang, Hanlin Goh, Jiatao Gu +1
Recent Self-Supervised Learning (SSL) methods are able to learn feature representations that are invariant to different data augmentations, which can then be transferred to downstr…
Stabilizing Transformer Training by Preventing Attention Entropy Collapse
Shuangfei Zhai, Tatiana Likhomanenko, Etai Littwin +5
Training stability is of great importance to Transformers. In this work, we investigate the training dynamics of Transformers by examining the evolution of the attention layers. In…
NerfDiff: Single-image View Synthesis with NeRF-guided Distillation from 3D-aware Diffusion
Jiatao Gu, Alex Trevithick, Kai-En Lin +4
Novel view synthesis from a single image requires inferring occluded regions of objects and scenes whilst simultaneously maintaining semantic and physical consistency with the inpu…
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…
Textless Speech-to-Speech Translation on Real Data
Ann Lee, Hongyu Gong, Paul-Ambroise Duquenne +8
We present a textless speech-to-speech translation (S2ST) system that can translate speech from one language into another language and can be built without the need of any text dat…
StyleNeRF: A Style-based 3D-Aware Generator for High-resolution Image Synthesis
Jiatao Gu, Lingjie Liu, Peng Wang +1
We propose StyleNeRF, a 3D-aware generative model for photo-realistic high-resolution image synthesis with high multi-view consistency, which can be trained on unstructured 2D imag…
fairseq S^2: A Scalable and Integrable Speech Synthesis Toolkit
Changhan Wang, Wei-Ning Hsu, Yossi Adi +5
This paper presents fairseq S^2, a fairseq extension for speech synthesis. We implement a number of autoregressive (AR) and non-AR text-to-speech models, and their multi-speaker va…