papers

Publications (17)

cs.DC2024

Supercharging Federated Learning with Flower and NVIDIA FLARE

Holger R. Roth, Daniel J. Beutel, Yan Cheng +13

Several open-source systems, such as Flower and NVIDIA FLARE, have been developed in recent years while focusing on different aspects of federated learning (FL). Flower is dedicate…

cs.LG2023

Efficient Vertical Federated Learning with Secure Aggregation

Xinchi Qiu, Heng Pan, Wanru Zhao +3

The majority of work in privacy-preserving federated learning (FL) has been focusing on horizontally partitioned datasets where clients share the same sets of features and can trai…

cs.CR2024

Secure Vertical Federated Learning Under Unreliable Connectivity

Xinchi Qiu, Heng Pan, Wanru Zhao +5

Most work in privacy-preserving federated learning (FL) has focused on horizontally partitioned datasets where clients hold the same features and train complete client-level models…

cs.LG2021

Attacking Adversarial Attacks as A Defense

Boxi Wu, Heng Pan, Li Shen +6

It is well known that adversarial attacks can fool deep neural networks with imperceptible perturbations. Although adversarial training significantly improves model robustness, fai…

cs.NI2026

PSP: Low-Overhead Packet-Level Load Balancing for Stale-State and Bandwidth-Asymmetric Networks

Jiaqi Liu, Chunyang Zhang, Heng Pan +1

With the rapid growth of large language model training and generative artificial intelligence services, data center networks face severe micro-burst traffic and high concurrency. T…

cs.CV2025

Follow-Your-Emoji-Faster: Towards Efficient, Fine-Controllable, and Expressive Freestyle Portrait Animation

Yue Ma, Zexuan Yan, Hongyu Liu +11

We present Follow-Your-Emoji-Faster, an efficient diffusion-based framework for freestyle portrait animation driven by facial landmarks. The main challenges in this task are preser…

cs.CV2024

Follow-Your-Emoji: Fine-Controllable and Expressive Freestyle Portrait Animation

Yue Ma, Hongyu Liu, Hongfa Wang +8

We present Follow-Your-Emoji, a diffusion-based framework for portrait animation, which animates a reference portrait with target landmark sequences. The main challenge of portrait…

cs.NI2021

NetFC: enabling accurate floating-point arithmetic on programmable switches

Penglai Cui, Heng Pan, Zhenyu Li +5

In-network computation has been widely used to accelerate data-intensive distributed applications. Some computational tasks, traditional performed on servers, are offloaded to the…

cs.NI2022

Enabling Fast and Flexible Distributed Deep Learning with Programmable Switches

Heng Pan, Penglai Cui, Zhenyu li +11

Deep learning has been used in a wide range of areas and made a huge breakthrough. With the ever-increasing model size and train-ing data volume, distributed deep learning emerges…

physics.optics2019

Phase-change silicon as an ultrafast active photonic platform

Letian Wang, Matthew Eliceiri, Yang Deng +5

Phase change material (PCM) features distinct optical or electronic properties between amorphous and crystalline states. Recently, it starts to play a key role in the emerging phot…

cs.CR2026

TurboRetry: Mitigating Large-Scale QUIC Handshake Floods with Off-the-Shelf DPU Offloading

Jiahao Wu, Heng Pan, Kai Lv +3

The modern transport protocol QUIC is designed to enhance network performance and security, but it remains vulnerable to handshake flooding attacks. Such attacks exhaust CPU resour…

cs.LG2024

FedAnchor: Enhancing Federated Semi-Supervised Learning with Label Contrastive Loss for Unlabeled Clients

Xinchi Qiu, Yan Gao, Lorenzo Sani +6

Federated learning (FL) is a distributed learning paradigm that facilitates collaborative training of a shared global model across devices while keeping data localized. The deploym…

cs.HC2023

Recent developments of selective laser processes for wearable devices

Youngchan Kim, Eunseung Hwang, Chang Kai +3

Recently, the growing interest in wearable technology for personal healthcare and smart VR/AR applications newly imposed a need for development of facile fabrication method. Regard…

physics.acc-ph2022

MQXFA Final Design Report

Giorgio Ambrosio, Kathleen Amm, Mike Anerella +29

The MQXFA Quadrupole magnets will be installed in High Luminosity LHC to form the Q1 and Q3 inner triplet optical elements in front of the interaction points 1 (ATLAS) and 5 (CMS).…

cs.CV2023

Img2Vec: A Teacher of High Token-Diversity Helps Masked AutoEncoders

Heng Pan, Chenyang Liu, Wenxiao Wang +4

We present a pipeline of Image to Vector (Img2Vec) for masked image modeling (MIM) with deep features. To study which type of deep features is appropriate for MIM as a learning tar…

eess.IV2020

Cloud Removal for Remote Sensing Imagery via Spatial Attention Generative Adversarial Network

Heng Pan

Optical remote sensing imagery has been widely used in many fields due to its high resolution and stable geometric properties. However, remote sensing imagery is inevitably affecte…

cs.IT2022

Digital Twin Assisted Task Offloading for Aerial Edge Computing and Networks

Bin Li, Yufeng Liu, Ling Tan +2

Considering the user mobility and unpredictable mobile edge computing (MEC) environments, this paper studies the intelligent task offloading problem in unmanned aerial vehicle (UAV…