5 citations · 20 across the 11 of their papers we have counts for
11 papers
Reimagining Parameter Space Exploration with Diffusion Models
Lijun Zhang, Xiao Liu, Hui Guan
Adapting neural networks to new tasks typically requires task-specific fine-tuning, which is time-consuming and reliant on labeled data. We explore a generative alternative that pr…
ASTRA: Communication-Efficient Acceleration for Multi-Device Transformer Inference
Xiao Liu, Lijun Zhang, Deepak Ganesan +1
Multi-device inference can reduce Transformer latency by parallelizing computation. However, existing methods require high inter-device bandwidth, making them impractical for bandw…
Aligned Vector Quantization for Edge-Cloud Collabrative Vision-Language Models
Xiao Liu, Lijun Zhang, Deepak Ganesan +1
Vision Language Models (VLMs) are central to Visual Question Answering (VQA) systems and are typically deployed in the cloud due to their high computational demands. However, this…
Attack-Resilient Image Watermarking Using Stable Diffusion
Lijun Zhang, Xiao Liu, Antoni Viros Martin +3
Watermarking images is critical for tracking image provenance and proving ownership. With the advent of generative models, such as stable diffusion, that can create fake but realis…
Attacking All Tasks at Once Using Adversarial Examples in Multi-Task Learning
Lijun Zhang, Xiao Liu, Kaleel Mahmood +2
Visual content understanding frequently relies on multi-task models to extract robust representations of a single visual input for multiple downstream tasks. However, in comparison…
Uplifting Message Passing Neural Network with Graph Original Information
Xiao Liu, Lijun Zhang, Hui Guan
Message passing neural networks (MPNNs) learn the representation of graph-structured data based on graph original information, including node features and graph structures, and hav…
A Tree-Structured Multi-Task Model Recommender
Lijun Zhang, Xiao Liu, Hui Guan
Tree-structured multi-task architectures have been employed to jointly tackle multiple vision tasks in the context of multi-task learning (MTL). The major challenge is to determine…
Toward Compact Parameter Representations for Architecture-Agnostic Neural Network Compression
Yuezhou Sun, Wenlong Zhao, Lijun Zhang +3
This paper investigates deep neural network (DNN) compression from the perspective of compactly representing and storing trained parameters. We explore the previously overlooked op…
AutoMTL: A Programming Framework for Automating Efficient Multi-Task Learning
Lijun Zhang, Xiao Liu, Hui Guan
Multi-task learning (MTL) jointly learns a set of tasks by sharing parameters among tasks. It is a promising approach for reducing storage costs while improving task accuracy for m…
Rethinking Hard-Parameter Sharing in Multi-Domain Learning
Lijun Zhang, Qizheng Yang, Xiao Liu +1
Hard parameter sharing in multi-domain learning (MDL) allows domains to share some of the model parameters to reduce storage cost while improving prediction accuracy. One common sh…
SID-NISM: A Self-supervised Low-light Image Enhancement Framework
Lijun Zhang, Xiao Liu, Erik Learned-Miller +1
When capturing images in low-light conditions, the images often suffer from low visibility, which not only degrades the visual aesthetics of images, but also significantly degenera…