activity
20242026
collaborators

8 papers

cs.CV2026

Simple Supervision Is Hard to Beat: A Bitter Lesson from Sparse Target Labels in Domain-Adaptive Object Detection

Lijun Zhang, Ruinian Xu, Mudit Agrawal

Source-free domain adaptive object detection adapts a source-trained detector to an unlabeled target domain, typically through teacher-student self-training with pseudo-labels. We…

cs.LG2026

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…

cs.CV2026

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…

cs.CV2026

RPiAE: A Representation-Pivoted Autoencoder Enhancing Both Image Generation and Editing

Yue Gong, Hongyu Li, Shanyuan Liu +8

Diffusion models have become the dominant paradigm for image generation and editing, with latent diffusion models shifting denoising to a compact latent space for efficiency and sc…

cs.LG2025

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…

cs.LG2025

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…