papers

Publications (15)

cs.SD2026

Edge-Cloud Collaborative Speech Emotion Captioning via Token-Level Speculative Decoding in Audio-Language Models

Xiangyuan Xue, Jiajun Lu, Yan Gao +3

Speech Emotion Captioning (SEC) leverages large audio-language models to generate rich, context-aware affective descriptions from speech. However, real-world deployment remains cha…

cs.SD2023

Dynamic Prediction of Full-Ocean Depth SSP by Hierarchical LSTM: An Experimental Result

Jiajun Lu, Wei Huang, Hao Zhang

SSP distribution is an important parameter for underwater positioning, navigation and timing (PNT) because it affects the propagation mode of underwater acoustic signals. To accura…

cs.CV2017

SafetyNet: Detecting and Rejecting Adversarial Examples Robustly

Jiajun Lu, Theerasit Issaranon, David Forsyth

We describe a method to produce a network where current methods such as DeepFool have great difficulty producing adversarial samples. Our construction suggests some insights into h…

cs.CV2017

Learning Diverse Image Colorization

Aditya Deshpande, Jiajun Lu, Mao-Chuang Yeh +2

Colorization is an ambiguous problem, with multiple viable colorizations for a single grey-level image. However, previous methods only produce the single most probable colorization…

cs.CV2017

NO Need to Worry about Adversarial Examples in Object Detection in Autonomous Vehicles

Jiajun Lu, Hussein Sibai, Evan Fabry +1

It has been shown that most machine learning algorithms are susceptible to adversarial perturbations. Slightly perturbing an image in a carefully chosen direction in the image spac…

cond-mat.mtrl-sci2025

Nonvolatile Electrical Control of Spin via Sliding Fractional Quantum Multiferroics

Jiajun Lu, Mu Tian, Chaoxi Cui +3

We propose a fractionally quantized polarization induced by interlayer sliding in bilayer altermagnets, unveiling a previously unrecognized multiferroic phase termed sliding fracti…