Publications (78)
A New Amharic Speech Emotion Dataset and Classification Benchmark
Ephrem A. Retta, Eiad Almekhlafi, Richard Sutcliffe +3
In this paper we present the Amharic Speech Emotion Dataset (ASED), which covers four dialects (Gojjam, Wollo, Shewa and Gonder) and five different emotions (neutral, fearful, happ…
Scalable Normalizing Flows Enable Boltzmann Generators for Macromolecules
Joseph C. Kim, David Bloore, Karan Kapoor +3
The Boltzmann distribution of a protein provides a roadmap to all of its functional states. Normalizing flows are a promising tool for modeling this distribution, but current metho…
Uncertainty relation in Schwarzschild spacetime
Jun Feng, Yao-Zhong Zhang, Mark D. Gould +1
We explore the entropic uncertainty relation in the curved background outside a Schwarzschild black hole, and find that Hawking radiation introduces a nontrivial modification on th…
Quantum Mpemba-like effect in Unruh thermalization
Zihao Wang, Wenjing Chen, Si-Wei Han +4
We revisit the thermal nature of the Unruh effect within a quantum thermodynamic framework. For a Unruh-deWitt (UDW) detector in -dimensional Minkowski spacetime, we demonstrate…
Work extraction from long-lived quantum coherence of a three-level system
Wenjing Chen, Si-Wei Han, Xiaoshan Feng +1
We analyze work extraction protocols using the long-lived quantum coherence of a three-level quantum system, which is coupled to a thermal bath through dipole-monopole interactions…
Design of optimal illumination patterns in single-pixel imaging using image dictionaries
Jun Feng, Shuming Jiao, Yang Gao +2
Single-pixel imaging (SPI) has a major drawback that many sequential illuminations are required for capturing one single image with long acquisition time. Basis illumination patter…
Learning to Collaborate: Multi-Scenario Ranking via Multi-Agent Reinforcement Learning
Jun Feng, Heng Li, Minlie Huang +4
Ranking is a fundamental and widely studied problem in scenarios such as search, advertising, and recommendation. However, joint optimization for multi-scenario ranking, which aims…
FaceShield: Explainable Face Anti-Spoofing with Multimodal Large Language Models
Hongyang Wang, Yichen Shi, Zhuofu Tao +7
Face anti-spoofing (FAS) is crucial for protecting facial recognition systems from presentation attacks. Previous methods approached this task as a classification problem, lacking…
Gaze-directed Vision GNN for Mitigating Shortcut Learning in Medical Image
Shaoxuan Wu, Xiao Zhang, Bin Wang +3
Deep neural networks have demonstrated remarkable performance in medical image analysis. However, its susceptibility to spurious correlations due to shortcut learning raises concer…
Entropic uncertainty relations under the relativistic motion
Jun Feng, Yao-Zhong Zhang, Mark D. Gould +1
The uncertainty principle bounds our ability to simultaneously predict two incompatible observables of a quantum particle. Assisted by a quantum memory to store the particle, this…
The Invitation Trap: Proactive Availability Backdoor in LLMs via Conversational Induction
He Wang, Jun Feng, Hong Sun +1
Current backdoor attacks against LLMs are typically manipulated by the attacker and remain passive. In this paper, we introduce the \textbf{Proactive Availability Backdoor (PAB)},…
ScalingNet: extracting features from raw EEG data for emotion recognition
Jingzhao Hu, Chen Wang, Qiaomei Jia +2
Convolutional Neural Networks(CNNs) has achieved remarkable performance breakthrough in a variety of tasks. Recently, CNNs based methods that are fed with hand-extracted EEG featur…
Determinant representations of scalar products for the open XXZ chain with non-diagonal boundary terms
Wen-Li Yang, Xi Chen, Jun Feng +4
With the help of the F-basis provided by the Drinfeld twist or factorizing F-matrix for the open XXZ spin chain with non-diagonal boundary terms, we obtain the determinant represen…
PASC-Net:Plug-and-play Shape Self-learning Convolutions Network with Hierarchical Topology Constraints for Vessel Segmentation
Xiao Zhang, Zhuo Jin, Shaoxuan Wu +6
Accurate vessel segmentation is crucial to assist in clinical diagnosis by medical experts. However, the intricate tree-like tubular structure of blood vessels poses significant ch…
Visual cryptography in single-pixel imaging
Shuming Jiao, Jun Feng, Yang Gao +2
Two novel visual cryptography (VC) schemes are proposed by combining VC with single-pixel imaging (SPI) for the first time. It is pointed out that the overlapping of visual key ima…
Quantum estimation in an expanding spacetime
Xiaoyang Huang, Jun Feng, Yao-Zhong Zhang +1
We investigate the quantum estimation on the Hubble parameter of an expanding de Sitter space by quantum metrological techniques. By exploring the dynamics of a freely falling Unru…
Optical machine learning with incoherent light and a single-pixel detector
Shuming Jiao, Jun Feng, Yang Gao +3
An optical diffractive neural network (DNN) can be implemented with a cascaded phase mask architecture. Like an optical computer, the system can perform machine learning tasks such…
Relation Mention Extraction from Noisy Data with Hierarchical Reinforcement Learning
Jun Feng, Minlie Huang, Yijie Zhang +2
In this paper we address a task of relation mention extraction from noisy data: extracting representative phrases for a particular relation from noisy sentences that are collected…
A Conflict-aware Evidential Framework for Reliable Sleep Stage Classification
Yunzhi Tian, Dekui Wang, Qirong Bu +3
Multi-view learning has been widely applied for sleep stage classification using multi-modal data. However, existing methods typically assume that different modalities are well-ali…
Adversary-Aware DPO: Enhancing Safety Alignment in Vision Language Models via Adversarial Training
Fenghua Weng, Jian Lou, Jun Feng +2
Safety alignment is critical in pre-training large language models (LLMs) to generate responses aligned with human values and refuse harmful queries. Unlike LLM, the current safety…
Software Engineering Solutions To Support Vertical Transportation
Alber J. Christianto, Peng Chen, Osheen Walawedura +4
In this paper we introduce the core results of the project on visualisation and analysis of data collected from the vertical transport facilities. The aim of the project was to pro…
A One-Step Model of Photoemission from Single Crystal Surfaces
Siddharth Karkare, Weishi Wan, Jun Feng +2
In this paper, we present a 3-D one step photoemission model that can be used to calculate the quantum efficiency and momentum distributions of electrons photoemitted from ordered…
Knowlege Graph Embedding by Flexible Translation
Jun Feng, Mantong Zhou, Yu Hao +2
Knowledge graph embedding refers to projecting entities and relations in knowledge graph into continuous vector spaces. State-of-the-art methods, such as TransE, TransH, and TransR…
Reliable quantum master equation of the Unruh-DeWitt detector
Si-Wei Han, Wenjing Chen, Langxuan Chen +2
In this paper, we present a method for estimating the validity range of the quantum Markovian master equation as applied to the Unruh-DeWitt (UDW) detector within a broader context…
Sequential Click Prediction for Sponsored Search with Recurrent Neural Networks
Yuyu Zhang, Hanjun Dai, Chang Xu +5
Click prediction is one of the fundamental problems in sponsored search. Most of existing studies took advantage of machine learning approaches to predict ad click for each event o…
Relative entropy formulation of thermalization process in a Schwarzschild spacetime
Si-Wei Han, Zhichun Ouyang, Zhiyao Hu +1
We revisit the problem of the thermalization process in an entropic formulation for the Unruh-DeWitt (UDW) detector outside a Schwarzschild black hole. We derive the late-time dyna…
Investigation of the near-threshold cluster resonance in
Hong-Liang Zang, Yan-Lin Ye, Zhi-Huan Li +26
An experiment for , inelastic excitation and decay was performed in inverse kinematics at a beam energy of 25.3…
BioMoTouch: Touch-Based Behavioral Authentication via Biometric-Motion Interaction Modeling
Zijian Ling, Jianbang Chen, Hongwei Li +6
Touch-based authentication is widely deployed on mobile devices due to its convenience and seamless user experience. However, existing systems largely model touch interaction as a…
Prompt-Guided Generation of Structured Chest X-Ray Report Using a Pre-trained LLM
Hongzhao Li, Hongyu Wang, Xia Sun +2
Medical report generation automates radiology descriptions from images, easing the burden on physicians and minimizing errors. However, current methods lack structured outputs and…
Quantum Fisher information as a probe for Unruh thermality
Jun Feng, Jing-Jun Zhang
A long-standing debate on Unruh effect is about its obscure thermal nature. In this Letter, we use quantum Fisher information (QFI) as an effective probe to explore the thermal nat…
Following the Diagnostic Trace: Visual Cognition-guided Cooperative Network for Chest X-Ray Diagnosis
Shaoxuan Wu, Jingkun Chen, Chong Ma +3
Computer-aided diagnosis (CAD) has significantly advanced automated chest X-ray diagnosis but remains isolated from clinical workflows and lacks reliable decision support and inter…
DeFacto: Counterfactual Thinking with Images for Enforcing Evidence-Grounded and Faithful Reasoning
Tianrun Xu, Haoda Jing, Ye Li +6
Recent advances in multimodal language models (MLLMs) have made thinking with images a dominant paradigm for multimodal reasoning. However, existing methods still fail to ensure ev…
The interplay between spatial and heliconical bond order in twist-bend nematic materials
Rony Saha, Chenrun Feng, Chris Welch +6
The nanostructure of two novel sulfur containing dimer materials has been investigated experimentally by hard and by resonant tender X-ray scattering techniques. On cooling the dim…
Reinforcement Learning for Relation Classification from Noisy Data
Jun Feng, Minlie Huang, Li Zhao +2
Existing relation classification methods that rely on distant supervision assume that a bag of sentences mentioning an entity pair are all describing a relation for the entity pair…
Understanding the Essence: Delving into Annotator Prototype Learning for Multi-Class Annotation Aggregation
Ju Chen, Jun Feng, Shenyu Zhang
Multi-class classification annotations have significantly advanced AI applications, with truth inference serving as a critical technique for aggregating noisy and biased annotation…
Analysis of Trace Impurities in Semiconductor Gas via Cavity-Enhanced Direct Frequency Comb Spectroscopy
Kevin C. Cossel, Florian Adler, Kris A. Bertness +4
Cavity-enhanced direct frequency comb spectroscopy (CE-DFCS) has demonstrated powerful potential for trace gas detection based on its unique combination of high bandwidth, rapid da…
Lookup subnet based Spatial Graph Convolutional neural Network
Jingzhao Hu, Xiaoqi Zhang, Qiaomei Jia +3
Convolutional Neural Networks(CNNs) has achieved remarkable performance breakthrough in Euclidean structure data. Recently, aggregation-transformation based Graph Neural networks(G…
Kinit Classification in Ethiopian Chants, Azmaris and Modern Music: A New Dataset and CNN Benchmark
Ephrem A. Retta, Richard Sutcliffe, Eiad Almekhlafi +6
In this paper, we create EMIR, the first-ever Music Information Retrieval dataset for Ethiopian music. EMIR is freely available for research purposes and contains 600 sample record…
Near atomically smooth alkali antimonide photocathode thin films
Jun Feng, Siddharth Karkare, James Nasiatka +3
Nano-roughness limits the emittance of electron beams that can be generated by high efficiency photocathodes, such as the thermally reacted alkali antimonide thin films. However th…
SHIELD : An Evaluation Benchmark for Face Spoofing and Forgery Detection with Multimodal Large Language Models
Yichen Shi, Yuhao Gao, Yingxin Lai +7
Multimodal large language models (MLLMs) have demonstrated strong capabilities in vision-related tasks, capitalizing on their visual semantic comprehension and reasoning capabiliti…
Notes on teleportation in an expanding space
Jun Feng, Wen-Li Yang, Yao-Zhong Zhang +1
We investigate the quantum teleportation between a conformal detector Alice and an inertial detector Bob in de Sitter space in two schemes, (i) one uses free scalar modes and (ii)…
MathReal: We Keep It Real! A Real Scene Benchmark for Evaluating Math Reasoning in Multimodal Large Language Models
Jun Feng, Zixin Wang, Zhentao Zhang +5
Multimodal Large Language Models (MLLMs) have demonstrated remarkable capabilities in visual mathematical reasoning across various existing benchmarks. However, these benchmarks ar…
Identification of New Assembly Mode in the Heliconical Nematic Phase via Tender Resonant X-ray Scattering
Yu Cao, Jun Feng, Asritha Nallapaneni +5
Helical structures are exciting and are utilized in numerous applications ranging from biotechnology to displays to medicine. Accurate description and understanding of resonance ef…
Fine-grained uncertainty relation under the relativistic motion
Jun Feng, Yao-Zhong Zhang, Mark D. Gould +1
Among various uncertainty relations, the profound fine-grained uncertainty relation is used to distinguish the uncertainty inherent in obtaining any combination of outcomes for dif…
Quantum Fisher information of a cosmic qubit undergoing non-Markovian de Sitter evolution
Langxuan Chen, Jun Feng
We revisit the problem of thermalization process for an Unruh-DeWitt (UDW) detector in de Sitter space. We derive the full dynamics of the detector in the context of open quantum s…
Cross-Corpus Multilingual Speech Emotion Recognition: Amharic vs. Other Languages
Ephrem Afele Retta, Richard Sutcliffe, Jabar Mahmood +6
In a conventional Speech emotion recognition (SER) task, a classifier for a given language is trained on a pre-existing dataset for that same language. However, where training data…
FAS-R1: A Unified Multi-Task MLLM for Reasoning Face Anti-Spoofing
Hongyang Wang, Yichen Shi, Hongrui Li +3
The paper introduces FAS-R1, a two‑stage multimodal large language model that simultaneously classifies face authenticity, identifies attack types, and localizes spoof regions, usi…
Sirens' Whisper: Inaudible Near-Ultrasonic Jailbreaks of Speech-Driven LLMs
Zijian Ling, Pingyi Hu, Xiuyong Gao +6
Speech-driven large language models (LLMs) are increasingly accessed through speech interfaces, introducing new security risks via open acoustic channels. We present Sirens' Whispe…
Invariant Content Synergistic Learning for Domain Generalization of Medical Image Segmentation
Yuxin Kang, Hansheng Li, Xuan Zhao +5
While achieving remarkable success for medical image segmentation, deep convolution neural networks (DCNNs) often fail to maintain their robustness when confronting test data with…
Stream-Flow Forecasting of Small Rivers Based on LSTM
Youchuan Hu, Le Yan, Tingting Hang +1
Stream-flow forecasting for small rivers has always been of great importance, yet comparatively challenging due to the special features of rivers with smaller volume. Artificial In…
UniShield: Unified Face Attack Detection via KG-Informed Multimodal Reasoning
Hongrui Li, Yichen Shi, Hongyang Wang +4
Unified face attack detection (UAD) requires recognizing physical spoofing and digital forgery within a shared decision space, yet existing discriminative or prompt-based methods l…
Scalar products of the open XYZ chain with non-diagonal boundary terms
Wen-Li Yang, Xi Chen, Jun Feng +4
With the help of the F-basis provided by the Drinfeld twist or factorizing F-matrix of the eight-vertex solid-on-solid (SOS) model, we obtain the determinant representations of the…
A Deep CNN Architecture with Novel Pooling Layer Applied to Two Sudanese Arabic Sentiment Datasets
Mustafa Mhamed, Richard Sutcliffe, Xia Sun +3
Arabic sentiment analysis has become an important research field in recent years. Initially, work focused on Modern Standard Arabic (MSA), which is the most widely-used form. Since…
HELPNet: Hierarchical Perturbations Consistency and Entropy-guided Ensemble for Scribble Supervised Medical Image Segmentation
Xiao Zhang, Shaoxuan Wu, Peilin Zhang +5
Creating fully annotated labels for medical image segmentation is prohibitively time-intensive and costly, emphasizing the necessity for innovative approaches that minimize relianc…
Coherence revival under the Unruh effect and its metrological advantage
Jiafan Wang, Jingjun Zhang, Jun Feng
In this paper, we investigate the quantum coherence extraction {between} two accelerating Unruh-DeWitt detectors, coupling to a scalar field in -dimensional Minkowski spacet…
Does deep learning always outperform simple linear regression in optical imaging?
Shuming Jiao, Yang Gao, Jun Feng +2
Deep learning has been extensively applied in many optical imaging applications in recent years. Despite the success, the limitations and drawbacks of deep learning in optical imag…
From Spatial Semantics to Temporal Context: Leveraging Gaze Trajectory for Weakly Supervised Medical Image Segmentation
Shaoxuan Wu, Xiao Zhang, Xiaodi Zhao +3
The paper introduces TrailNet, a weakly supervised medical image segmentation model that leverages clinicians' eye‑tracking fixations and gaze trajectories to capture spatial seman…
Multi-Kernel Filtering for Nonstationary Noise: An Extension of Bilateral Filtering Using Image Context
Feihong Liu, Jun Feng, Pew-Thian Yap +1
Bilateral filtering (BF) is one of the most classical denoising filters, however, the manually initialized filtering kernel hampers its adaptivity across images with various charac…
Free field realization of the exceptional current superalgebra $\hat{D(2,1;\a)}_k$
Xi Chen, Wen-Li Yang, Xiang-Mao Ding +4
The free-field representations of the $D(2,1;\a)$ current superalgebra and the corresponding energy-momentum tensor are constructed. The related screening currents of the first kin…
TABNet: A Triplet Augmentation Self-Recovery Framework with Boundary-Aware Pseudo-Labels for Medical Image Segmentation
Peilin Zhang, Shaouxan Wua, Jun Feng +5
Background and objective: Medical image segmentation is a core task in various clinical applications. However, acquiring large-scale, fully annotated medical image datasets is both…
Hawking radiation as tunneling and the unified first law of thermodynamics at the apparent horizon in the FRW universe
Ke-Xia Jiang, San-Min Ke, Dan-Tao Peng +1
Relations between the tunneling rate and the unified first law of thermodynamics at the apparent horizon of the FRW universe are investigated. The tunneling rate arises as a conseq…
DeepBundle: Fiber Bundle Parcellation with Graph Convolution Neural Networks
Feihong Liu, Jun Feng, Geng Chen +4
Parcellation of whole-brain tractography streamlines is an important step for tract-based analysis of brain white matter microstructure. Existing fiber parcellation approaches rely…
Rethinking the Necessity of Adaptive Retrieval-Augmented Generation through the Lens of Adaptive Listwise Ranking
Jun Feng, Jiahui Tang, Zhicheng He +5
Adaptive Retrieval-Augmented Generation aims to mitigate the interference of extraneous noise by dynamically determining the necessity of retrieving supplementary passages. However…
AHEAD: Advancing Multi-Class Label Aggregation with Interpretable Cross-Annotator Modeling
Ju Chen, Sijia Xu, Jun Feng +2
Crowdsourced labeling provides valuable labeled data for domains across natural language processing, computer vision, and video. Label aggregation aims to infer latent true labels…
Scalar perturbation of gravitating double-kink solutions
Jun Feng, Yuan Zhong
In this letter, a two-dimensional (2D) gravity-scalar model is studied. This model supports interesting double-kink solutions, and the corresponding metric solutions can be derived…
DiffuGR: Generative Document Retrieval with Diffusion Language Models
Xinpeng Zhao, Zhaochun Ren, Yukun Zhao +9
Generative retrieval (GR) reframes document retrieval as an end-to-end task of generating sequential document identifiers (DocIDs). Existing GR methods predominantly rely on left-t…
Bell inequalities violation within non-Bunch-Davies states
Jun Feng, Xiaoyang Huang, Yao-Zhong Zhang +1
We study the quantum nature of non-Bunch-Davies states in de Sitter space by evaluating CHSH inequality on a localized two-atom system. We show that quantum nonlocality can be gene…
Domain wall partition function of the eight-vertex model with a non-diagonal reflecting end
Wen-Li Yang, Xi Chen, Jun Feng +5
With the help of the Drinfeld twist or factorizing F-matrix for the eight-vertex SOS model, we obtain the explicit determinant expression of the partition function of the eight-ver…
Solution Transformations for GS String in AdS_5 x S^5 by Conserved Quantities
Zhan-Yun Wang, Xiao-Ning Xie, Jun Feng +3
For Light-cone gauge of Green-Schwarz superstring in AdS_5 x S^5 background, we fix two bosonic variables x^{+}=Ïand y^{9}=Ï, and then perform the partial Legendre transformation…
APS-LSTM: Exploiting Multi-Periodicity and Diverse Spatial Dependencies for Flood Forecasting
Jun Feng, Xueyi Liu, Jiamin Lu +1
Accurate flood prediction is crucial for disaster prevention and mitigation. Hydrological data exhibit highly nonlinear temporal patterns and encompass complex spatial relationship…
Drinfeld twist and symmetric Bethe vectors of the open XYZ chain with non-diagonal boundary terms
Wen-Li Yang, Xi Chen, Jun Feng +4
With the help of the Drinfeld twist or factorizing F-matrix for the eight-vertex solid-on-solid (SOS) model, we find that in the F-basis provided by the twist the two sets of pseud…
Quantum thermodynamics in a rotating BTZ black hole spacetime
Wenjing Chen, Yixuan Ma, Si-Wei Han +2
We address the problem of the thermalization process for an Unruh-DeWitt (UDW) detector outside a BTZ black hole, from a perspective of quantum thermodynamics. In the context of an…
Thermality of the Unruh effect with intermediate statistics
Jun Feng, Jing-Jun Zhang, Yihao Zhou
Utilizing quantum coherence monotone, we reexamine the thermal nature of the Unruh effect of an accelerating detector. We consider an UDW detector coupling to a n-dimensional confo…
Determinant formula for the partition function of the six-vertex model with a non-diagonal reflecting end
Wen-Li Yang, Xi Chen, Jun Feng +4
With the help of the F-basis provided by the Drinfeld twist or factorizing F-matrix for the open XXZ spin chain with non-diagonal boundary terms, we obtain the determinant represen…
Aggregating E-commerce Search Results from Heterogeneous Sources via Hierarchical Reinforcement Learning
Ryuichi Takanobu, Tao Zhuang, Minlie Huang +3
In this paper, we investigate the task of aggregating search results from heterogeneous sources in an E-commerce environment. First, unlike traditional aggregated web search that m…
A Quantum-Inspired Method for Three-Dimensional Ligand-Based Virtual Screening
Maritza Hernandez, Guo Liang Gan, Kirby Linvill +3
Measuring similarity between molecules is an important part of virtual screening (VS) experiments deployed during the early stages of drug discovery. Most widely used methods for e…
Probing Planckian physics in de Sitter space with quantum correlations
Jun Feng, Yao-Zhong Zhang, Mark D. Gould +3
We study the quantum correlation and quantum communication channel of both free scalar and fermionic fields in de Sitter space, while the Planckian modification presented by the ch…
Quantum correlations with vacuum ambiguity in de Sitter space
Jun Feng, Cheng-Yi Sun, Wen-Li Yang +2
We study the quantum correlations of free scalar field with vacuum ambiguity of de Sitter space. We show the occurrence of degradation of quantum entanglement and quantum discord b…