Publications (106)
SproutBench: A Benchmark for Safe and Ethical Large Language Models for Youth
Wenpeng Xing, Lanyi Wei, Haixiao Hu +5
The rapid proliferation of large language models (LLMs) in applications targeting children and adolescents necessitates a fundamental reassessment of prevailing AI safety framework…
Fingerprint Vector: Enabling Scalable and Efficient Model Fingerprint Transfer via Vector Addition
Zhenhua Xu, Qichen Liu, Zhebo Wang +4
Backdoor-based fingerprinting has emerged as an effective technique for tracing the ownership of large language models. However, in real-world deployment scenarios, developers ofte…
Argue with Me Tersely: Towards Sentence-Level Counter-Argument Generation
Jiayu Lin, Rong Ye, Meng Han +6
Counter-argument generation -- a captivating area in computational linguistics -- seeks to craft statements that offer opposing views. While most research has ventured into paragra…
Detecting Is Not Resolving: The Monitoring Control Gap in Retrieval Augmented LLMs
Zhe Yu, Wenpeng Xing, Chen Ye +4
Retrieval-augmented LLMs are deployed for tasks where evidence quality determines action safety, yet evaluation protocols assume that single-turn robustness predicts robustness whe…
Web Fraud Attacks Against LLM-Driven Multi-Agent Systems
Dezhang Kong, Hujin Peng, Yilun Zhang +5
With the proliferation of LLM-driven multi-agent systems (MAS), the security of Web links has become a critical concern. Once MAS is induced to trust a malicious link, attackers ca…
Latent Fusion Jailbreak: Blending Harmful and Harmless Representations to Elicit Unsafe LLM Outputs
Wenpeng Xing, Mohan Li, Bohan Yang +5
Safety-aligned large language models can still be manipulated through white-box interventions that modify their internal representations. We introduce Latent Fusion Jailbreak (LFJ)…
Privacy-Enhancing Technologies in Federated Learning for the Internet of Healthcare Things: A Survey
Fatemeh Mosaiyebzadeh, Seyedamin Pouriyeh, Reza M. Parizi +5
Advancements in wearable medical devices in IoT technology are shaping the modern healthcare system. With the emergence of the Internet of Healthcare Things (IoHT), we are witnessi…
Probing the ideal limit of interfacial thermal conductance in two-dimensional van der Waals heterostructures
Ting Liang, Ke Xu, Penghua Ying +9
Probing the ideal limit of interfacial thermal conductance (ITC) in two-dimensional (2D) heterointerfaces is of paramount importance for assessing heat dissipation in 2D-based nano…
Laser-assisted Fano resonance: attosecond quantum control and dynamical imaging
Meng Han, Hao Liang, Jia-bao Ji +4
A Fano resonance arises from the pathway interference between discrete and continuum states, playing a fundamental role in many branches of physics, chemistry and material science.…
E-SAGE: Explainability-based Defense Against Backdoor Attacks on Graph Neural Networks
Dingqiang Yuan, Xiaohua Xu, Lei Yu +3
Graph Neural Networks (GNNs) have recently been widely adopted in multiple domains. Yet, they are notably vulnerable to adversarial and backdoor attacks. In particular, backdoor at…
Silencing the Guardrails: Inference-Time Jailbreaking via Dynamic Contextual Representation Ablation
Wenpeng Xing, Moran Fang, Guangtai Wang +2
While Large Language Models (LLMs) have achieved remarkable performance, they remain vulnerable to jailbreak attacks that circumvent safety constraints. Existing strategies, rangin…
Scribble-based 3D Multiple Abdominal Organ Segmentation via Triple-branch Multi-dilated Network with Pixel- and Class-wise Consistency
Meng Han, Xiangde Luo, Wenjun Liao +3
Multi-organ segmentation in abdominal Computed Tomography (CT) images is of great importance for diagnosis of abdominal lesions and subsequent treatment planning. Though deep learn…
"Is your explanation stable?": A Robustness Evaluation Framework for Feature Attribution
Yuyou Gan, Yuhao Mao, Xuhong Zhang +5
Understanding the decision process of neural networks is hard. One vital method for explanation is to attribute its decision to pivotal features. Although many algorithms are propo…
Dual-view Curricular Optimal Transport for Cross-lingual Cross-modal Retrieval
Yabing Wang, Shuhui Wang, Hao Luo +5
Current research on cross-modal retrieval is mostly English-oriented, as the availability of a large number of English-oriented human-labeled vision-language corpora. In order to b…
Direct Behavior Optimization: Unlocking the Potential of Lightweight LLMs
Hongming Yang, Shi Lin, Jun Shao +4
Lightweight Large Language Models (LwLLMs) are reduced-parameter, optimized models designed to run efficiently on consumer-grade hardware, offering significant advantages in resour…
MEraser: An Effective Fingerprint Erasure Approach for Large Language Models
Jingxuan Zhang, Zhenhua Xu, Rui Hu +3
Large Language Models (LLMs) have become increasingly prevalent across various sectors, raising critical concerns about model ownership and intellectual property protection. Althou…
CaMDN: Enhancing Cache Efficiency for Multi-tenant DNNs on Integrated NPUs
Tianhao Cai, Liang Wang, Limin Xiao +4
With the rapid development of DNN applications, multi-tenant execution, where multiple DNNs are co-located on a single SoC, is becoming a prevailing trend. Although many methods ar…
SRAF: Stealthy and Robust Adversarial Fingerprint for Copyright Verification of Large Language Models
Zhebo Wang, Zhenhua Xu, Maike Li +4
The protection of Intellectual Property (IP) for Large Language Models (LLMs) has become a critical concern as model theft and unauthorized commercialization escalate. While advers…
Blockchain Architecture forAuditing Automation and TrustBuilding in Public Markets
Sean Cao, Lin William Cong, Meng Han +2
Business transactions by public firms are required to be reported, verified, and audited periodically, which is traditionally a labor-intensive and time-consuming process. To strea…
Attosecond metrology in circular polarization
Meng Han, Jia-bao Ji, Kiyoshi Ueda +1
Attosecond metrology with linearly polarized light pulses is the basis of a highly successful research area. An even broader impact can be expected from a generalized metrology tha…
Copyright Protection for Large Language Models: A Survey of Methods, Challenges, and Trends
Zhenhua Xu, Xubin Yue, Zhebo Wang +9
Copyright protection for large language models is of critical importance, given their substantial development costs, proprietary value, and potential for misuse. Existing surveys h…
A Survey of Privacy Threats and Defense in Vertical Federated Learning: From Model Life Cycle Perspective
Lei Yu, Meng Han, Yiming Li +8
Vertical Federated Learning (VFL) is a federated learning paradigm where multiple participants, who share the same set of samples but hold different features, jointly train machine…
IAG: Induction-Augmented Generation Framework for Answering Reasoning Questions
Zhebin Zhang, Xinyu Zhang, Yuanhang Ren +5
Retrieval-Augmented Generation (RAG), by incorporating external knowledge with parametric memory of language models, has become the state-of-the-art architecture for open-domain QA…
Policy of Thoughts: Scaling Test-Time Training for LLM Reasoning via Online Policy Evolution
Zhengbo Jiao, Hongyu Xian, Qinglong Wang +5
The paper introduces Policy of Thoughts (PoT), a test‑time training framework that continuously updates a lightweight LoRA adapter using online policy optimization to improve large…
The Attribution Blind Spot: Detecting When Language Models Rely on Memory Rather Than Retrieved Context
Zhe Yu, Wenpeng Xing, Yunzhao Wei +4
Retrieval-augmented generation promises to ground language model outputs in external evidence, yet the field has no reliable way to verify whether retrieved context actually govern…
Towards Robust and Secure Embodied AI: A Survey on Vulnerabilities and Attacks
Wenpeng Xing, Minghao Li, Mohan Li +1
Embodied AI systems, including robots and autonomous vehicles, are increasingly integrated into real-world applications, where they encounter a range of vulnerabilities stemming fr…
FineQ: Software-Hardware Co-Design for Low-Bit Fine-Grained Mixed-Precision Quantization of LLMs
Xilong Xie, Liang Wang, Limin Xiao +4
Large language models (LLMs) have significantly advanced the natural language processing paradigm but impose substantial demands on memory and computational resources. Quantization…
Observation of Nuclear-wavepacket Interference in Ultrafast Inter-atomic Energy Transfer
Meng Han, Jacqueline Fedyk, Jia-Bao Ji +3
We report the experimental observation of quantum interference in the nuclear wave-packet dynamics driving ultrafast excitation-energy transfer in argon dimers below the threshold…
SME-YOLO: A Real-Time Detector for Tiny Defect Detection on PCB Surfaces
Meng Han
Surface defects on Printed Circuit Boards (PCBs) directly compromise product reliability and safety. However, achieving high-precision detection is challenging because PCB defects…
Uncovering Promises and Challenges of Federated Learning to Detect Cardiovascular Diseases: A Scoping Literature Review
Sricharan Donkada, Seyedamin Pouriyeh, Reza M. Parizi +4
Cardiovascular diseases (CVD) are the leading cause of death globally, and early detection can significantly improve outcomes for patients. Machine learning (ML) models can help di…
ReDas: A Lightweight Architecture for Supporting Fine-Grained Reshaping and Multiple Dataflows on Systolic Array
Meng Han, Liang Wang, Limin Xiao +4
The systolic accelerator is one of the premier architectural choices for DNN acceleration. However, the conventional systolic architecture suffers from low PE utilization due to th…
FIDES: Faithful Inference via Deep Evidence Signals for Retrieval-Memory Conflict in RAG
Zhe Yu, Wenpeng Xing, Tiancheng Zhao +3
When retrieved evidence contradicts parametric memory, language models frequently ignore context and default to memorized priors -- a failure that undermines the core purpose of re…
UW-3DGS: Underwater 3D Reconstruction with Physics-Aware Gaussian Splatting
Wenpeng Xing, Jie Chen, Zaifeng Yang +5
Underwater 3D scene reconstruction faces severe challenges from light absorption, scattering, and turbidity, which degrade geometry and color fidelity in traditional methods like N…
ForgetMark: Stealthy Fingerprint Embedding via Targeted Unlearning in Language Models
Zhenhua Xu, Haobo Zhang, Zhebo Wang +4
Existing invasive (backdoor) fingerprints suffer from high-perplexity triggers that are easily filtered, fixed response patterns exposed by heuristic detectors, and spurious activa…
Improving General Role-Playing Agents via Psychology-Grounded Reasoning and Role-Aware Policy Optimization
Zhenhua Xu, Dongsheng Chen, Jian Li +7
Building general-purpose role-playing agents that faithfully portray any character from a natural-language profile remains challenging. The dominant paradigm -- supervised fine-tun…
Circular RABBITT goes under threshold
Vladislav V. Serov, Jia-Bao Ji, Meng Han +3
We introduce circular under-threshold RABBITT (cuRABBITT) as a new interferometric method to probe discrete electronic excitations in atoms with attosecond resolution. By combining…
Comment on "Brilliant source of 19.2 attosecond soft X-ray pulses below the atomic unit of time"
Meng Han
A recent preprint by Ardana-Lamas et al. (Ref. [1], arXiv:2510.04086) re-analyzes the data set of the attosecond streaking experiment on krypton atoms originally reported in Phys R…
AttnDiff: Attention-based Differential Fingerprinting for Large Language Models
Haobo Zhang, Zhenhua Xu, Junxian Li +3
Protecting the intellectual property of open-weight large language models (LLMs) requires verifying whether a suspect model is derived from a victim model despite common laundering…
MEUV: Achieving Fine-Grained Capability Activation in Large Language Models via Mutually Exclusive Unlock Vectors
Xin Tong, Zhi Lin, Jingya Wang +2
Large language models (LLMs) enforce safety alignment to reliably refuse malicious requests, yet the same blanket safeguards also block legitimate uses in policing, defense, and ot…
The quantum tunnel effect of photon in one-dimensional photonic crystals
Ming-li Ren, Han Liu, Qing-Pan +4
In the paper, we have given the quantum transmissivity, probability density and probability current density of photon in one-dimensional photonic crystals with the quantum…
Learning-Driven Adaptive Audit Scheduling: A Sequential Decision Approach to Off-Chain Data Integrity
Changting Lin, Fan Li, Weihang Yu +4
We model cryptographic auditing of off-chain data as a Constrained MDP (CMDP) under partial observability: the storage node's hidden type and corruption state make the problem a PO…
EverTracer: Hunting Stolen Large Language Models via Stealthy and Robust Probabilistic Fingerprint
Zhenhua Xu, Meng Han, Wenpeng Xing
The proliferation of large language models (LLMs) has intensified concerns over model theft and license violations, necessitating robust and stealthy ownership verification. Existi…
MalURLBench: A Benchmark Evaluating Agents' Vulnerabilities When Processing Web URLs
Dezhang Kong, Zhuxi Wu, Shiqi Liu +8
LLM-based web agents have become increasingly popular for their utility in daily life and work. However, they exhibit critical vulnerabilities when processing malicious URLs: accep…
MCP-Guard: A Multi-Stage Defense-in-Depth Framework for Securing Model Context Protocol in Agentic AI
Wenpeng Xing, Zhonghao Qi, Yupeng Qin +6
While Large Language Models (LLMs) have achieved remarkable performance, they remain vulnerable to jailbreak. The integration of Large Language Models (LLMs) with external tools vi…
CTCC: A Robust and Stealthy Fingerprinting Framework for Large Language Models via Cross-Turn Contextual Correlation Backdoor
Zhenhua Xu, Xixiang Zhao, Xubin Yue +3
The widespread deployment of large language models (LLMs) has intensified concerns around intellectual property (IP) protection, as model theft and unauthorized redistribution beco…
DNF: Dual-Layer Nested Fingerprinting for Large Language Model Intellectual Property Protection
Zhenhua Xu, Yiran Zhao, Mengting Zhong +4
The rapid growth of large language models raises pressing concerns about intellectual property protection under black-box deployment. Existing backdoor-based fingerprints either re…
GenTel-Safe: A Unified Benchmark and Shielding Framework for Defending Against Prompt Injection Attacks
Rongchang Li, Minjie Chen, Chang Hu +3
Large Language Models (LLMs) like GPT-4, LLaMA, and Qwen have demonstrated remarkable success across a wide range of applications. However, these models remain inherently vulnerabl…
Abnormally High Thermal Conductivity in Fivefold Twinned Diamond Nanowires
Ting Liang, Ke Xu, Meng Han +5
Fivefold twins (5FTs), discovered nearly 200 years ago, are a common multiply twinned structure that usually dramatically deteriorate the thermal transport properties of nanomateri…
Partial wave effects in the heavy quarkonium radiative electromagnetic decays
Su-Yan Pei, Wei Li, Ting-Ting Liu +3
In a previous paper \cite{Bc}, it was pointed out that the wave functions of all particles are not pure waves, besides the main partial waves, they all contain {other partial waves…
ATA-Cache: Contention Mitigation for GPU Shared L1 Cache with Aggregated Tag Array
Xiangrong Xu, Liang Wang, Limin Xiao +4
GPU shared L1 cache is a promising architecture while still suffering from high resource contentions. We present a GPU shared L1 cache architecture with an aggregated tag array tha…
MO-RiskVAE: A Multi-Omics Variational Autoencoder for Survival Risk Modeling in Multiple MyelomaMO-RiskVAE
Zixuan Chen, Heng Zhang, YuPeng Qin +5
Multimodal variational autoencoders (VAEs) have emerged as a powerful framework for survival risk modeling in multiple myeloma by integrating heterogeneous omics and clinical data.…
Attosecond Control and Measurement of Chiral Photoionisation Dynamics
Meng Han, Jia-Bao Ji, Alexander Blech +5
Many chirality-sensitive light-matter interactions are governed by chiral electron dynamics. Therefore, the development of advanced technologies harnessing chiral phenomena would c…
Machine Learning Research Towards Combating COVID-19: Virus Detection, Spread Prevention, and Medical Assistance
Osama Shahid, Mohammad Nasajpour, Seyedamin Pouriyeh +6
COVID-19 was first discovered in December 2019 and has continued to rapidly spread across countries worldwide infecting thousands and millions of people. The virus is deadly, and p…
Local Distance Query with Differential Privacy
Weihong Sheng, Jiajun Chen, Bin Cai +3
Differential Privacy (DP) is commonly employed to safeguard graph analysis or publishing. Distance, a critical factor in graph analysis, is typically handled using curator DP, wher…
AdaMARP: An Adaptive Multi-Agent Interaction Framework for General Immersive Role-Playing
Zhenhua Xu, Dongsheng Chen, Shuo Wang +4
LLM role-playing aims to portray arbitrary characters in interactive narratives, yet existing systems often suffer from limited immersion and adaptability. They typically under-mod…
A Survey of LLM-Driven AI Agent Communication: Protocols, Security Risks, and Defense Countermeasures
Dezhang Kong, Shi Lin, Zhenhua Xu +16
In recent years, Large-Language-Model-driven AI agents have exhibited unprecedented intelligence and adaptability. Nowadays, agents are undergoing a new round of evolution. They no…
PREE: Towards Harmless and Adaptive Fingerprint Editing in Large Language Models via Knowledge Prefix Enhancement
Xubin Yue, Zhenhua Xu, Wenpeng Xing +3
Addressing the intellectual property protection challenges in commercial deployment of large language models (LLMs), existing black-box fingerprinting techniques face dual challeng…
Coordinating Flexible Demand Response and Renewable Uncertainties for Scheduling of Community Integrated Energy Systems with an Electric Vehicle Charging Station: A Bi-level Approach
Yang Li, Meng Han, Zhen Yang +1
A community integrated energy system (CIES) with an electric vehicle charging station (EVCS) provides a new way for tackling growing concerns of energy efficiency and environmental…
Large-scale Multi-view Subspace Clustering in Linear Time
Zhao Kang, Wangtao Zhou, Zhitong Zhao +3
A plethora of multi-view subspace clustering (MVSC) methods have been proposed over the past few years. Researchers manage to boost clustering accuracy from different points of vie…
CoDe-NeRF: Neural Rendering via Dynamic Coefficient Decomposition
Wenpeng Xing, Jie Chen, Zaifeng Yang +5
Neural Radiance Fields (NeRF) have shown impressive performance in novel view synthesis, but challenges remain in rendering scenes with complex specular reflections and highlights.…
Hearing carrier-envelope offset frequency and phase in air with a microphone
Meng Han, Ming-Chang Chen, Ming-Shian Tsai +1
Attosecond science and frequency metrology rely on the precise measurement and control of the laser pulse waveform, a feat traditionally achieved using optoelectronic techniques. I…
FedWeave: Rethinking the Unit of Specialization in Heterogeneous Federated MoE-LoRA
Donghang Duan, Xu Zheng, Lizong Zhang +2
The paper introduces FedWeave, a federated learning framework that separates expert aggregation from router optimization to better handle heterogeneous tasks by using prototype-lev…
Decay properties of as a conventional meson
Meng Han, Wei Li, Su-Yan Pei +2
Taking as a conventional meson, we calculate its dominant strong and electromagnetic decays in the framework of the Bethe-Salpeter method. Our res…
LLMs can be Dangerous Reasoners: Analyzing-based Jailbreak Attack on Large Language Models
Shi Lin, Hongming Yang, Rongchang Li +4
The rapid development of Large Language Models (LLMs) has brought impressive advancements across various tasks. However, despite these achievements, LLMs still pose inherent safety…
NeuRel-Attack: Neuron Relearning for Safety Disalignment in Large Language Models
Yi Zhou, Wenpeng Xing, Dezhang Kong +2
Safety alignment in large language models (LLMs) is achieved through fine-tuning mechanisms that regulate neuron activations to suppress harmful content. In this work, we propose a…
Differentially Private Distance Query with Asymmetric Noise
Weihong Sheng, Jiajun Chen, Chunqiang Hu +3
With the growth of online social services, social information graphs are becoming increasingly complex. Privacy issues related to analyzing or publishing on social graphs are also…
Two-center Interference in the Photoionization Delays of Kr2
Saijoscha Heck, Meng Han, Denis Jelovina +6
We present the experimental observation of two-center interference in the ionization time delays of Kr2. Using attosecond electron-ion-coincidence spectroscopy, we simultaneously m…
From Retinal Evidence to Safe Decisions: RETINA-SAFE and ECRT for Hallucination Risk Triage in Medical LLMs
Zhe Yu, Wenpeng Xing, Meng Han
Hallucinations in medical large language models (LLMs) remain a safety-critical issue, particularly when available evidence is insufficient or conflicting. We study this problem in…
Hi-ArG: Exploring the Integration of Hierarchical Argumentation Graphs in Language Pretraining
Jingcong Liang, Rong Ye, Meng Han +6
The knowledge graph is a structure to store and represent knowledge, and recent studies have discussed its capability to assist language models for various applications. Some varia…
Attosecond-resolved probing of recolliding electron wave packets in liquids and aqueous solutions
Angana Mondal, Nicolas Tancogne-Dejean, George Trenins +8
High-harmonic spectroscopy (HHS) in liquids promises real-time access to ultrafast electronic dynamics in the native environment of chemical and biological processes. While electro…
LAFA: Agentic LLM-Driven Federated Analytics over Decentralized Data Sources
Haichao Ji, Zibo Wang, Cheng Pan +4
Large Language Models (LLMs) have shown great promise in automating data analytics tasks by interpreting natural language queries and generating multi-operation execution plans. Ho…
Adversarial Examples Versus Cloud-based Detectors: A Black-box Empirical Study
Xurong Li, Shouling Ji, Meng Han +4
Deep learning has been broadly leveraged by major cloud providers, such as Google, AWS and Baidu, to offer various computer vision related services including image classification,…
Scalpel-SAM: A Semi-Supervised Paradigm for Adapting SAM to Infrared Small Object Detection
Zihan Liu, Xiangning Ren, Dezhang Kong +2
Infrared small object detection urgently requires semi-supervised paradigms due to the high cost of annotation. However, existing methods like SAM face significant challenges of do…
Analytical Expression for Continuum-continuum Transition Amplitude of Hydrogen-like Atoms with Angular-momentum Dependence
Jia-Bao Ji, Kiyoshi Ueda, Meng Han +1
Attosecond chronoscopy typically utilises interfering two-photon transitions to access the phase information. Simulating these two-photon transitions is challenging due to the cont…
Photoelectronic mapping of spin-orbit interaction of intense light fields
Yiqi Fang, Meng Han, Peipei Ge +6
The interaction between a quantum particle's spin angular momentum and its orbital angular momentum is ubiquitous in nature. In optics, the spin-orbit optical phenomenon is closely…
Query Structure Modeling for Inductive Logical Reasoning Over Knowledge Graphs
Siyuan Wang, Zhongyu Wei, Meng Han +4
Logical reasoning over incomplete knowledge graphs to answer complex logical queries is a challenging task. With the emergence of new entities and relations in constantly evolving…
Artifact Correction in Magnetic Resonance Temperature Imaging for Laser Interstitial Thermotherapy with Multi-echo Acquisitions
Ziyi Pan, Yuancheng Jiang, Wenbo Lv +9
In MRI-guided laser interstitial thermotherapy (MRgLITT), a signal void sometimes appears at the heating center of the measured temperature map. In neurosurgical MRgLITT treatments…
ICPO: Illocution-Calibrated Policy Optimization for Multi-Turn Conversation
Zhebo Wang, Xiaohu Mu, Zijie Zhou +4
Large Language Models (LLMs) in multi-turn conversations often suffer from a ``lost-in-conversation'' phenomenon, where they struggle to recover from early incorrect assumptions, p…
The partial waves of and their contributions in strong decays
Ting-Ting Liu, Su-Yan Pei, Wei Li +2
By adopting the relativistic Bethe-Salpeter method, the OZI allowed strong decays of the state are studied, emphasis is paid to the relativistic correct…
Revisiting self-seeding mechanism by generating vector ultraviolet N lasing
Jingsong Gao, Yang Wang, Jiahao Dong +5
An intense femtosecond laser pulse can generate ultraviolet air lasing, offering a promising remote light source. A long-standing hypothesis is whether it is seeded by a self-gener…
DIAP: A Decentralized Agent Identity Protocol with Zero-Knowledge Proofs and a Hybrid P2P Stack
Yuanjie Liu, Wenpeng Xing, Ye Zhou +3
The absence of a fully decentralized, verifiable, and privacy-preserving communication protocol for autonomous agents remains a core challenge in decentralized computing. Existing…
The generalized Hamilton principle and non-Hermitian quantum theory
Xiang-Yao Wu, Ben-Shan Wu, Meng Han +5
The Hamilton principle is a variation principle describing the isolated and conservative systems, its Lagrange function is the difference between kinetic energy and potential energ…
Deep Reinforcement Learning-driven Cross-Community Energy Interaction Optimal Scheduling
Yang Li, Wenjie Ma, Fanjin Bu +3
In order to coordinate energy interactions among various communities and energy conversions among multi-energy subsystems within the multi-community integrated energy system under…
Asymmetric stress engineering of dense dislocations in brittle superconductors for strong vortex pinning
Meng Han, Chiheng Dong, Chao Yao +17
Large lossless currents in high-temperature superconductors (HTS) critically rely on dense defects with suitable size and dimensionality to pin vortices, with dislocations being pa…
Data-Driven Distributionally Robust Scheduling of Community Integrated Energy Systems with Uncertain Renewable Generations Considering Integrated Demand Response
Yang Li, Meng Han, Mohammad Shahidehpour +2
A community integrated energy system (CIES) is an important carrier of the energy internet and smart city in geographical and functional terms. Its emergence provides a new solutio…
TriLens: Per-Layer Logit-Lens Entropy for White-Box Hallucination Detection
Bohan Yang, Yijun Gong, Zhi Zhang +3
When a language model hallucinates, the final answer is wrong, but the mistake is not necessarily invisible inside the model. Different internal pathways may remain uncertain, disa…
Spectral Logit Sculpting: Adaptive Low-Rank Logit Transformation for Controlled Text Generation
Jin Li, Zhebo Wang, Tianliang Lu +3
Entropy-based inference methods have gained traction for improving the reliability of Large Language Models (LLMs). However, many existing approaches, such as entropy minimization…
Composition Collapse: Stable Factual Knowledge Does Not Imply Compositional Reasoning
Zhe Yu, Wenpeng Xing, Yunzhao Wei +4
Post-training is routinely evaluated through aggregate benchmark scores that treat multi-hop reasoning as a single capability -- as if a model that answers more questions correctly…
Unlocking the Effectiveness of LoRA-FP for Seamless Transfer Implantation of Fingerprints in Downstream Models
Zhenhua Xu, Zhaokun Yan, Binhan Xu +4
With the rapid advancement of large language models (LLMs), safeguarding intellectual property (IP) has become increasingly critical. To address the challenges of high costs and po…
Debatrix: Multi-dimensional Debate Judge with Iterative Chronological Analysis Based on LLM
Jingcong Liang, Rong Ye, Meng Han +4
How can we construct an automated debate judge to evaluate an extensive, vibrant, multi-turn debate? This task is challenging, as judging a debate involves grappling with lengthy t…
Degrading Voice: A Comprehensive Overview of Robust Voice Conversion Through Input Manipulation
Xining Song, Zhihua Wei, Rui Wang +3
Identity, accent, style, and emotions are essential components of human speech. Voice conversion (VC) techniques process the speech signals of two input speakers and other modaliti…
Time-domain measurement of Auger electron dynamics in xenon atoms after giant resonant photoionization
Mahmudul Hasan, Jingsong Gao, Hao Liang +7
Time-resolved measurement of Auger-Meitner (AM) decay [Nature 419, 803 (2002)] marked a milestone in the development of attosecond science. To date, the time constants for the AM d…
KinGuard: Hierarchical Kinship-Aware Fingerprinting to Defend Against Large Language Model Stealing
Zhenhua Xu, Xiaoning Tian, Wenjun Zeng +5
Protecting the intellectual property of large language models requires robust ownership verification. Conventional backdoor fingerprinting, however, is flawed by a stealth-robustne…
Attosecond X-ray Core-level Chronoscopy of Aromatic Molecules
Jia-Bao Ji, Zhaoheng Guo, Taran Driver +32
Attosecond photoemission or photoionization delays are a unique probe of the structure and the electronic dynamics of matter. However, spectral congestion and spatial delocalizatio…
Relation Between Photoionisation Cross Sections and Attosecond Time Delays
Jia-Bao Ji, Anatoli S. Kheifets, Meng Han +2
Determination and interpretation of Wigner-like photoionisation delays is one of the most active fields of attosecond science. Previous results have suggested that large photoionis…
FuseFPS: Accelerating Farthest Point Sampling with Fusing KD-tree Construction for Point Clouds
Meng Han, Liang Wang, Limin Xiao +5
Point cloud analytics has become a critical workload for embedded and mobile platforms across various applications. Farthest point sampling (FPS) is a fundamental and widely used k…
Strongly Anisotropic Thermal and Electrical Conductivities of Self-assembled Silver Nanowire Network
Zhe Cheng, Meng Han, Pengyu Yuan +3
Heat dissipation issues are the emerging challenges in the field of flexible electronics. Thermal management of flexible electronics creates a demand for flexible materials with hi…
LatentAudit: Real-Time White-Box Faithfulness Monitoring for Retrieval-Augmented Generation with Verifiable Deployment
Zhe Yu, Wenpeng Xing, Meng Han
Retrieval-augmented generation (RAG) mitigates hallucination but does not eliminate it: a deployed system must still decide, at inference time, whether its answer is actually suppo…
CopyrightMeter: Revisiting Copyright Protection in Text-to-image Models
Naen Xu, Changjiang Li, Tianyu Du +8
Text-to-image diffusion models have emerged as powerful tools for generating high-quality images from textual descriptions. However, their increasing popularity has raised signific…
Pushing the Limits of Safety: A Technical Report on the ATLAS Challenge 2025
Zonghao Ying, Siyang Wu, Run Hao +44
Multimodal Large Language Models (MLLMs) have enabled transformative advancements across diverse applications but remain susceptible to safety threats, especially jailbreak attacks…