Publications (81)
Sigma: Differential Rescaling of Query, Key and Value for Efficient Language Models
Zhenghao Lin, Zihao Tang, Xiao Liu +31
We introduce Sigma, an efficient large language model specialized for the system domain, empowered by a novel architecture including DiffQKV attention, and pre-trained on our metic…
Harmonic and Interharmonic Detection in Power Systems Based on Fractal-Optimized Variational Mode Decomposition
Pei Yuhang, Yu Min, Yu Yan
The proposed method introduces a parameter determination approach based on the minimum Fractal box dimension (FBD) of Variational Mode Decomposition (VMD) components, aiming to add…
Explainable Biomedical Hypothesis Generation via Retrieval Augmented Generation enabled Large Language Models
Alexander R. Pelletier, Joseph Ramirez, Irsyad Adam +6
The vast amount of biomedical information available today presents a significant challenge for investigators seeking to digest, process, and understand these findings effectively.…
QCFE: An efficient Feature engineering for query cost estimation
Yu Yan, Hongzhi Wang, Junfang Huang +5
Query cost estimation is a classical task for database management. Recently, researchers apply the AI-driven model to implement query cost estimation for achieving high accuracy. H…
Observation and Modulation of the Quantum Mpemba Effect on a Superconducting Quantum Processor
Yueshan Xu, Cai-Ping Fang, Bing-Jie Chen +33
In non-equilibrium quantum systems, the quantum Mpemba effect (QME) emerges as a counterintuitive phenomenon: systems exhibiting greater initial symmetry breaking restore symmetry…
On Local Solutions of Second Order Quasi-linear Elliptic Systems with Arbitrary 1-Jet at a Point
Yifei Pan, Yu Yan
We prove a general result on the existence of local solutions of any second order quasi-linear elliptic system with arbitrary 1-jet at a point.
Factorisation-based Image Labelling
Yu Yan, Yael Balbastre, Mikael Brudfors +1
Segmentation of brain magnetic resonance images (MRI) into anatomical regions is a useful task in neuroimaging. Manual annotation is time consuming and expensive, so having a fully…
Gas pressure manipulation of exciton states in monolayer WS2
Shuangping Han, Pengyu Zan, Yu Yan +3
Over the past few decades, thin film optoelectronic devices based on transition metal dichalcogenides (TMDs) have made significant progress. However, the sensitivity of the exciton…
Watch Closely: Mitigating Object Hallucinations in Large Vision-Language Models with Disentangled Decoding
Ruiqi Ma, Yu Yan, Chunhong Zhang +4
Large Vision-Language Models (LVLMs) bridge the gap between visual and linguistic modalities, demonstrating strong potential across a variety of domains. However, despite significa…
Enhancing Mobile Face Anti-Spoofing: A Robust Framework for Diverse Attack Types under Screen Flash
Weihua Liu, Chaochao Lin, Yu Yan
Face anti-spoofing (FAS) is crucial for securing face recognition systems. However, existing FAS methods with handcrafted binary or pixel-wise labels have limitations due to divers…
Building an Ethical and Trustworthy Biomedical AI Ecosystem for the Translational and Clinical Integration of Foundational Models
Simha Sankar Baradwaj, Destiny Gilliland, Jack Rincon +9
Foundational Models (FMs) are gaining increasing attention in the biomedical AI ecosystem due to their ability to represent and contextualize multimodal biomedical data. These capa…
RT-DETRv4: Painlessly Furthering Real-Time Object Detection with Vision Foundation Models
Zijun Liao, Yian Zhao, Xin Shan +5
Real-time object detection has achieved substantial progress through meticulously designed architectures and optimization strategies. However, the pursuit of high-speed inference v…
Experience-Enhanced Learning: One Size Still does not Fit All in Automatic Database
Yu Yan, Hongzhi Wang, Jian Ma +2
Recent years, the database committee has attempted to develop automatic database management systems. Although some researches show that the applying AI to data management is a sign…
Tell Me How to Ask Again: Question Data Augmentation with Controllable Rewriting in Continuous Space
Dayiheng Liu, Yeyun Gong, Jie Fu +5
In this paper, we propose a novel data augmentation method, referred to as Controllable Rewriting based Question Data Augmentation (CRQDA), for machine reading comprehension (MRC),…
On a Local Radial Rigidity Phenomenon of Elliptic Systems on Riemannian Manifolds
Yifei Pan, Yu Yan, Yuan Zhang
In this paper, we study local radial rigidity phenomena for a broad class of general-order elliptic systems on Riemannian manifolds via a reduction to singular ordinary differentia…
Clinical Temporal Relation Extraction with Probabilistic Soft Logic Regularization and Global Inference
Yichao Zhou, Yu Yan, Rujun Han +5
There has been a steady need in the medical community to precisely extract the temporal relations between clinical events. In particular, temporal information can facilitate a vari…
Noise-tolerant correlated coincidence imaging based on super-correlated light at 1550 nm
Yu Yan, Jiamin Li, Ruikang Li +7
Single-photon-level imaging at 1550 nm is a key driver for significant advancements in the next-generation laser detection technology. This cutting-edge approach plays a vital role…
A Hopf's Lemma for Higher Order Differential Inequalities and Its Applications
Yifei Pan, Mei Wang, Yu Yan
We establish a sequential Hopf's Lemma for higher order differential inequalities in one variable and give some applications of this result.
SearchAttack: Red-Teaming LLMs against Knowledge-to-Action Threats under Online Web Search
Yu Yan, Sheng Sun, Mingfeng Li +6
Recently, people have suffered from LLM hallucination and have become increasingly aware of the reliability gap of LLMs in open and knowledge-intensive tasks. As a result, they hav…
GloSS over Toxicity: Understanding and Mitigating Toxicity in LLMs via Global Toxic Subspace
Zenghao Duan, Zhiyi Yin, Zhichao Shi +6
This paper investigates the underlying mechanisms of toxicity generation in Large Language Models (LLMs) and proposes an effective detoxification approach. Prior work typically con…
Index Selection for NoSQL Database with Deep Reinforcement Learning
Shun Yao, Hongzhi Wang, Yu Yan
We propose a new approach of NoSQL database index selection. For different workloads, we select different indexes and their different parameters to optimize the database performanc…
Lattice thermal conductivity of 16 elemental metals from molecular dynamics simulations with a unified neuroevolution potential
Shuo Cao, Ao Wang, Zheyong Fan +4
Metals play a crucial role in heat management in electronic devices, such as integrated circuits, making it vital to understand heat transport in elementary metals and alloys. In t…
Projecting Out the Malice: A Global Subspace Approach to LLM Detoxification
Zenghao Duan, Zhiyi Yin, Zhichao Shi +8
Large language models (LLMs) exhibit exceptional performance but pose inherent risks of generating toxic content, restricting their safe deployment. While traditional methods (e.g.…
CONCERTO: Complex Query Execution Mechanism-Aware Learned Cost Estimation
Kaixin Zhang, Hongzhi Wang, Kunkai Gu +4
With the growing demand for massive data analysis, many DBMSs have adopted complex underlying query execution mechanisms, including vectorized operators, parallel execution, and dy…
Out-of-Plane Polarization from Spin Reflection Induces Field-Free Spin-Orbit Torque Switching in Structures with Canted NiO Interfacial Moments
Zhe Zhang, Zhuoyi Li, Yuzhe Chen +9
Realizing deterministic current-induced spin-orbit torque (SOT) magnetization switching, especially in systems exhibiting perpendicular magnetic anisotropy (PMA), typically require…
Decision-Level Hijacking: Injecting Cognitive Bias into Large Language Models via Bit-Flip Attacks
Yu Yan, Jiahao Chen, Siqi Lu +6
Large Language Models (LLMs) have been widely applied in high-stakes decision-making scenarios such as corporate strategy, and users are increasingly relying on their outputs. Howe…
Construction of Twice Differentiable Functions with Continuous Laplacian and Bounded Hessian
Yifei Pan, Yu Yan
We construct examples of twice differentiable functions in with continuous Laplacian and bounded Hessian. The same construction is also applicable to higher order di…
DistJoin: A Decoupled Join Cardinality Estimator based on Adaptive Neural Predicate Modulation
Kaixin Zhang, Hongzhi Wang, Ziqi Li +4
Research on learned cardinality estimation has made significant progress in recent years. However, existing methods still face distinct challenges that hinder their practical deplo…
Uniform Estimates for the Constant Mean Curvature Solutions of the Vacuum Einstein Constraint Equations on Compact Manifolds
Yu Yan
We give some uniform estimates for constant mean curvature solutions of the conformal vacuum Einstein constraint equations on compact manifolds. Existence of those solutions was gi…
KnobCF: Uncertainty-aware Knob Tuning
Yu Yan, Junfang Huang, Hongzhi Wang +3
The knob tuning aims to optimize database performance by searching for the most effective knob configuration under a certain workload. Existing works suffer two significant problem…
Uniqueness Theorems for Ordinary Differential Equations with Hölder Continuity
Yifei Pan, Mei Wang, Yu Yan
We study ordinary differential equations of the type with initial conditions and where ,…
Unified-MAS: Universally Generating Domain-Specific Nodes for Empowering Automatic Multi-Agent Systems
Hehai Lin, Yu Yan, Zixuan Wang +6
Automatic Multi-Agent Systems (MAS) generation has emerged as a promising paradigm for solving complex reasoning tasks. However, existing frameworks are fundamentally bottlenecked…
S-DIGing: A Stochastic Gradient Tracking Algorithm for Distributed Optimization
Huaqing Li, Lifeng Zheng, Zheng Wang +3
In this paper, we study convex optimization problems where agents of a network cooperatively minimize the global objective function which consists of multiple local objective funct…
Antiferromagnetic Ordering Enhanced Magnetic Damping in Mn2Au/CoFeB Bilayers
Donghang Xie, Haozhe Wang, Zhe Zhang +12
Antiferromagnets (AFMs) hold significant potential for spintronic devices owing to their insensitivity to external magnetic fields and the absence of stray fields. Beyond these inh…
Jailbreak-as-a-Service++: Unveiling Distributed AI-Driven Malicious Information Campaigns Powered by LLM Crowdsourcing
Yu Yan, Sheng Sun, Mingfeng Li +6
To prevent the misuse of Large Language Models (LLMs) for malicious purposes, numerous efforts have been made to develop the safety alignment mechanisms of LLMs. However, as multip…
BANG: Bridging Autoregressive and Non-autoregressive Generation with Large Scale Pretraining
Weizhen Qi, Yeyun Gong, Jian Jiao +9
In this paper, we propose BANG, a new pretraining model to Bridge the gap between Autoregressive (AR) and Non-autoregressive (NAR) Generation. AR and NAR generation can be uniforml…
EL-Attention: Memory Efficient Lossless Attention for Generation
Yu Yan, Jiusheng Chen, Weizhen Qi +4
Transformer model with multi-head attention requires caching intermediate results for efficient inference in generation tasks. However, cache brings new memory-related costs and pr…
Examples of Twice Differentiable Functions in with Continuous Laplacian and Unbounded Hessian
Yifei Pan, Yu Yan
We construct examples of twice differentiable functions in with continuous Laplacian and unbounded Hessian. The same construction is also applicable to higher order…
IWEK: An Interpretable What-If Estimator for Database Knobs
Yu Yan, Hongzhi Wang, Jian Geng +5
The knobs of modern database management systems have significant impact on the performance of the systems. With the development of cloud databases, an estimation service for knobs…
Red-teaming the Multimodal Reasoning: Jailbreaking Vision-Language Models via Cross-modal Entanglement Attacks
Yu Yan, Sheng Sun, Shengjia Cheng +3
Vision-Language Models (VLMs) with multimodal reasoning capabilities are high-value attack targets, given their potential for handling complex multimodal harmful tasks. Mainstream…
Electrically Tunable Wafer-Sized Three-Dimensional Topological Insulator Thin Films Grown by Magnetron Sputtering
Qixun Guo, Yu Wu, Longxiang Xu +18
Three-dimensional (3D) topological insulators (TIs) are candidate materials for various electronic and spintronic devices due to their strong spin-orbit coupling and unique surface…
Collaborative Stance Detection via Small-Large Language Model Consistency Verification
Yu Yan, Sheng Sun, Zixiang Tang +2
Stance detection on social media aims to identify attitudes expressed in tweets towards specific targets. Current studies prioritize Large Language Models (LLMs) over Small Languag…
Effect of Notch Structure on Magnetic Domain Movement in Planar Nanowires
Hua Ling, Junlin Wang, Xianyang Lu +8
We present the direct observation of magnetic domain motion in permalloy nanowires with notches using a wide-field Kerr microscopy technique. The domain wall motion can be modulate…
Xmodel-LM Technical Report
Yichuan Wang, Yang Liu, Yu Yan +3
We introduce Xmodel-LM, a compact and efficient 1.1B language model pre-trained on around 2 trillion tokens. Trained on our self-built dataset (Xdata), which balances Chinese and E…
MiniWorld: Democratizing the Training of Video World Models from Scratch
Yian Zhao, Ruochong Zheng, Hongcan Guo +3
Video world models predict future observations conditioned on historical observations and control signals, enabling long-horizon generation through autoregressive state transitions…
A Self-Paced Mixed Distillation Method for Non-Autoregressive Generation
Weizhen Qi, Yeyun Gong, Yelong Shen +6
Non-Autoregressive generation is a sequence generation paradigm, which removes the dependency between target tokens. It could efficiently reduce the text generation latency with pa…
Some Compactness Results Related to Scalar Curvature Deformation
Yu Yan
Motivated by the prescribing scalar curvature problem, we study the equation on locally conformally flat manifolds with $…
Flexible Readout and Unconditional Reset for Superconducting Multi-Qubit Processors with Tunable Purcell Filters
Yong-Xi Xiao, Da'er Feng, Xu-Yang Gu +18
Achieving high-fidelity qubit readout and reset while preserving qubit coherence is essential for quantum error correction and other advanced quantum algorithms. Here, we design an…
ForeSight: A Predictive-Scheduling Deterministic Database
Junfang Huang, Yu Yan, Hongzhi Wang +2
Deterministic databases enable scalable replicated systems by executing transactions in a predetermined order. However, existing designs fail to capture transaction dependencies, l…
Duet: efficient and scalable hybriD neUral rElation undersTanding
Kaixin Zhang, Hongzhi Wang, Yabin Lu +4
Learned cardinality estimation methods have achieved high precision compared to traditional methods. Among learned methods, query-driven approaches have faced the workload drift pr…
AAE: An Active Auto-Estimator for Improving Graph Storage
Yu Yan, Man Yang, Hongzhi Wang +1
Nowadays, graph becomes an increasingly popular model in many real applications. The efficiency of graph storage is crucial for these applications. Generally speaking, the tune tas…
InstruGen: Automatic Instruction Generation for Vision-and-Language Navigation Via Large Multimodal Models
Yu Yan, Rongtao Xu, Jiazhao Zhang +3
Recent research on Vision-and-Language Navigation (VLN) indicates that agents suffer from poor generalization in unseen environments due to the lack of realistic training environme…
Scene Summarization: Clustering Scene Videos into Spatially Diverse Frames
Chao Chen, Mingzhi Zhu, Ankush Pratap Singh +3
Humans are remarkably efficient at forming spatial understanding from just a few visual observations. When browsing real estate or navigating unfamiliar spaces, they intuitively se…
Confusion is the Final Barrier: Rethinking Jailbreak Evaluation and Investigating the Real Misuse Threat of LLMs
Yu Yan, Sheng Sun, Zhe Wang +6
With the development of Large Language Models (LLMs), numerous efforts have revealed their vulnerabilities to jailbreak attacks. Although these studies have driven the progress in…
Tunable Coupling Architectures with Capacitively Connecting Pads for Large-Scale Superconducting Multi-Qubit Processors
Gui-Han Liang, Xiao-Hui Song, Cheng-Lin Deng +20
We have proposed and experimentally verified a tunable inter-qubit coupling scheme for large-scale integration of superconducting qubits. The key feature of the scheme is the inser…
ProphetNet: Predicting Future N-gram for Sequence-to-Sequence Pre-training
Weizhen Qi, Yu Yan, Yeyun Gong +5
This paper presents a new sequence-to-sequence pre-training model called ProphetNet, which introduces a novel self-supervised objective named future n-gram prediction and the propo…
Prethermalization by Random Multipolar Driving on a 78-Qubit Superconducting Processor
Zheng-He Liu, Yu Liu, Gui-Han Liang +43
Time-dependent drives hold the promise of realizing non-equilibrium many-body phenomena that are absent in undriven systems. Yet, drive-induced heating normally destabilizes the sy…
The Scalar Curvature Deformation Equation on Locally Conformally Flat Manifolds
Yu Yan
We study the equation on locally conformally flat compact manifolds . We prove the following: (i…
AI Reasoning for Wireless Communications and Networking: A Survey and Perspectives
Haoxiang Luo, Yu Yan, Yanhui Bian +9
Artificial Intelligence (AI) techniques play a pivotal role in optimizing wireless communication networks. However, traditional deep learning approaches often act as closed boxes,…
SAM: A Stability-Aware Cache Manager for Multi-Tenant Embedded Databases
Haoran Zhang, Decheng Zuo, Yu Yan +2
The co-location of multiple database instances on resource constrained edge nodes creates significant cache contention, where traditional schemes are inefficient and unstable under…
Elementary specific spin and orbital moments of ultrathin CoFeB amorphous films on GaAs(100)
Yu Yan, Cong Lu, Hongqing Tu +12
Nanoscale CoFeB amorphous films have been synthesized on GaAs(100) and studied with X-ray magnetic circular dichroism (XMCD) and transmission electron microscopy (TEM). We have fou…
ProphetNet-Ads: A Looking Ahead Strategy for Generative Retrieval Models in Sponsored Search Engine
Weizhen Qi, Yeyun Gong, Yu Yan +6
In a sponsored search engine, generative retrieval models are recently proposed to mine relevant advertisement keywords for users' input queries. Generative retrieval models genera…
Super-bunching light with giant high-order correlations and extreme multi-photon events
Chengbing Qin, Yuanyuan Li, Yu Yan +14
Non-classical light sources emitting bundles of N-photons with strong correlation represent versatile resources of interdisciplinary importance with applications ranging from funda…
ProphetNet-X: Large-Scale Pre-training Models for English, Chinese, Multi-lingual, Dialog, and Code Generation
Weizhen Qi, Yeyun Gong, Yu Yan +9
Now, the pre-training technique is ubiquitous in natural language processing field. ProphetNet is a pre-training based natural language generation method which shows powerful perfo…
Multi-SQL: An extensible multi-model data query language
Yu Yan, Nan Jiang, Hongzhi Wang +3
Big data management aims to establish data hubs that support data in multiple models and types in an all-around way. Thus, the multi-model database system is a promising architectu…
On the Local Regularity of the Hilbert Transform
Yifei Pan, Jianfei Wang, Yu Yan
In this paper the local regularity of the Hilbert transform is considered, and local smoothness and real analyticity results are obtained.
FastSeq: Make Sequence Generation Faster
Yu Yan, Fei Hu, Jiusheng Chen +7
Transformer-based models have made tremendous impacts in natural language generation. However the inference speed is a bottleneck due to large model size and intensive computing in…
CliBench: A Multifaceted and Multigranular Evaluation of Large Language Models for Clinical Decision Making
Mingyu Derek Ma, Chenchen Ye, Yu Yan +4
The integration of Artificial Intelligence (AI), especially Large Language Models (LLMs), into the clinical diagnosis process offers significant potential to improve the efficiency…
Has the Two-Decade-Old Prophecy Come True? Artificial Bad Intelligence Triggered by Merely a Single-Bit Flip in Large Language Models
Yu Yan, Siqi Lu, Yang Gao +4
Recently, Bit-Flip Attack (BFA) has garnered widespread attention for its ability to compromise software system integrity remotely through hardware fault injection. With the widesp…
CAST: Collapse-Aware multi-Scale Topology Fusion for Multimodal Coreset Selection
Boran Zhao, Hetian Liu, Zhenxian Hu +3
The training of large multimodal models fundamentally relies on massive image-text datasets, which inevitably incur prohibitive computational overhead. Dataset selection offers a p…
PosIR: Position-Aware Heterogeneous Information Retrieval Benchmark
Ziyang Zeng, Dun Zhang, Yu Yan +4
In real-world documents, the information relevant to a user query may reside anywhere from the beginning to the end. This makes position bias -- a systematic tendency of retrieval…
RikiNet: Reading Wikipedia Pages for Natural Question Answering
Dayiheng Liu, Yeyun Gong, Jie Fu +5
Reading long documents to answer open-domain questions remains challenging in natural language understanding. In this paper, we introduce a new model, called RikiNet, which reads W…
from Benign import Toxic: Jailbreaking the Language Model via Adversarial Metaphors
Yu Yan, Sheng Sun, Zenghao Duan +5
Current studies have exposed the risk of Large Language Models (LLMs) generating harmful content by jailbreak attacks. However, they overlook that the direct generation of harmful…
Na'vi or Knave: Jailbreaking Language Models via Metaphorical Avatars
Yu Yan, Sheng Sun, Junqi Tong +2
Metaphor serves as an implicit approach to convey information, while enabling the generalized comprehension of complex subjects. However, metaphor can potentially be exploited to b…
GLGE: A New General Language Generation Evaluation Benchmark
Dayiheng Liu, Yu Yan, Yeyun Gong +15
Multi-task benchmarks such as GLUE and SuperGLUE have driven great progress of pretraining and transfer learning in Natural Language Processing (NLP). These benchmarks mostly focus…
Platform for Representation and Integration of multimodal Molecular Embeddings
Erika Yilin Zheng, Yu Yan, Baradwaj Simha Sankar +8
Existing machine learning methods for molecular (e.g., gene) embeddings are restricted to specific tasks or data modalities, limiting their effectiveness within narrow domains. As…
Decoding RobKiNet: Insights into Efficient Training of Robotic Kinematics Informed Neural Network
Yanlong Peng, Zhigang Wang, Ziwen He +4
In robots task and motion planning (TAMP), it is crucial to sample within the robot's configuration space to meet task-level global constraints and enhance the efficiency of subseq…
Multimode Purcell Filter for Superconducting-Qubit Reset and Readout with Intrinsic Purcell Protection
Xu-Yang Gu, Da'er Feng, Zhen-Yu Peng +17
Efficient qubit reset and leakage reduction are essential for scalable superconducting quantum computing, particularly in the context of quantum error correction. However, such ope…
EMIT: Micro-Invasive Database Configuration Tuning
Jian Geng, Hongzhi Wang, Yu Yan
The process of database knob tuning has always been a challenging task. Recently, database knob tuning methods has emerged as a promising solution to mitigate these issues. However…
Cognitive Dual-Process Planning for Autonomous Driving with Structured Scene Knowledge and Verifiable Reasoning-Action Consistency
Zhongyao Yang, Haoyu Li, Yu Yan +3
High-level planning for autonomous driving is a knowledge-intensive engineering decision task that requires accurate scene understanding, timely inference, and internally consisten…
Diverse, Controllable, and Keyphrase-Aware: A Corpus and Method for News Multi-Headline Generation
Dayiheng Liu, Yeyun Gong, Jie Fu +6
News headline generation aims to produce a short sentence to attract readers to read the news. One news article often contains multiple keyphrases that are of interest to different…