Publications (276)
In-Context Probing for Membership Inference in Fine-Tuned Language Models
Zhexi Lu, Hongliang Chi, Nathalie Baracaldo +3
Membership inference attacks (MIAs) pose a critical privacy threat to fine-tuned large language models (LLMs), especially when models are adapted to domain-specific tasks using sen…
High-level semantic feature matters few-shot unsupervised domain adaptation
Lei Yu, Wanqi Yang, Shengqi Huang +2
In few-shot unsupervised domain adaptation (FS-UDA), most existing methods followed the few-shot learning (FSL) methods to leverage the low-level local features (learned from conve…
QQQ: Quality Quattuor-Bit Quantization for Large Language Models
Ying Zhang, Peng Zhang, Mincong Huang +7
Quantization is a proven effective method for compressing large language models. Although popular techniques like W8A8 and W4A16 effectively maintain model performance, they often…
ULSD: Unified Line Segment Detection across Pinhole, Fisheye, and Spherical Cameras
Hao Li, Huai Yu, Wen Yang +2
Line segment detection is essential for high-level tasks in computer vision and robotics. Currently, most stateof-the-art (SOTA) methods are dedicated to detecting straight line se…
Effective Diffusion Transformer Architecture for Image Super-Resolution
Kun Cheng, Lei Yu, Zhijun Tu +7
Recent advances indicate that diffusion models hold great promise in image super-resolution. While the latest methods are primarily based on latent diffusion models with convolutio…
Beyond the Central Limit Theorem: Universal and Non-universal Simulations of Random Variables by General Mappings
Lei Yu
Motivated by the Central Limit Theorem, in this paper, we study both universal and non-universal simulations of random variables with an arbitrary target distribution by ge…
Privacy-Preserving Redaction of Diagnosis Data through Source Code Analysis
Lixi Zhou, Lei Yu, Jia Zou +1
Protecting sensitive information in diagnostic data such as logs, is a critical concern in the industrial software diagnosis and debugging process. While there are many tools devel…
A Natural Bias for Language Generation Models
Clara Meister, Wojciech Stokowiec, Tiago Pimentel +3
After just a few hundred training updates, a standard probabilistic model for language generation has likely not yet learnt many semantic or syntactic rules of natural language, ma…
Odd induced subgraphs in graphs with treewidth at most two
Xinmin Hou, Lei Yu, Jiaao Li +1
A long-standing conjecture asserts that there exists a constant such that every graph of order without isolated vertices contains an induced subgraph of order at least $c…
Weak solutions to an initial-boundary value problem for a continuum equation of motion of grain boundaries
Peicheng Zhu, Lei Yu, Yang Xiang
We investigate an initial-(periodic-)boundary value problem for a continuum equation, which is a model for motion of grain boundaries based on the underlying microscopic mechanisms…
Modelling Electrical Car Diffusion Based on Agents
Lei Yu, Tao Zhang, Peer-Olaf Siebers +1
Replacing traditional fossil fuel vehicles with innovative zero-emission vehicles for the transport in ci ties is one of the major tactics to achieve the UK government 2020 target…
Inferring symmetry in natural language
Chelsea Tanchip, Lei Yu, Aotao Xu +1
We present a methodological framework for inferring symmetry of verb predicates in natural language. Empirical work on predicate symmetry has taken two main approaches. The feature…
Designing optimal subsidy schemes and recycling plans for sustainable treatment of construction and demolition waste
Lei Yu, Qian Ge, Ke Han +2
More than 10 billion tons of construction and demolition waste (CW) are generated globally each year, exerting a significant impact on the environment. In the CW recycling process,…
Fresh2comm: Information Freshness Optimized Collaborative Perception
Ziyong Wu, Zhilin Peng, Lei Yu
Collaborative perception is a cornerstone of intelligent connected vehicles, enabling them to share and integrate sensory data to enhance situational awareness. However, measuring…
Better Document-Level Machine Translation with Bayes' Rule
Lei Yu, Laurent Sartran, Wojciech Stokowiec +4
We show that Bayes' rule provides an effective mechanism for creating document translation models that can be learned from only parallel sentences and monolingual documents---a com…
Structure of entropy solutions to general scalar conservation laws in one space dimension
Stefano Bianchini, Lei Yu
In this paper, we show that the entropy solution of a scalar conservation law is - continuous outside a -rectifiable set , - up to a negligible set, for each…
LaVIDE: Language-Prompted Satellite Change Detection via Map-Image Alignment
Shuguo Jiang, Fang Xu, Chuandong Liu +6
Remote sensing change detection based on a map reference and an up-to-date image boosts timely observation of the Earth's surface when earlier images are lacking for comparison. Ho…
MAAC: Novel Alert Correlation Method To Detect Multi-step Attack
Xiaoyu Wang, Xiaorui Gong, Lei Yu +1
With the continuous improvement of attack methods, there are more and more distributed, complex, targeted attacks in which the attackers use combined attack methods to achieve the…
Hallucination reduction with CASAL: Contrastive Activation Steering For Amortized Learning
Wannan, Yang, Xinchi Qiu +6
Large Language Models (LLMs) exhibit impressive capabilities but often hallucinate, confidently providing incorrect answers instead of admitting ignorance. Prior work has shown tha…
Tackling Sequence to Sequence Mapping Problems with Neural Networks
Lei Yu
In Natural Language Processing (NLP), it is important to detect the relationship between two sequences or to generate a sequence of tokens given another observed sequence. We call…
Frequency Estimation of Multiple Sinusoids with Sub-Nyquist Sampling Sequences
Shan Huang, Hong Sun, Haijian Zhang +1
In some applications of frequency estimation, the frequencies of multiple sinusoids are required to be estimated from sub-Nyquist sampling sequences. In this paper, we propose a no…
PMGS: Reconstruction of Projectile Motion Across Large Spatiotemporal Spans via 3D Gaussian Splatting
Yijun Xu, Jingrui Zhang, Yuhan Chen +3
Modeling complex rigid motion across large spatiotemporal spans remains an unresolved challenge in dynamic reconstruction. Existing paradigms are mainly confined to short-term, sma…
The most distant HI galaxies discovered by the 500 m dish FAST
Hongwei Xi, Bo Peng, Lister Staveley-Smith +20
Neutral hydrogen (HI) is the primary component of the cool interstellar medium (ISM) and is the reservoir of fuel for star formation. Owing to the sensitivity of existing radio tel…
Frequency Estimation of Multiple Sinusoids with Three Sub-Nyquist Channels
Shan Huang, Haijian Zhang, Hong Sun +2
Frequency estimation of multiple sinusoids is significant in both theory and application. In some application scenarios, only sub-Nyquist samples are available to estimate the freq…
Biomedical image analysis competitions: The state of current participation practice
Matthias Eisenmann, Annika Reinke, Vivienn Weru +352
The number of international benchmarking competitions is steadily increasing in various fields of machine learning (ML) research and practice. So far, however, little is known abou…
First implementation of full-workflow automation in radiotherapy: the All-in-One solution on rectal cancer
Lei Yu, Jun Zhao, Fan Xia +7
The aim of this work is to describe the technical characteristics of an AI-powered radiotherapy workflow that enables full-process automation (All-in-One), evaluate its performance…
Robust Time-Frequency Reconstruction by Learning Structured Sparsity
Lei Jiang, Haijian Zhang, Lei Yu
Time-frequency distributions (TFDs) play a vital role in providing descriptive analysis of non-stationary signals involved in realistic scenarios. It is well known that low time-fr…
Learning Parallax for Stereo Event-based Motion Deblurring
Mingyuan Lin, Chi Zhang, Chu He +1
Due to the extremely low latency, events have been recently exploited to supplement lost information for motion deblurring. Existing approaches largely rely on the perfect pixel-wi…
On the -Stability and Related Conjectures
Lei Yu
Given a convex function and the mean , which Boolean function maximizes the -stability $\mathbb{E}[Φ(T_Ïf(\math…
An algorithm of frequency estimation for multi-channel coprime sampling
Shan Huang, Haijian Zhang, Hong Sun +1
In some applications of frequency estimation, it is challenging to sample at as high as the Nyquist rate due to hardware limitations. An effective solution is to use multiple sub-N…
GT-CausIn: a novel causal-based insight for traffic prediction
Ting Gao, Rodrigo Kappes Marques, Lei Yu
Traffic forecasting is an important application of spatiotemporal series prediction. Among different methods, graph neural networks have achieved so far the most promising results,…
Learning to Extract Building Footprints from Off-Nadir Aerial Images
Jinwang Wang, Lingxuan Meng, Weijia Li +3
Extracting building footprints from aerial images is essential for precise urban mapping with photogrammetric computer vision technologies. Existing approaches mainly assume that t…
BashCoder-R1: Towards Robust and Explainable Bash Code Generation with Robustness-Aware Group Relative Policy Optimization
Lei Yu, Peng Wang, Jia Xu +7
Bash scripts are the cornerstone of system administration and DevOps automation, where code quality directly impacts system stability and security. In automated Bash script generat…
Mechanistic Understanding and Mitigation of Language Model Non-Factual Hallucinations
Lei Yu, Meng Cao, Jackie Chi Kit Cheung +1
State-of-the-art language models (LMs) sometimes generate non-factual hallucinations that misalign with world knowledge. To explore the mechanistic causes of these hallucinations,…
Distortion Bounds for Source Broadcast Problems
Lei Yu, Houqiang Li, Weiping Li
This paper investigates the joint source-channel coding problem of sending a memoryless source over a memoryless broadcast channel. An inner bound and several outer bounds on the a…
Comments on "Approximate Characterizations for the Gaussian Source Broadcast Distortion Region"
Lei Yu, Houqiang Li, Weiping Li
Recently, Tian et al. [1] considered joint source-channel coding of transmitting a Gaussian source over -user Gaussian broadcast channel, and derived an outer bound on the admis…
Asymptotics for Strassen's Optimal Transport Problem
Lei Yu
In this paper, we consider Strassen's version of optimal transport (OT) problem, which concerns minimizing the excess-cost probability (i.e., the probability that the cost is large…
NTIRE 2025 Challenge on Event-Based Image Deblurring: Methods and Results
Lei Sun, Andrea Alfarano, Peiqi Duan +85
This paper presents an overview of NTIRE 2025 the First Challenge on Event-Based Image Deblurring, detailing the proposed methodologies and corresponding results. The primary goal…
Secrecy Communication with Security Rate Measure
Lei Yu, Houqiang Li, Weiping Li
We introduce a new measure on secrecy, which is established based on rate-distortion theory. It is named \emph{security rate}, which is the minimum (infimum) of the additional rate…
Dimension-Free Bounds for the Union-Closed Sets Conjecture
Lei Yu
The union-closed sets conjecture states that in any nonempty union-closed family of subsets of a finite set, there exists an element contained in at least a proportio…
MTFM: A Scalable and Alignment-free Foundation Model for Industrial Recommendation in Meituan
Xin Song, Zhilin Guan, Ruidong Han +12
Industrial recommendation systems typically involve multiple scenarios, yet existing cross-domain (CDR) and multi-scenario (MSR) methods often require prohibitive resources and str…
Diverse Pretrained Context Encodings Improve Document Translation
Domenic Donato, Lei Yu, Chris Dyer
We propose a new architecture for adapting a sentence-level sequence-to-sequence transformer by incorporating multiple pretrained document context signals and assess the impact on…
"Seeing'' Electric Network Frequency from Events
Lexuan Xu, Guang Hua, Haijian Zhang +2
Most of the artificial lights fluctuate in response to the grid's alternating current and exhibit subtle variations in terms of both intensity and spectrum, providing the potential…
Evaluating the Dynamics of Membership Privacy in Deep Learning
Yuetian Chen, Zhiqi Wang, Nathalie Baracaldo +2
Membership inference attacks (MIAs) pose a critical threat to the privacy of training data in deep learning. Despite significant progress in attack methodologies, our understanding…
DeepCRCEval: Revisiting the Evaluation of Code Review Comment Generation
Junyi Lu, Xiaojia Li, Zihan Hua +5
Code review is a vital but demanding aspect of software development, generating significant interest in automating review comments. Traditional evaluation methods for these comment…
Intrinsic Test of Unlearning Using Parametric Knowledge Traces
Yihuai Hong, Lei Yu, Haiqin Yang +2
The task of "unlearning" certain concepts in large language models (LLMs) has attracted immense attention recently, due to its importance in mitigating undesirable model behaviours…
Line Spectral Estimation Based on Compressed Sensing with Deterministic Sub-Nyquist Sampling
Shan Huang, Hong Sun, Haijian Zhang +1
As an alternative to the traditional sampling theory, compressed sensing allows acquiring much smaller amount of data, still estimating the spectra of frequency-sparse signals accu…
Calibrating Verbal Uncertainty as a Linear Feature to Reduce Hallucinations
Ziwei Ji, Lei Yu, Yeskendir Koishekenov +6
LLMs often adopt an assertive language style also when making false claims. Such ``overconfident hallucinations'' mislead users and erode trust. Achieving the ability to express in…
Maximum Entropy Diverse Exploration: Disentangling Maximum Entropy Reinforcement Learning
Andrew Cohen, Lei Yu, Xingye Qiao +1
Two hitherto disconnected threads of research, diverse exploration (DE) and maximum entropy RL have addressed a wide range of problems facing reinforcement learning algorithms via…
Intra-Ensemble in Neural Networks
Yuan Gao, Zixiang Cai, Lei Yu
Improving model performance is always the key problem in machine learning including deep learning. However, stand-alone neural networks always suffer from marginal effect when stac…
Automatic Streaming Segmentation of Stereo Video Using Bilateral Space
Wenjing Ke, Yuanjie Zhu, Lei Yu
In this paper, we take advantage of binocular camera and propose an unsupervised algorithm based on semi-supervised segmentation algorithm and extracting foreground part efficientl…
Online Segment to Segment Neural Transduction
Lei Yu, Jan Buys, Phil Blunsom
We introduce an online neural sequence to sequence model that learns to alternate between encoding and decoding segments of the input as it is read. By independently tracking the e…
SenseCrypt: Sensitivity-guided Selective Homomorphic Encryption for Joint Federated Learning in Cross-Device Scenarios
Borui Li, Li Yan, Junhao Han +2
Homomorphic Encryption (HE) prevails in securing Federated Learning (FL), but suffers from high overhead and adaptation cost. Selective HE methods, which partially encrypt model pa…
Diverse Exploration via Conjugate Policies for Policy Gradient Methods
Andrew Cohen, Xingye Qiao, Lei Yu +2
We address the challenge of effective exploration while maintaining good performance in policy gradient methods. As a solution, we propose diverse exploration (DE) via conjugate po…
Efficient and Accurate Quantized Image Super-Resolution on Mobile NPUs, Mobile AI & AIM 2022 challenge: Report
Andrey Ignatov, Radu Timofte, Maurizio Denna +93
Image super-resolution is a common task on mobile and IoT devices, where one often needs to upscale and enhance low-resolution images and video frames. While numerous solutions hav…
Super-Resolving Blurry Images with Events
Chi Zhang, Mingyuan Lin, Xiang Zhang +2
Super-resolution from motion-blurred images poses a significant challenge due to the combined effects of motion blur and low spatial resolution. To address this challenge, this pap…
An LLM Maturity Model for Reliable and Transparent Text-to-Query
Lei Yu, Abir Ray
Recognizing the imperative to address the reliability and transparency issues of Large Language Models (LLM), this work proposes an LLM maturity model tailored for text-to-query ap…
Rényi Common Information for Doubly Symmetric Binary Sources
Lei Yu
In this note, we provide analytic expressions for the Rényi common information of orders in for the doubly symmetric binary source (DSBS). Until now, analytic express…
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…
Asymptotic Coupling and Its Applications in Information Theory
Lei Yu, Vincent Y. F. Tan
A coupling of two distributions and is a joint distribution with marginal distributions equal to and . Given marginals and a…
Effects of Differential Privacy and Data Skewness on Membership Inference Vulnerability
Stacey Truex, Ling Liu, Mehmet Emre Gursoy +2
Membership inference attacks seek to infer the membership of individual training instances of a privately trained model. This paper presents a membership privacy analysis and evalu…
Using construction waste hauling trucks' GPS data to classify earthwork-related locations: A Chengdu case study
Lei Yu, Ke Han
Earthwork-related locations (ERLs), such as construction sites, earth dumping ground, and concrete mixing stations, are major sources of urban dust pollution (particulate matters).…
Source-Channel Secrecy for Shannon Cipher System
Lei Yu, Houqiang Li, Weiping Li
Recently, a secrecy measure based on list-reconstruction has been proposed [2], in which a wiretapper is allowed to produce a list of reconstruction sequences and the…
Local Optimality of Dictator Functions with Applications to Courtade--Kumar and Li--Médard Conjectures
Lei Yu
Given a convex function , the -stability of a Boolean function is defined as , where is a random vect…
HomoMatcher: Dense Feature Matching Results with Semi-Dense Efficiency by Homography Estimation
Xiaolong Wang, Lei Yu, Yingying Zhang +6
Feature matching between image pairs is a fundamental problem in computer vision that drives many applications, such as SLAM. Recently, semi-dense matching approaches have achieved…
CasP: Improving Semi-Dense Feature Matching Pipeline Leveraging Cascaded Correspondence Priors for Guidance
Peiqi Chen, Lei Yu, Yi Wan +9
Semi-dense feature matching methods have shown strong performance in challenging scenarios. However, the existing pipeline relies on a global search across the entire feature map t…
Linear change and minutes variability of solar wind velocity revealed by FAST
Li-Jia Liu, Bo Peng, Lei Yu +6
Observation of Interplanetary Scintillation (IPS) provides an important and effective way to study the solar wind and the space weather. A series of IPS observations were conducted…
Rate-Distortion-Perception Theory for the Quadratic Wasserstein Space
Xiqiang Qu, Jun Chen, Lei Yu +1
We establish a single-letter characterization of the fundamental distortion-rate-perception tradeoff with limited common randomness under the squared error distortion measure and t…
Dynamic Coarse-to-Fine Learning for Oriented Tiny Object Detection
Chang Xu, Jian Ding, Jinwang Wang +4
Detecting arbitrarily oriented tiny objects poses intense challenges to existing detectors, especially for label assignment. Despite the exploration of adaptive label assignment in…
Dynamic Bandwidth Allocation for Hybrid Event-RGB Transmission
Pujing Yang, Guangyi Zhang, Yunlong Cai +2
Event cameras asynchronously capture pixel-level intensity changes with extremely low latency. They are increasingly used in conjunction with RGB cameras for a wide range of vision…
QPanda3: A High-Performance Software-Hardware Collaborative Framework for Large-Scale Quantum-Classical Computing Integration
Tianrui Zou, Yuan Fang, Jing Wang +8
In emerging quantum-classical integration applications, the classical time cost-especially from compilation and protocol-level communication often exceeds the execution time of qua…
Predicting emergent linguistic compositions through time: Syntactic frame extension via multimodal chaining
Lei Yu, Yang Xu
Natural language relies on a finite lexicon to express an unbounded set of emerging ideas. One result of this tension is the formation of new compositions, such that existing lingu…
Generalizing Event-Based Motion Deblurring in Real-World Scenarios
Xiang Zhang, Lei Yu, Wen Yang +2
Event-based motion deblurring has shown promising results by exploiting low-latency events. However, current approaches are limited in their practical usage, as they assume the sam…
A Class of Deterministic Sensing Matrices and Their Application in Harmonic Detection
Shan Huang, Hong Sun, Lei Yu +1
In this paper, a class of deterministic sensing matrices are constructed by selecting rows from Fourier matrices. These matrices have better performance in sparse recovery than ran…
On Conditional Correlations
Lei Yu
The Pearson correlation, correlation ratio, and maximal correlation have been well-studied in the literature. In this paper, we study the conditional versions of these quantities.…
SBV-like regularity for general hyperbolic systems of conservation laws
Stefano Bianchini, Lei Yu
We prove the SBV regularity of the characteristic speed of the scalar hyperbolic conservation law and SBV-like regularity of the eigenvalue functions of the Jacobian matrix of flux…
Sheaf Discovery with Joint Computation Graph Pruning and Flexible Granularity
Lei Yu, Jingcheng Niu, Zining Zhu +2
In this paper, we introduce DiscoGP, a novel framework for extracting self-contained modular units, or sheaves, within neural language models (LMs). Sheaves extend the concept of f…
SAEL: Leveraging Large Language Models with Adaptive Mixture-of-Experts for Smart Contract Vulnerability Detection
Lei Yu, Shiqi Cheng, Zhirong Huang +6
With the increasing security issues in blockchain, smart contract vulnerability detection has become a research focus. Existing vulnerability detection methods have their limitatio…
On Non-Interactive Simulation of Binary Random Variables
Lei Yu, Vincent Y. F. Tan
We leverage proof techniques Fourier analysis and an existing result in coding theory to derive new bounds for the problem of non-interactive simulation of binary random variables.…
Detecting Line Segments in Motion-blurred Images with Events
Huai Yu, Hao Li, Wen Yang +2
Making line segment detectors more reliable under motion blurs is one of the most important challenges for practical applications, such as visual SLAM and 3D reconstruction. Existi…
Capturing document context inside sentence-level neural machine translation models with self-training
Elman Mansimov, Gábor Melis, Lei Yu
Neural machine translation (NMT) has arguably achieved human level parity when trained and evaluated at the sentence-level. Document-level neural machine translation has received l…
Detoxification for LLM: From Dataset Itself
Wei Shao, Yihang Wang, Gaoyu Zhu +4
Existing detoxification methods for large language models mainly focus on post-training stage or inference time, while few tackle the source of toxicity, namely, the dataset itself…
Fast Nearest Convolution for Real-Time Efficient Image Super-Resolution
Ziwei Luo, Youwei Li, Lei Yu +4
Deep learning-based single image super-resolution (SISR) approaches have drawn much attention and achieved remarkable success on modern advanced GPUs. However, most state-of-the-ar…
Deep learning scheme for recovery of broadband microwave photonic receiving systems in transceivers without expert knowledge and system priors
Shaofu Xu, Rui Wang, Jianping Chen +2
In regular microwave photonic (MWP) receiving systems, broadband signals are processed in the analog domain before they are transformed to the digital domain for further processing…
Dynamically encircling an exceptional point through phase-tracked closed-loop control
Sen Zhang, Yangyu Huang, Lei Yu +7
The intricate complex eigenvalues of non-Hermitian Hamiltonians manifest as Riemann surfaces in control parameter spaces. At the exceptional points (EPs), the degeneracy of both ei…
LLaMA-Reviewer: Advancing Code Review Automation with Large Language Models through Parameter-Efficient Fine-Tuning
Junyi Lu, Lei Yu, Xiaojia Li +2
The automation of code review activities, a long-standing pursuit in software engineering, has been primarily addressed by numerous domain-specific pre-trained models. Despite thei…
A clinically relevant online patient QA solution with daily CT scans and EPID-based in vivo dosimetry: A feasible study on rectal cancer
Liyuan Chen, Zhiyuan Zhang, Lei Yu +8
Adaptive radiation therapy (ART) could protect organs at risk (OARs) while maintain high dose coverage to targets. However, there still lack efficient online patient QA methods. We…
Sentence Encoding with Tree-constrained Relation Networks
Lei Yu, Cyprien de Masson d'Autume, Chris Dyer +3
The meaning of a sentence is a function of the relations that hold between its words. We instantiate this relational view of semantics in a series of neural models based on variant…
ViewBridge:Revisiting Cross-View Localization from Image Matching
Panwang Xia, Qiong Wu, Lei Yu +11
Cross-view localization aims to estimate the 3-DoF pose of a ground-view image by aligning it with aerial or satellite imagery. Existing methods typically address this task through…
MTS-Net: Dual-Enhanced Positional Multi-Head Self-Attention for 3D CT Diagnosis of May-Thurner Syndrome
Yixin Huang, Yiqi Jin, Ke Tao +6
May-Thurner Syndrome (MTS) is a vascular condition that affects over 20\% of the population and significantly increases the risk of iliofemoral deep venous thrombosis. Accurate and…
An Unsupervised Learning Method for Radio Interferometry Deconvolution
Lei Yu, Bin Liu, Cheng-Jin Jin +3
Given the incomplete sampling of spatial frequencies by radio interferometers, achieving precise restoration of astrophysical information remains challenging. To address this ill-p…
Exponential Strong Converse for Content Identification with Lossy Recovery
Lin Zhou, Vincent Y. F. Tan, Lei Yu +1
We revisit the high-dimensional content identification with lossy recovery problem (Tuncel and Gündüz, 2014) and establish an exponential strong converse theorem. As a corollary…
Learning Monocular Depth from Focus with Event Focal Stack
Chenxu Jiang, Mingyuan Lin, Chi Zhang +2
Depth from Focus estimates depth by determining the moment of maximum focus from multiple shots at different focal distances, i.e. the Focal Stack. However, the limited sampling ra…
Motion Robust High-Speed Light-Weighted Object Detection With Event Camera
Bingde Liu, Chang Xu, Wen Yang +2
In this work, we propose a motion robust and high-speed detection pipeline which better leverages the event data. First, we design an event stream representation called temporal ac…
IsarStep: a Benchmark for High-level Mathematical Reasoning
Wenda Li, Lei Yu, Yuhuai Wu +1
A well-defined benchmark is essential for measuring and accelerating research progress of machine learning models. In this paper, we present a benchmark for high-level mathematical…
Exponential Stabilization of Moving Shockwave in ARZ Traffic Model via Boundary Control: Explicit Gains and Arbitrary Decay Rate
Mina Cao, Mamadou Diagne, Peipei Shang +1
This paper develops boundary feedback controls to stabilize traffic congestion toward a predefined shock equilibrium in the Aw-Rascle-Zhang (ARZ) traffic flow model. We transform t…
Noun2Verb: Probabilistic frame semantics for word class conversion
Lei Yu, Yang Xu
Humans can flexibly extend word usages across different grammatical classes, a phenomenon known as word class conversion. Noun-to-verb conversion, or denominal verb (e.g., to Googl…
Learning a Simple and Effective Model for Multi-turn Response Generation with Auxiliary Tasks
Yufan Zhao, Can Xu, Wei Wu +1
We study multi-turn response generation for open-domain dialogues. The existing state-of-the-art addresses the problem with deep neural architectures. While these models improved r…
Towards Demystifying Membership Inference Attacks
Stacey Truex, Ling Liu, Mehmet Emre Gursoy +2
Membership inference attacks seek to infer membership of individual training instances of a model to which an adversary has black-box access through a machine learning-as-a-service…
Recovering Continuous Scene Dynamics from A Single Blurry Image with Events
Zhangyi Cheng, Xiang Zhang, Lei Yu +3
This paper aims at demystifying a single motion-blurred image with events and revealing temporally continuous scene dynamics encrypted behind motion blurs. To achieve this end, an…