Publications (298)
FairGU: Fairness-aware Graph Unlearning in Social Networks
Renqiang Luo, Yongshuai Yang, Huafei Huang +6
Graph unlearning has emerged as a critical mechanism for supporting sustainable and privacy-preserving social networks, enabling models to remove the influence of deleted nodes and…
The threshold of semiconductor nanolasers
Marco Saldutti, Yi Yu, Jesper Mørk
Nanolasers based on emerging dielectric cavities with deep sub-wavelength confinement of light offer a large light-matter coupling rate and a near-unity spontaneous emission factor…
Sparsity-Aware Robust Normalized Subband Adaptive Filtering algorithms based on Alternating Optimization
Yi Yu, Zongxin Huang, Hongsen He +2
This paper proposes a unified sparsity-aware robust normalized subband adaptive filtering (SA-RNSAF) algorithm for identification of sparse systems under impulsive noise. The propo…
DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models
DeepSeek-AI, Aixin Liu, Aoxue Mei +260
We introduce DeepSeek-V3.2, a model that harmonizes high computational efficiency with superior reasoning and agent performance. The key technical breakthroughs of DeepSeek-V3.2 ar…
Deep Learning of Human Perception in Audio Event Classification
Yi Yu, Samuel Beuret, Donghuo Zeng +1
In this paper, we introduce our recent studies on human perception in audio event classification by different deep learning models. In particular, the pre-trained model VGGish is u…
Ionization-Induced Electrostatic Hose Instability in Electron-Beam-Sustained Plasmas
Jia-Hong Chen, Yi Yu, Jian Chen +1
We report the discovery of a previously unrecognized electrostatic hose instability in electron-beam-sustained plasmas, driven by the coupling between the electron beam centroid an…
CRNNTL: convolutional recurrent neural network and transfer learning for QSAR modelling
Yaqin Li, Yongjin Xu, Yi Yu
In this study, we propose the convolutional recurrent neural network and transfer learning (CRNNTL) for QSAR modelling. The method was inspired by the applications of polyphonic so…
Demonstration of a self-pulsing photonic crystal Fano laser
Yi Yu, Weiqi Xue, Elizaveta Semenova +2
Semiconductor lasers in use today rely on mirrors based on the reflection at a cleaved facet or Bragg reflection from a periodic stack of layers. Here, we demonstrate an ultra-smal…
Theory of Linewidth-Narrowing in Fano Lasers
Yi Yu, Aref Rasoulzadeh Zali, Jesper Mørk
We present a general theory for the coherence of Fano lasers based on a bound state in the continuum. We find that such lasers enable orders of magnitude reduction of the quantum-l…
TEAR: Temporal-aware Automated Red-teaming for Text-to-Video Models
Jiaming He, Guanyu Hou, Hongwei Li +6
Text-to-Video (T2V) models are capable of synthesizing high-quality, temporally coherent dynamic video content, but the diverse generation also inherently introduces critical safet…
Single-Image Shadow Removal Using Deep Learning: A Comprehensive Survey
Laniqng Guo, Chong Wang, Yufei Wang +5
Shadow removal aims at restoring the image content within shadow regions, pursuing a uniform distribution of illumination that is consistent between shadow and non-shadow regions.…
HingeNet: A Harmonic-Aware Fine-Tuning Approach for Beat Tracking
Ganghui Ru, Jieying Wang, Jiahao Zhao +5
Fine-tuning pre-trained foundation models has made significant progress in music information retrieval. However, applying these models to beat tracking tasks remains unexplored as…
Longitudinal double spin asymmetry of -tagged jet, , , and in polarized collisions at at STAR
Yi Yu
Understanding the origin of the proton spin is one of the most fundamental and challenging questions in QCD. Much progress has been made since the first surprising result by the EM…
UniMark: Artificial Intelligence Generated Content Identification Toolkit
Meilin Li, Ji He, Yi Yu +5
The rapid proliferation of Artificial Intelligence Generated Content has precipitated a crisis of trust and urgent regulatory demands. However, existing identification tools suffer…
EMF-Aware MU-MIMO Beamforming in RIS-Aided Cellular Networks
Yi Yu, Rita Ibrahim, Dinh-Thuy Phan-Huy
Reconfigurable Intelligent Surfaces (RISs) are one of the key emerging 6th Generation (6G) technologies that are expected to improve the link budgets between transmitters and recei…
A Survey of Recent Advances and Challenges in Deep Audio-Visual Correlation Learning
Luis Vilaca, Yi Yu, Paula Vinan
Audio-visual correlation learning aims to capture and understand natural phenomena between audio and visual data. The rapid growth of Deep Learning propelled the development of pro…
Generalized non-stationary bandits
Anne Gael Manegueu, Alexandra Carpentier, Yi Yu
In this paper, we study a non-stationary stochastic bandit problem, which generalizes the switching bandit problem. On top of the switching bandit problem (\textbf{Case a}), we are…
Robust Andrew's sine estimate adaptive filtering
Lu Lu, Yi Yu, Zongsheng Zheng +2
The Andrew's sine function is a robust estimator, which has been used in outlier rejection and robust statistics. However, the performance of such estimator does not receive attent…
Unsupervised Generative Adversarial Alignment Representation for Sheet music, Audio and Lyrics
Donghuo Zeng, Yi Yu, Keizo Oyama
Sheet music, audio, and lyrics are three main modalities during writing a song. In this paper, we propose an unsupervised generative adversarial alignment representation (UGAAR) mo…
Learning from Dense Events: Towards Fast Spiking Neural Networks Training via Event Dataset Distillation
Shuhan Ye, Yi Yu, Qixin Zhang +4
Event cameras sense brightness changes and output binary asynchronous event streams, attracting increasing attention. Their bio-inspired dynamics align well with spiking neural net…
MusicTM-Dataset for Joint Representation Learning among Sheet Music, Lyrics, and Musical Audio
Donghuo Zeng, Yi Yu, Keizo Oyama
This work present a music dataset named MusicTM-Dataset, which is utilized in improving the representation learning ability of different types of cross-modal retrieval (CMR). Littl…
Rate Optimality and Phase Transition for User-Level Local Differential Privacy
Alexander Kent, Thomas B. Berrett, Yi Yu
Most of the literature on differential privacy considers the item-level case where each user has a single observation, but a growing field of interest is that of user-level privacy…
Benchmarking Vision-Language-Action Models on SO-101: Failure and Recovery Analysis
Yi Yu, Xinchuan Qiu
Vision-Language-Action (VLA) models have demonstrated strong generalization in robotic manipulation, yet existing evaluations are primarily conducted in simulation or on expensive…
Building Intelligence Identification System via Large Language Model Watermarking: A Survey and Beyond
Xuhong Wang, Haoyu Jiang, Yi Yu +7
Large Language Models (LLMs) are increasingly integrated into diverse industries, posing substantial security risks due to unauthorized replication and misuse. To mitigate these co…
MemVerse: Multimodal Memory for Lifelong Learning Agents
Junming Liu, Yifei Sun, Weihua Cheng +11
Despite rapid progress in large-scale language and vision models, AI agents still suffer from a fundamental limitation: they cannot remember. Without reliable memory, agents catast…
Online Learning for Autoregressive Multilayer Stochastic Block Models under Stationarity and Non-Stationarity
Fan Wang, Haotian Xu, Yi Yu
Dynamic multilayer networks arise in many applications where multiple types of relations among a common set of nodes evolve over time. Existing approaches often assume temporal ind…
X-Boundary: Establishing Exact Safety Boundary to Shield LLMs from Multi-Turn Jailbreaks without Compromising Usability
Xiaoya Lu, Dongrui Liu, Yi Yu +2
Despite the rapid development of safety alignment techniques for LLMs, defending against multi-turn jailbreaks is still a challenging task. In this paper, we conduct a comprehensiv…
SoccerNet 2022 Challenges Results
Silvio Giancola, Anthony Cioppa, Adrien Deliège +91
The SoccerNet 2022 challenges were the second annual video understanding challenges organized by the SoccerNet team. In 2022, the challenges were composed of 6 vision-based tasks:…
Widely Used and Fast De Novo Drug Design by a Protein Sequence-Based Reinforcement Learning Model
Yaqin Li, Lingli Li, Yongjin Xu +1
De novo molecular design has facilitated the exploration of large chemical space to accelerate drug discovery. Structure-based de novo method can overcome the data scarcity of acti…
End-to-end Named Entity Recognition from English Speech
Hemant Yadav, Sreyan Ghosh, Yi Yu +1
Named entity recognition (NER) from text has been a widely studied problem and usually extracts semantic information from text. Until now, NER from speech is mostly studied in a tw…
Network change point localisation under local differential privacy
Mengchu Li, Thomas B. Berrett, Yi Yu
Network data are ubiquitous in our daily life, containing rich but often sensitive information. In this paper, we expand the current static analysis of privatised networks to a dyn…
Leaning Compact and Representative Features for Cross-Modality Person Re-Identification
Guangwei Gao, Hao Shao, Fei Wu +2
This paper pays close attention to the cross-modality visible-infrared person re-identification (VI Re-ID) task, which aims to match pedestrian samples between visible and infrared…
Backdoor Attacks Against Deep Image Compression via Adaptive Frequency Trigger
Yi Yu, Yufei Wang, Wenhan Yang +3
Recent deep-learning-based compression methods have achieved superior performance compared with traditional approaches. However, deep learning models have proven to be vulnerable t…
Deep Knowledge Tracing and Dynamic Student Classification for Knowledge Tracing
Sein Minn, Yi Yu, Michel C. Desmarais +2
In Intelligent Tutoring System (ITS), tracing the student's knowledge state during learning has been studied for several decades in order to provide more supportive learning instru…
DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence
DeepSeek-AI, Anyi Xu, Bangcai Lin +315
We present a preview version of DeepSeek-V4 series, including two strong Mixture-of-Experts (MoE) language models -- DeepSeek-V4-Pro with 1.6T parameters (49B activated) and DeepSe…
CirrusBench: Evaluating LLM-based Agents Beyond Correctness in Real-World Cloud Service Environments
Yi Yu, Guangquan Hu, Chenghuang Shen +15
The increasing agentic capabilities of Large Language Models (LLMs) have enabled their deployment in real-world applications, such as cloud services, where customer-assistant inter…
Conditional LSTM-GAN for Melody Generation from Lyrics
Yi Yu, Abhishek Srivastava, Simon Canales
Melody generation from lyrics has been a challenging research issue in the field of artificial intelligence and music, which enables to learn and discover latent relationship betwe…
Quasi-Monte Carlo finite element approximation of the Navier-Stokes equations with initial data modeled by log-normal random fields
Seungchan Ko, Guanglian Li, Yi Yu
In this paper, we analyze the numerical approximation of the Navier-Stokes problem over a bounded polygonal domain in , where the initial condition is modeled by a lo…
All Vehicles Can Lie: Efficient Adversarial Defense in Fully Untrusted-Vehicle Collaborative Perception via Pseudo-Random Bayesian Inference
Yi Yu, Libing Wu, Zhuangzhuang Zhang +3
Collaborative perception (CP) enables multiple vehicles to augment their individual perception capacities through the exchange of feature-level sensory data. However, this fusion m…
Link prediction for interdisciplinary collaboration via co-authorship network
Haeran Cho, Yi Yu
We analyse the Publication and Research (PURE) data set of University of Bristol collected between and . Using the existing co-authorship network and academic informat…
From Pretrain to Pain: Adversarial Vulnerability of Video Foundation Models Without Task Knowledge
Hui Lu, Yi Yu, Song Xia +5
Large-scale Video Foundation Models (VFMs) has significantly advanced various video-related tasks, either through task-specific models or Multi-modal Large Language Models (MLLMs).…
Locally Differentially Private Two-Sample Testing
Alexander Kent, Thomas B. Berrett, Yi Yu
We consider the problem of two-sample testing under a local differential privacy constraint where a permutation procedure is used to calibrate the tests. We develop testing procedu…
Dynamic Tuning of Single-Photon Emission in Monolayer WSe2 via Localized Strain Engineering
Yi Yu, Junyu Ge, Manlin Luo +9
Two-dimensional (2D) materials have emerged as promising candidates for next-generation integrated single-photon emitters (SPEs). However, significant variability in the emission e…
Robust and Transferable Backdoor Attacks Against Deep Image Compression With Selective Frequency Prior
Yi Yu, Yufei Wang, Wenhan Yang +5
Recent advancements in deep learning-based compression techniques have surpassed traditional methods. However, deep neural networks remain vulnerable to backdoor attacks, where pre…
Preliminary Study on Bit-String Modelling of Opinion Formation in Complex Networks
Yi Yu, Gaoxi Xiao
Opinion formation has been gaining increasing research interests recently, and various models have been proposed. These models, however, have their limitations, among which noticea…
Data on the Move: Traffic-Oriented Data Trading Platform Powered by AI Agent with Common Sense
Yi Yu, Shengyue Yao, Tianchen Zhou +6
In the digital era, data has become a pivotal asset, advancing technologies such as autonomous driving. Despite this, data trading faces challenges like the absence of robust prici…
Conditional Hybrid GAN for Sequence Generation
Yi Yu, Abhishek Srivastava, Rajiv Ratn Shah
Conditional sequence generation aims to instruct the generation procedure by conditioning the model with additional context information, which is a self-supervised learning issue (…
Optimal Cox regression under federated differential privacy: coefficients and cumulative hazards
Elly K. H. Hung, Yi Yu
We study two foundational problems in distributed survival analysis under federated differential privacy (FDP): estimation of the Cox regression coefficients and of the cumulative…
Variational Autoencoder with CCA for Audio-Visual Cross-Modal Retrieval
Jiwei Zhang, Yi Yu, Suhua Tang +2
Cross-modal retrieval is to utilize one modality as a query to retrieve data from another modality, which has become a popular topic in information retrieval, machine learning, and…
Change-point Detection for Sparse and Dense Functional Data in General Dimensions
Carlos Misael Madrid Padilla, Daren Wang, Zifeng Zhao +1
We study the problem of change-point detection and localisation for functional data sequentially observed on a general d-dimensional space, where we allow the functional curves to…
Deep Attention-Based Alignment Network for Melody Generation from Incomplete Lyrics
Gurunath Reddy M, Zhe Zhang, Yi Yu +3
We propose a deep attention-based alignment network, which aims to automatically predict lyrics and melody with given incomplete lyrics as input in a way similar to the music creat…
Federated fairness-aware classification under differential privacy
Gengyu Xue, Yi Yu
Privacy and algorithmic fairness have become two central issues in modern machine learning. Although each has separately emerged as a rapidly growing research area, their joint eff…
Syllable-level lyrics generation from melody exploiting character-level language model
Zhe Zhang, Karol Lasocki, Yi Yu +1
The generation of lyrics tightly connected to accompanying melodies involves establishing a mapping between musical notes and syllables of lyrics. This process requires a deep unde…
Empirical Upscaling of Point-scale Soil Moisture Measurements for Spatial Evaluation of Model Simulations and Satellite Retrievals
Yi Yu, Brendan P. Malone, Luigi J. Renzullo
The evaluation of modelled or satellite-derived soil moisture (SM) estimates is usually dependent on comparisons against in-situ SM measurements. However, the inherent mismatch in…
Refining time-space traffic diagrams: A neighborhood-adaptive linear regression method
Zhihong Yao, Yi Yu, Yunxia Wu +3
The time-space (TS) traffic diagram serves as a crucial tool for characterizing the dynamic evolution of traffic flow, with its resolution directly influencing the effectiveness of…
Suppression of coherence collapse in semiconductor Fano lasers
Thorsten S. Rasmussen, Yi Yu, Jesper Mork
We show that semiconductor Fano lasers strongly suppress dynamic instabilities induced by external optical feedback. A comparison with conventional Fabry-Perot lasers shows orders…
Agentic-MME: What Agentic Capability Really Brings to Multimodal Intelligence?
Qianshan Wei, Yishan Yang, Siyi Wang +12
Multimodal Large Language Models (MLLMs) are evolving from passive observers into active agents, solving problems through Visual Expansion (invoking visual tools) and Knowledge Exp…
Spectral symmetry of Fano resonances in a waveguide coupled to a microcavity
Andreas Dyhl Osterkryger, Jakob Rosenkrantz de Lasson, Mikkel Heuck +3
We investigate the parity of transmission spectra in a photonic crystal (PhC) waveguide with a side-coupled cavity and a partially blocking element. We demonstrate, by means of num…
Chemical transformer compression for accelerating both training and inference of molecular modeling
Yi Yu, Karl Borjesson
Transformer models have been developed in molecular science with excellent performance in applications including quantitative structure-activity relationship (QSAR) and virtual scr…
Federated Transfer Learning with Differential Privacy
Mengchu Li, Ye Tian, Yang Feng +1
Federated learning has emerged as a powerful framework for analysing distributed data, yet two challenges remain pivotal: heterogeneity across sites and privacy of local data. In t…
Dive into the Agent Matrix: A Realistic Evaluation of Self-Replication Risk in LLM Agents
Boxuan Zhang, Yi Yu, Jiaxuan Guo +1
The prevalent deployment of Large Language Model agents such as OpenClaw unlocks potential in real-world applications, while amplifying safety concerns. Among these concerns, the s…
Change point detection and inference in multivariable nonparametric models under mixing conditions
Carlos Misael Madrid Padilla, Haotian Xu, Daren Wang +2
This paper studies multivariate nonparametric change point localization and inference problems. The data consists of a multivariate time series with potentially short range depende…
Differentially private hypothesis testing in survival analysis
Elly K. H. Hung, Yi Yu
Survival analysis is widely used in applications involving sensitive individual-level data, yet differentially private hypothesis testing for right-censored data remains largely un…
Backdoor Attacks against No-Reference Image Quality Assessment Models via a Scalable Trigger
Yi Yu, Song Xia, Xun Lin +4
No-Reference Image Quality Assessment (NR-IQA), responsible for assessing the quality of a single input image without using any reference, plays a critical role in evaluating and o…
Category-Based Deep CCA for Fine-Grained Venue Discovery from Multimodal Data
Yi Yu, Suhua Tang, Kiyoharu Aizawa +1
In this work, travel destination and business location are taken as venues. Discovering a venue by a photo is very important for context-aware applications. Unfortunately, few effo…
Atlas is Your Perfect Context: One-Shot Customization for Generalizable Foundational Medical Image Segmentation
Ziyu Zhang, Yi Yu, Simeng Zhu +4
Accurate segmentation of anatomical structures in medical images is essential for diagnosis and treatment planning. While recent interactive segmentation foundation models enhance…
Wholly-WOOD: Wholly Leveraging Diversified-quality Labels for Weakly-supervised Oriented Object Detection
Yi Yu, Xue Yang, Yansheng Li +3
Accurately estimating the orientation of visual objects with compact rotated bounding boxes (RBoxes) has become a prominent demand, which challenges existing object detection parad…
Emotionally Enhanced Talking Face Generation
Sahil Goyal, Shagun Uppal, Sarthak Bhagat +3
Several works have developed end-to-end pipelines for generating lip-synced talking faces with various real-world applications, such as teaching and language translation in videos.…
Superfluidity and pairing phenomena in ultracold atomic Fermi gases in one-dimensional optical lattices, Part I: Balanced case
Jibiao Wang, Leifeng Zhang, Yi Yu +2
The superfluidity and pairing phenomena in ultracold atomic Fermi gases have been of great interest in recent years, with multiple tunable parameters. Here we study the BCS-BEC cro…
Nanobeam Laser Cavities with High Quality-factor and Near-Unity Outcoupling Efficiency
Mathias Marchal, Meng Xiong, Evangelos Dimopoulos +3
Cavities with high quality (Q) factor and small mode-volume are crucial to realize high-performance nanolasers suitable for optical interconnects. In this work, we propose a novel…
Benchmarking Adversarial Robustness of Image Shadow Removal with Shadow-adaptive Attacks
Chong Wang, Yi Yu, Lanqing Guo +1
Shadow removal is a task aimed at erasing regional shadows present in images and reinstating visually pleasing natural scenes with consistent illumination. While recent deep learni…
DEEPCHORUS: A Hybrid Model of Multi-scale Convolution and Self-attention for Chorus Detection
Qiqi He, Xiaoheng Sun, Yi Yu +1
Chorus detection is a challenging problem in musical signal processing as the chorus often repeats more than once in popular songs, usually with rich instruments and complex rhythm…
Ultrafast coherent dynamics of a photonic crystal all-optical switch
Pierre Colman, Per Lunnemann, Yi Yu +1
We present pump-probe measurements of an all-optical photonic crystal switch based on a nanocavity, resolving fast coherent temporal dynamics. The measurements demonstrate the impo…
Adaptive Nonoverlapping Preconditioners for the Helmholtz Equation
Yi Yu, Marcus Sarkis, Guanglian Li +1
The Helmholtz equation poses significant computational challenges due to its oscillatory solutions, particularly for large wavenumbers. Inspired by the Schur complement system for…
Superfluidity and pairing phenomena in ultracold atomic Fermi gases in one-dimensional optical lattices, Part II: Effects of population imbalance
Jibiao Wang, Lin Sun, Qiang Zhang +4
In this paper, we study the effect of population imbalance and its interplay with pairing strength and lattice effect in atomic Fermi gases in a one-dimensional optical lattice. We…
Lightweight Adaptation for LLM-based Technical Service Agent: Latent Logic Augmentation and Robust Noise Reduction
Yi Yu, Junzhuo Ma, Chenghuang Shen +15
Adapting Large Language Models in complex technical service domains is constrained by the absence of explicit cognitive chains in human demonstrations and the inherent ambiguity ar…
Multilayer random dot product graphs: Estimation and online change point detection
Fan Wang, Wanshan Li, Oscar Hernan Madrid Padilla +2
We study the multilayer random dot product graph (MRDPG) model, an extension of the random dot product graph to multilayer networks. To estimate the edge probabilities, we deploy a…
Multinoulli Extension: A Lossless Continuous Relaxation for Partition-Constrained Subset Selection
Qixin Zhang, Wei Huang, Yan Sun +3
Identifying the most representative subset for a close-to-submodular objective while satisfying the predefined partition constraint is a fundamental task with numerous applications…
Functional Linear Regression with Mixed Predictors
Daren Wang, Zifeng Zhao, Yi Yu +1
We study a functional linear regression model that deals with functional responses and allows for both functional covariates and high-dimensional vector covariates. The proposed mo…
Optimal nonparametric change point detection and localization
Oscar Hernan Madrid Padilla, Yi Yu, Daren Wang +1
We study change point detection and localization for univariate data in fully nonparametric settings in which, at each time point, we acquire an i.i.d. sample from an unknown distr…
Frontier AI Risk Management Framework in Practice: A Risk Analysis Technical Report v1.5
Dongrui Liu, Yi Yu, Jie Zhang +18
To understand and identify the unprecedented risks posed by rapidly advancing artificial intelligence (AI) models, Frontier AI Risk Management Framework in Practice presents a comp…
Scalable Motion Style Transfer with Constrained Diffusion Generation
Wenjie Yin, Yi Yu, Hang Yin +2
Current training of motion style transfer systems relies on consistency losses across style domains to preserve contents, hindering its scalable application to a large number of do…
Lightweight Bimodal Network for Single-Image Super-Resolution via Symmetric CNN and Recursive Transformer
Guangwei Gao, Zhengxue Wang, Juncheng Li +3
Single-image super-resolution (SISR) has achieved significant breakthroughs with the development of deep learning. However, these methods are difficult to be applied in real-world…
Feature Distillation Interaction Weighting Network for Lightweight Image Super-Resolution
Guangwei Gao, Wenjie Li, Juncheng Li +3
Convolutional neural networks based single-image super-resolution (SISR) has made great progress in recent years. However, it is difficult to apply these methods to real-world scen…
Nonreciprocal transmission in a photonic-crystal Fano structure enabled by symmetry breaking
Yi Yu, Yaohui Chen, Hao Hu +3
Nanostructures that feature nonreciprocal light transmission are highly desirable building blocks for realizing photonic integrated circuits. Here, a simple and ultra-compact photo…
Self-Evolving Cognitive Framework via Causal World Modeling for Embodied Scientific Intelligence
Yi Yu, Tetsunari Inamura
Current embodied world models are primarily optimized for predictive objectives, limiting their ability to generalize under distribution shifts and reason systematically about unse…
Optimal network online change point localisation
Yi Yu, Oscar Hernan Madrid Padilla, Daren Wang +1
We study the problem of online network change point detection. In this setting, a collection of independent Bernoulli networks is collected sequentially, and the underlying distrib…
Interpretable Visual Understanding with Cognitive Attention Network
Xuejiao Tang, Wenbin Zhang, Yi Yu +4
While image understanding on recognition-level has achieved remarkable advancements, reliable visual scene understanding requires comprehensive image understanding on recognition-l…
Recent Advances and Challenges in Deep Audio-Visual Correlation Learning
LuÃs Vilaça, Yi Yu, Paula Viana
Audio-visual correlation learning aims to capture essential correspondences and understand natural phenomena between audio and video. With the rapid growth of deep learning, an inc…
SafeWork-R1: Coevolving Safety and Intelligence under the AI-45 Law
Shanghai AI Lab, :, Yicheng Bao +115
We introduce SafeWork-R1, a cutting-edge multimodal reasoning model that demonstrates the coevolution of capabilities and safety. It is developed by our proposed SafeLadder framewo…
Optimal Covariance Change Point Localization in High Dimension
Daren Wang, Yi Yu, Alessandro Rinaldo
We study the problem of change point detection for covariance matrices in high dimensions. We assume that we observe a sequence {X_i}_{i=1,...,n} of independent and centered p-dime…
Theoretical Insights in Model Inversion Robustness and Conditional Entropy Maximization for Collaborative Inference Systems
Song Xia, Yi Yu, Wenhan Yang +5
By locally encoding raw data into intermediate features, collaborative inference enables end users to leverage powerful deep learning models without exposure of sensitive raw data…
Fire on Motion: Optimizing Video Pass-bands for Efficient Spiking Action Recognition
Shuhan Ye, Yuanbin Qian, Yi Yu +5
Spiking neural networks (SNNs) have gained traction in vision due to their energy efficiency, bio-plausibility, and inherent temporal processing. Yet, despite this temporal capacit…
Breaking the Modality Wall: Time-step Mixup for Efficient Spiking Knowledge Transfer from Static to Event Domain
Yuqi Xie, Shuhan Ye, Yi Yu +7
The integration of event cameras and spiking neural networks (SNNs) promises energy-efficient visual intelligence, yet scarce event data and the sparsity of DVS outputs hinder effe…
Open-set Anomaly Segmentation in Complex Scenarios
Song Xia, Yi Yu, Henghui Ding +4
Precise segmentation of out-of-distribution (OoD) objects, herein referred to as anomalies, is crucial for the reliable deployment of semantic segmentation models in open-set, safe…
PointOBB: Learning Oriented Object Detection via Single Point Supervision
Junwei Luo, Xue Yang, Yi Yu +3
Single point-supervised object detection is gaining attention due to its cost-effectiveness. However, existing approaches focus on generating horizontal bounding boxes (HBBs) while…
Univariate Mean Change Point Detection: Penalization, CUSUM and Optimality
Daren Wang, Yi Yu, Alessandro Rinaldo
The problem of univariate mean change point detection and localization based on a sequence of independent observations with piecewise constant means has been intensively studie…
Change point localization in dependent dynamic nonparametric random dot product graphs
Oscar Hernan Madrid Padilla, Yi Yu, Carey E. Priebe
In this paper, we study the offline change point localization problem in a sequence of dependent nonparametric random dot product graphs. To be specific, assume that at every time…
From Additive Average Schwarz Methods to Non-overlapping Spectral Additive Schwarz Methods
Yi Yu, Maksymilian Dryja, Marcus Sarkis
In this paper, we design and analyze two new methods based on additive average Schwarz -- AAS method introduced in \cite{MR1943457}. The new methods design for elliptic problems wi…
Self-pulsing dynamics in microscopic lasers with dispersive mirrors
Kristian Seegert, Mikkel Heuck, Yi Yu +1
We show that a passive dispersive reflector integrated into a semiconductor laser can be used to tailor the laser dynamics for the generation of ultrashort pulses as well as stable…