Publications (117)
Radio Map Estimation via Latent Domain Plug-and-Play Denoising
Le Xu, Lei Cheng, Junting Chen +2
Radio map estimation (RME), also known as spectrum cartography, aims to reconstruct the strength of radio interference across different domains (e.g., space and frequency) from spa…
Inexact Alternating Optimization for Phase Retrieval In the Presence of Outliers
Cheng Qian, Xiao Fu, Nicholas D. Sidiropoulos +2
Phase retrieval has been mainly considered in the presence of Gaussian noise. However, the performance of the algorithms proposed under the Gaussian noise model severely degrades w…
Nonlinear Multiview Analysis: Identifiability and Neural Network-assisted Implementation
Qi Lyu, Xiao Fu
Multiview analysis aims at extracting shared latent components from data samples that are acquired in different domains, e.g., image, text, and audio. Classic multiview analysis, e…
Anchor-Free Correlated Topic Modeling: Identifiability and Algorithm
Kejun Huang, Xiao Fu, Nicholas D. Sidiropoulos
In topic modeling, many algorithms that guarantee identifiability of the topics have been developed under the premise that there exist anchor words -- i.e., words that only appear…
SynCamMaster: Synchronizing Multi-Camera Video Generation from Diverse Viewpoints
Jianhong Bai, Menghan Xia, Xintao Wang +6
Recent advancements in video diffusion models have shown exceptional abilities in simulating real-world dynamics and maintaining 3D consistency. This progress inspires us to invest…
Hyperspectral Unmixing Under Endmember Variability: A Variational Inference Framework
Yuening Li, Xiao Fu, Junbin Liu +1
This work proposes a variational inference (VI) framework for hyperspectral unmixing in the presence of endmember variability (HU-EV). An EV-accounted noisy linear mixture model (L…
SciText2Eq: Assessing LLMs for Explainable Equation Generation for Scientific Creativity
Yifan Mo, Xiao Fu, Yue Su +4
This work investigates the ability of large language models (LLMs) to generate mathematical equations from scientific texts. Prior work faces challenges in unstructured grounding,…
AFD-Ledger: Deployment Provisioning for Attention--FFN Disaggregation
Chengyu Qiu, Xiao Fu, Fengcun Li +6
Attention--Feed-Forward Network (FFN) Disaggregation (AFD) is emerging as a promising architecture for serving Mixture-of-Experts (MoE) language models. While existing AFD systems…
On Convergence of Epanechnikov Mean Shift
Kejun Huang, Xiao Fu, Nicholas D. Sidiropoulos
Epanechnikov Mean Shift is a simple yet empirically very effective algorithm for clustering. It localizes the centroids of data clusters via estimating modes of the probability dis…
On Recoverability of Randomly Compressed Tensors with Low CP Rank
Shahana Ibrahim, Xiao Fu, Xingguo Li
Our interest lies in the recoverability properties of compressed tensors under the \textit{canonical polyadic decomposition} (CPD) model. The considered problem is well-motivated i…
LTM: Large-scale Terrain Model for Wildfire-prone Landscapes
Xiao Fu, Yue Hu, Meida Chen +2
Accurate 3D terrain maps are essential for emergency response when assessing wildfire hazards. However, wildfire-prone regions often span vast areas where conventional reconstructi…
Towards Identifiable Unsupervised Domain Translation: A Diversified Distribution Matching Approach
Sagar Shrestha, Xiao Fu
Unsupervised domain translation (UDT) aims to find functions that convert samples from one domain (e.g., sketches) to another domain (e.g., photos) without changing the high-level…
Crowdsourcing via Pairwise Co-occurrences: Identifiability and Algorithms
Shahana Ibrahim, Xiao Fu, Nikos Kargas +1
The data deluge comes with high demands for data labeling. Crowdsourcing (or, more generally, ensemble learning) techniques aim to produce accurate labels via integrating noisy, no…
Rethinking Coupled Tensor Analysis for Hyperspectral Super-Resolution: Recoverable Modeling Under Endmember Variability
Meng Ding, Xiao Fu
This work revisits the hyperspectral super-resolution (HSR) problem, i.e., fusing a pair of spatially co-registered hyperspectral (HSI) and multispectral (MSI) images to recover a…
On the Effectiveness of Pinyin-Character Dual-Decoding for End-to-End Mandarin Chinese ASR
Zhao Yang, Dianwen Ng, Xiao Fu +5
End-to-end automatic speech recognition (ASR) has achieved promising results. However, most existing end-to-end ASR methods neglect the use of specific language characteristics. Fo…
Self-Dictionary Sparse Regression for Hyperspectral Unmixing: Greedy Pursuit and Pure Pixel Search are Related
Xiao Fu, Wing-Kin Ma, Tsung-Han Chan +1
This paper considers a recently emerged hyperspectral unmixing formulation based on sparse regression of a self-dictionary multiple measurement vector (SD-MMV) model, wherein the m…
Quantized Radio Map Estimation Using Tensor and Deep Generative Models
Subash Timilsina, Sagar Shrestha, Xiao Fu
Spectrum cartography (SC), also known as radio map estimation (RME), aims at crafting multi-domain (e.g., frequency and space) radio power propagation maps from limited sensor meas…
A Noise-Robust Loss for Unlabeled Entity Problem in Named Entity Recognition
Wentao Kang, Guijun Zhang, Xiao Fu
Named Entity Recognition (NER) is an important task in natural language processing. However, traditional supervised NER requires large-scale annotated datasets. Distantly supervisi…
Structured SUMCOR Multiview Canonical Correlation Analysis for Large-Scale Data
Charilaos I. Kanatsoulis, Xiao Fu, Nicholas D. Sidiropoulos +1
The sum-of-correlations (SUMCOR) formulation of generalized canonical correlation analysis (GCCA) seeks highly correlated low-dimensional representations of different views via max…
Learning to Optimize: Training Deep Neural Networks for Wireless Resource Management
Haoran Sun, Xiangyi Chen, Qingjiang Shi +3
For the past couple of decades, numerical optimization has played a central role in addressing wireless resource management problems such as power control and beamformer design. Ho…
Learning From Hidden Traits: Joint Factor Analysis and Latent Clustering
Bo Yang, Xiao Fu, Nicholas D. Sidiropoulos
Dimensionality reduction techniques play an essential role in data analytics, signal processing and machine learning. Dimensionality reduction is usually performed in a preprocessi…
ReCamMaster: Camera-Controlled Generative Rendering from A Single Video
Jianhong Bai, Menghan Xia, Xiao Fu +8
Camera control has been actively studied in text or image conditioned video generation tasks. However, altering camera trajectories of a given video remains under-explored, despite…
Real-time Geoinformation Systems to Improve the Quality, Scalability, and Cost of Internet of Things for Agri-environment Research
Bryan C. Runck, Bobby Schulz, Jeff Bishop +41
With the increasing emphasis on machine learning and artificial intelligence to drive knowledge discovery in the agricultural sciences, spatial internet of things (IoT) technologie…
Efficient Green Emission from Edge States in Graphene Perforated by Nitrogen Plasma Treatment
N N Kovaleva, D Chvostova, Z PotůÄek +10
Plasma functionalization of graphene is one of the facile ways to tune its doping level without the need for wet chemicals making graphene photoluminescent. Microscopic corrugation…
Tensor Decomposition for Signal Processing and Machine Learning
Nicholas D. Sidiropoulos, Lieven De Lathauwer, Xiao Fu +3
Tensors or {\em multi-way arrays} are functions of three or more indices -- similar to matrices (two-way arrays), which are functions of two indices for (r…
Joint Tensor Factorization and Outlying Slab Suppression with Applications
Xiao Fu, Kejun Huang, Wing-Kin Ma +2
We consider factoring low-rank tensors in the presence of outlying slabs. This problem is important in practice, because data collected in many real-world applications, such as spe…
Deep Learning From Crowdsourced Labels: Coupled Cross-entropy Minimization, Identifiability, and Regularization
Shahana Ibrahim, Tri Nguyen, Xiao Fu
Using noisy crowdsourced labels from multiple annotators, a deep learning-based end-to-end (E2E) system aims to learn the label correction mechanism and the neural classifier simul…
OmniObject3D: Large-Vocabulary 3D Object Dataset for Realistic Perception, Reconstruction and Generation
Tong Wu, Jiarui Zhang, Xiao Fu +9
Recent advances in modeling 3D objects mostly rely on synthetic datasets due to the lack of large-scale realscanned 3D databases. To facilitate the development of 3D perception, re…
Plenoptic Video Generation
Xiao Fu, Shitao Tang, Min Shi +5
Camera-controlled generative video re-rendering methods, such as ReCamMaster, have achieved remarkable progress. However, despite their success in single-view setting, these works…
Cosmos 3: Omnimodal World Models for Physical AI
NVIDIA, :, Aditi +293
We introduce Cosmos 3, a family of omnimodal world models designed to jointly process and generate language, image, video, audio, and action sequences within a unified mixture-of-t…
Learning to Continuously Optimize Wireless Resource in a Dynamic Environment: A Bilevel Optimization Perspective
Haoran Sun, Wenqiang Pu, Xiao Fu +2
There has been a growing interest in developing data-driven, and in particular deep neural network (DNN) based methods for modern communication tasks. For a few popular tasks such…
Link Prediction Under Imperfect Detection: Collaborative Filtering for Ecological Networks
Xiao Fu, Eugene Seo, Justin Clarke +1
Matrix completion based collaborative filtering is considered scalable and effective for online service link prediction (e.g., movie recommendation) but does not meet the challenge…
Robust Volume Minimization-Based Matrix Factorization for Remote Sensing and Document Clustering
Xiao Fu, Kejun Huang, Bo Yang +2
This paper considers \emph{volume minimization} (VolMin)-based structured matrix factorization (SMF). VolMin is a factorization criterion that decomposes a given data matrix into a…
UniGP: Taming Diffusion Transformer for Prior-Preserved Unified Generation and Perception
Qin Guo, Hao Luo, Dongxu Yue +4
Recent advances in diffusion models have shown impressive performance in controllable image generation and dense prediction tasks. However, existing approaches typically treat diff…
Hyperspectral Super-Resolution via Global-Local Low-Rank Matrix Estimation
Ruiyuan Wu, Wing-Kin Ma, Xiao Fu +1
Hyperspectral super-resolution (HSR) is a problem that aims to estimate an image of high spectral and spatial resolutions from a pair of co-registered multispectral (MS) and hypers…
Fast and Structured Block-Term Tensor Decomposition For Hyperspectral Unmixing
Meng Ding, Xiao Fu, Xi-Le Zhao
The block-term tensor decomposition model with multilinear rank- terms (or, the "LL1 tensor decomposition" in short) offers a valuable alternative for hyperspectral un…
Metalenses with polarization-independent adaptive nano-antennas
Jianchao Zhang, Haowen Liang, Yong Long +8
Metalens research has made major advances in recent years. These advances rely on the simple design principle of arranging meta-atoms in regular arrays to create an arbitrary phase…
LiMnS and LiSiS as a pair of all-electrochem-active electrode and solid-state electrolyte with chemical compatibility and low interface resistance
Qifan Yang, Jing Xu, Xiao Fu +6
In solid-state batteries (SSBs), improving the physical contact at the electrode-electrolyte interface is essential for achieving better performance and durability. On the one hand…
Learning Video Generation for Robotic Manipulation with Collaborative Trajectory Control
Xiao Fu, Xintao Wang, Xian Liu +5
Recent advances in video diffusion models shows promise for generating robotic decision-making data, with trajectory conditions further enabling fine-grained control. However, exis…
Timing Channel in IaaS: How to Identify and Investigate
Xiao Fu, Rui Yang, Xiaojiang Du +1
Recently, the IaaS (Infrastructure as a Service) Cloud (e.g., Amazon EC2) has been widely used by many organizations. However, some IaaS security issues create serious threats to i…
Algebraic Channel Estimation Algorithms for FDD Massive MIMO systems
Cheng Qian, Xiao Fu, Nicholas D. Sidiropoulos
We consider downlink (DL) channel estimation for frequency division duplex based massive MIMO systems under the multipath model. Our goal is to provide fast and accurate channel es…
Isolated anions induced high ionic conductivity
Qifan Yang, Jing Xu, Yuqi Wang +3
One of the key materials in solid-state lithium batteries is fast ion conductors. However, the Li+ ion transport in inorganic crystals involves complex factors, making it a mystery…
Memory-Efficient Convex Optimization for Self-Dictionary Separable Nonnegative Matrix Factorization: A Frank-Wolfe Approach
Tri Nguyen, Xiao Fu, Ruiyuan Wu
Nonnegative matrix factorization (NMF) often relies on the separability condition for tractable algorithm design. Separability-based NMF is mainly handled by two types of approache…
StatEcoNet: Statistical Ecology Neural Networks for Species Distribution Modeling
Eugene Seo, Rebecca A. Hutchinson, Xiao Fu +4
This paper focuses on a core task in computational sustainability and statistical ecology: species distribution modeling (SDM). In SDM, the occurrence pattern of a species on a lan…
Stochastic Block-ADMM for Training Deep Networks
Saeed Khorram, Xiao Fu, Mohamad H. Danesh +2
In this paper, we propose Stochastic Block-ADMM as an approach to train deep neural networks in batch and online settings. Our method works by splitting neural networks into an arb…
Solute strengthening and softening from screw dislocation in BCC tantalum: A first-principles study
Jiajun Feng, Kangzhi Zhou, Xiaowei Zhou +3
Improving the high-temperature performance and low-temperature plasticity of tantalum (Ta) alloys is a significant scientific challenge. We employed first-principles calculations t…
Tensor-Based Channel Estimation for Dual-Polarized Massive MIMO Systems
Cheng Qian, Xiao Fu, Nicholas D. Sidiropoulos +1
The 3GPP suggests to combine dual polarized (DP) antenna arrays with the double directional (DD) channel model for downlink channel estimation. This combination strikes a good bala…
Amplitude Retrieval for Channel Estimation of MIMO Systems with One-Bit ADCs
Cheng Qian, Xiao Fu, Nicholas D. Sidiropoulos
This letter revisits the channel estimation problem for MIMO systems with one-bit analog-to-digital converters (ADCs) through a novel algorithm--Amplitude Retrieval (AR). Unlike th…
Limited Feedback Channel Estimation in Massive MIMO with Non-uniform Directional Dictionaries
Panos N. Alevizos, Xiao Fu, Nicholas D. Sidiropoulos +2
Channel state information (CSI) at the base station (BS) is crucial to achieve beamforming and multiplexing gains in multiple-input multiple-output (MIMO) systems. State-of-the-art…
Semiblind Hyperspectral Unmixing in the Presence of Spectral Library Mismatches
Xiao Fu, Wing-Kin Ma, José Bioucas-Dias +1
The dictionary-aided sparse regression (SR) approach has recently emerged as a promising alternative to hyperspectral unmixing (HU) in remote sensing. By using an available spectra…
LongCat-Flash Technical Report
Meituan LongCat Team, Bayan, Bei Li +179
We introduce LongCat-Flash, a 560-billion-parameter Mixture-of-Experts (MoE) language model designed for both computational efficiency and advanced agentic capabilities. Stemming f…
Under-Counted Tensor Completion with Neural Incorporation of Attributes
Shahana Ibrahim, Xiao Fu, Rebecca Hutchinson +1
Systematic under-counting effects are observed in data collected across many disciplines, e.g., epidemiology and ecology. Under-counted tensor completion (UC-TC) is well-motivated…
Multiuser Video Streaming Rate Adaptation: A Physical Layer Resource-Aware Deep Reinforcement Learning Approach
Kexin Tang, Nuowen Kan, Junni Zou +3
We consider a multi-user video streaming service optimization problem over a time-varying and mutually interfering multi-cell wireless network. The key research challenge is to app…
On Finite-Sample Identifiability of Contrastive Learning-Based Nonlinear Independent Component Analysis
Qi Lyu, Xiao Fu
Nonlinear independent component analysis (nICA) aims at recovering statistically independent latent components that are mixed by unknown nonlinear functions. Central to nICA is the…
On Local Linear Convergence of Projected Gradient Descent for Unit-Modulus Least Squares
Trung Vu, Raviv Raich, Xiao Fu
The unit-modulus least squares (UMLS) problem has a wide spectrum of applications in signal processing, e.g., phase-only beamforming, phase retrieval, radar code design, and sensor…
Scalable and Flexible Multiview MAX-VAR Canonical Correlation Analysis
Xiao Fu, Kejun Huang, Mingyi Hong +2
Generalized canonical correlation analysis (GCCA) aims at finding latent low-dimensional common structure from multiple views (feature vectors in different domains) of the same ent…
Domain Transfer Becomes Identifiable via a Single Alignment
Sagar Shrestha, Subash Timilsina, Hoang-Son Nguyen +1
Domain transfer (DT) maps source to target distributions and supports tasks such as unsupervised image-to-image translation, single-cell analysis, and cross-platform medical imagin…
Content-Style Identification via Differential Independence
Subash Timilsina, Hoang-Son Nguyen, Sagar Shrestha +1
Generative analysis often models multi-domain observations as nonlinear mixtures of domain-invariant content variables and domain-specific style variables. Identifying both factors…
Tensor-Based Parameter Estimation of Double Directional Massive MIMO Channel with Dual-Polarized Antennas
Cheng Qian, Xiao Fu, Nicholas D. Sidiropoulos +1
The 3GPP suggests to combine dual polarized (DP) antenna arrays with the double directional (DD) channel model for downlink channel estimation. This combination strikes a good bala…
StreamPhy: Streaming Inference of High-Dimensional Physical Dynamics via State Space Models
Panqi Chen, Yifan Sun, Shikai Fang +2
Inferring the evolution of high-dimensional and multi-modal (e.g., spatio-temporal) physical fields from irregular sparse measurements in real time is a fundamental challenge in sc…
A More Efficient Chinese Named Entity Recognition base on BERT and Syntactic Analysis
Xiao Fu, Guijun Zhang
We propose a new Named entity recognition (NER) method to effectively make use of the results of Part-of-speech (POS) tagging, Chinese word segmentation (CWS) and parsing while avo…
Immunometabolic Gatekeeping: Reconciling Peto's & the T-cell Infiltration Prognostic Paradox
Naomi Iris van den Berg, Matouš Elphick, Kevin Mulder +4
Classical models of cancer focus on tumour-intrinsic genetic aberrations and immune dynamics and often overlook how the metabolic environment of healthy tissues shapes tumour devel…
On Identifiability of Nonnegative Matrix Factorization
Xiao Fu, Kejun Huang, Nicholas D. Sidiropoulos
In this letter, we propose a new identification criterion that guarantees the recovery of the low-rank latent factors in the nonnegative matrix factorization (NMF) model, under mil…
Recovering Joint Probability of Discrete Random Variables from Pairwise Marginals
Shahana Ibrahim, Xiao Fu
Learning the joint probability of random variables (RVs) is the cornerstone of statistical signal processing and machine learning. However, direct nonparametric estimation for high…
Crowdsourcing via Annotator Co-occurrence Imputation and Provable Symmetric Nonnegative Matrix Factorization
Shahana Ibrahim, Xiao Fu
Unsupervised learning of the Dawid-Skene (D&S) model from noisy, incomplete and crowdsourced annotations has been a long-standing challenge, and is a critical step towards reliably…
SemanticGen: Video Generation in Semantic Space
Jianhong Bai, Xiaoshi Wu, Xintao Wang +9
State-of-the-art video generative models typically learn the distribution of video latents in the VAE space and map them to pixels using a VAE decoder. While this approach can gene…
Communication-Efficient Federated Linear and Deep Generalized Canonical Correlation Analysis
Sagar Shrestha, Xiao Fu
Classic and deep generalized canonical correlation analysis (GCCA) algorithms seek low-dimensional common representations of data entities from multiple ``views'' (e.g., audio and…
Uncovering migration systems through spatio-temporal tensor co-clustering
Zack W. Almquist, Tri Duc Nguyen, Mikael Sorensen +2
A central problem in the study of human mobility is that of migration systems. Typically, migration systems are defined as a set of relatively stable movements of people between tw…
Tensors, Learning, and 'Kolmogorov Extension' for Finite-alphabet Random Vectors
Nikos Kargas, Nicholas D. Sidiropoulos, Xiao Fu
Estimating the joint probability mass function (PMF) of a set of random variables lies at the heart of statistical learning and signal processing. Without structural assumptions, s…
Hyperspectral Super-Resolution: A Coupled Tensor Factorization Approach
Charilaos I. Kanatsoulis, Xiao Fu, Nicholas D. Sidiropoulos +1
Hyperspectral super-resolution refers to the problem of fusing a hyperspectral image (HSI) and a multispectral image (MSI) to produce a super-resolution image (SRI) that has fine s…
Towards K-means-friendly Spaces: Simultaneous Deep Learning and Clustering
Bo Yang, Xiao Fu, Nicholas D. Sidiropoulos +1
Most learning approaches treat dimensionality reduction (DR) and clustering separately (i.e., sequentially), but recent research has shown that optimizing the two tasks jointly can…
Computing Large-Scale Matrix and Tensor Decomposition with Structured Factors: A Unified Nonconvex Optimization Perspective
Xiao Fu, Nico Vervliet, Lieven De Lathauwer +2
The proposed article aims at offering a comprehensive tutorial for the computational aspects of structured matrix and tensor factorization. Unlike existing tutorials that mainly fo…
Identifiability-Guaranteed Simplex-Structured Post-Nonlinear Mixture Learning via Autoencoder
Qi Lyu, Xiao Fu
This work focuses on the problem of unraveling nonlinearly mixed latent components in an unsupervised manner. The latent components are assumed to reside in the probability simplex…
DuoGen: Towards General Purpose Interleaved Multimodal Generation
Min Shi, Xiaohui Zeng, Jiannan Huang +13
Interleaved multimodal generation enables capabilities beyond unimodal generation models, such as step-by-step instructional guides, visual planning, and generating visual drafts f…
GeoWizard: Unleashing the Diffusion Priors for 3D Geometry Estimation from a Single Image
Xiao Fu, Wei Yin, Mu Hu +6
We introduce GeoWizard, a new generative foundation model designed for estimating geometric attributes, e.g., depth and normals, from single images. While significant research has…
World Simulation with Video Foundation Models for Physical AI
NVIDIA, :, Arslan Ali +87
We introduce [Cosmos-Predict2.5], the latest generation of the Cosmos World Foundation Models for Physical AI. Built on a flow-based architecture, [Cosmos-Predict2.5] unifies Text2…
Hyperspectral Super-resolution: A Coupled Nonnegative Block-term Tensor Decomposition Approach
Guoyong Zhang, Xiao Fu, Kejun Huang +1
Hyperspectral super-resolution (HSR) aims at fusing a hyperspectral image (HSI) and a multispectral image (MSI) to produce a super-resolution image (SRI). Recently, a coupled tenso…
See4D: Pose-Free 4D Generation via Auto-Regressive Video Inpainting
Dongyue Lu, Ao Liang, Tianxin Huang +8
Immersive applications call for synthesizing spatiotemporal 4D content from casual videos without costly 3D supervision. Existing video-to-4D methods typically rely on manually ann…
Panoptic NeRF: 3D-to-2D Label Transfer for Panoptic Urban Scene Segmentation
Xiao Fu, Shangzhan Zhang, Tianrun Chen +5
Large-scale training data with high-quality annotations is critical for training semantic and instance segmentation models. Unfortunately, pixel-wise annotation is labor-intensive…
Spectrum Cartography via Coupled Block-Term Tensor Decomposition
Guoyong Zhang, Xiao Fu, Jun Wang +2
Spectrum cartography aims at estimating power propagation patterns over a geographical region across multiple frequency bands (i.e., a radio map)---from limited samples taken spars…
High-Entropy Solid Electrolytes Discovery: A Dual-Stage Machine Learning Framework Bridging Atomic Configurations and Ionic Transport Properties
Xiao Fu, Jing Xu, Qifan Yang +6
The rapid development of computational materials science powered by machine learning (ML) is gradually leading to solutions to several previously intractable scientific problems. O…
Learning Hidden Markov Models from Pairwise Co-occurrences with Application to Topic Modeling
Kejun Huang, Xiao Fu, Nicholas D. Sidiropoulos
We present a new algorithm for identifying the transition and emission probabilities of a hidden Markov model (HMM) from the emitted data. Expectation-maximization becomes computat…
High-Throughput NEB for Li-Ion Conductor Discovery via Fine-Tuned CHGNet Potential
Jingchen Lian, Xiao Fu, Xuhe Gong +2
Solid-state electrolytes are essential in the development of all-solid-state batteries. While density functional theory (DFT)-based nudged elastic band (NEB) and ab initio molecula…
Deep Clustering with Incomplete Noisy Pairwise Annotations: A Geometric Regularization Approach
Tri Nguyen, Shahana Ibrahim, Xiao Fu
The recent integration of deep learning and pairwise similarity annotation-based constrained clustering -- i.e., (DCC) -- has proven effectiv…
Nonnegative Matrix Factorization for Signal and Data Analytics: Identifiability, Algorithms, and Applications
Xiao Fu, Kejun Huang, Nicholas D. Sidiropoulos +1
Nonnegative matrix factorization (NMF) has become a workhorse for signal and data analytics, triggered by its model parsimony and interpretability. Perhaps a bit surprisingly, the…
Interplay: Training Independent Simulators for Reference-Free Conversational Recommendation
Jerome Ramos, Feng Xia, Xi Wang +4
Training conversational recommender systems (CRS) requires extensive dialogue data, which is challenging to collect at scale. To address this, researchers have used simulated user-…
Unregistered Spectral Image Fusion: Unmixing, Adversarial Learning, and Recoverability
Jiahui Song, Sagar Shrestha, Xiao Fu
This paper addresses the fusion of a pair of spatially unregistered hyperspectral image (HSI) and multispectral image (MSI) covering roughly overlapping regions. HSIs offer high sp…
Data-Driven Learning-Based Optimization for Distribution System State Estimation
Ahmed S. Zamzam, Xiao Fu, Nicholas D. Sidiropoulos
Distribution system state estimation (DSSE) is a core task for monitoring and control of distribution networks. Widely used algorithms such as Gauss-Netwon perform poorly with the…
Learning From Crowdsourced Noisy Labels: A Signal Processing Perspective
Shahana Ibrahim, Panagiotis A. Traganitis, Xiao Fu +1
One of the primary catalysts fueling advances in artificial intelligence (AI) and machine learning (ML) is the availability of massive, curated datasets. A commonly used technique…
Domain-Factored Untrained Deep Prior for Spectrum Cartography
Subash Timilsina, Sagar Shrestha, Lei Cheng +1
Spectrum cartography (SC) focuses on estimating the radio power propagation map of multiple emitters across space and frequency using limited sensor measurements. Recent advances i…
Block-Randomized Stochastic Proximal Gradient for Low-Rank Tensor Factorization
Xiao Fu, Shahana Ibrahim, Hoi-To Wai +2
This work considers the problem of computing the canonical polyadic decomposition (CPD) of large tensors. Prior works mostly leverage data sparsity to handle this problem, which is…
Learning Nonlinear Mixtures: Identifiability and Algorithm
Bo Yang, Xiao Fu, Nicholas D. Sidiropoulos +1
Linear mixture models have proven very useful in a plethora of applications, e.g., topic modeling, clustering, and source separation. As a critical aspect of the linear mixture mod…
PanopticNeRF-360: Panoramic 3D-to-2D Label Transfer in Urban Scenes
Xiao Fu, Shangzhan Zhang, Tianrun Chen +4
Training perception systems for self-driving cars requires substantial 2D annotations that are labor-intensive to manual label. While existing datasets provide rich annotations on…
Provable Subspace Identification Under Post-Nonlinear Mixtures
Qi Lyu, Xiao Fu
Unsupervised mixture learning (UML) aims at identifying linearly or nonlinearly mixed latent components in a blind manner. UML is known to be challenging: Even learning linear mixt…
HSD: A hierarchical singing annotation dataset
Xiao Fu, Xin Yuan, Jinglu Hu
Commonly music has an obvious hierarchical structure, especially for the singing parts which usually act as the main melody in pop songs. However, most of the current singing annot…
Identifiable Shared Component Analysis of Unpaired Multimodal Mixtures
Subash Timilsina, Sagar Shrestha, Xiao Fu
A core task in multi-modal learning is to integrate information from multiple feature spaces (e.g., text and audio), offering modality-invariant essential representations of data.…
Understanding Latent Correlation-Based Multiview Learning and Self-Supervision: An Identifiability Perspective
Qi Lyu, Xiao Fu, Weiran Wang +1
Multiple views of data, both naturally acquired (e.g., image and audio) and artificially produced (e.g., via adding different noise to data samples), have proven useful in enhancin…
3DTrajMaster: Mastering 3D Trajectory for Multi-Entity Motion in Video Generation
Xiao Fu, Xian Liu, Xintao Wang +7
This paper aims to manipulate multi-entity 3D motions in video generation. Previous methods on controllable video generation primarily leverage 2D control signals to manipulate obj…
Diversified Flow Matching with Translation Identifiability
Sagar Shrestha, Xiao Fu
Diversified distribution matching (DDM) finds a unified translation function mapping a diverse collection of conditional source distributions to their target counterparts. DDM was…
Deep Spectrum Cartography: Completing Radio Map Tensors Using Learned Neural Models
Sagar Shrestha, Xiao Fu, Mingyi Hong
The spectrum cartography (SC) technique constructs multi-domain (e.g., frequency, space, and time) radio frequency (RF) maps from limited measurements, which can be viewed as an il…