Publications (287)
The Librating Companions in HD 37124, HD 12661, HD 82943, 47 Uma and GJ 876: Alignment or Antialignment?
Jianghui Ji, Lin Liu, H. Kinoshita +3
We investigated the apsidal motion for the multi-planet systems. In the simulations, we found that the two planets of HD 37124, HD 12661, 47 Uma and HD 82943 separately undergo aps…
uLEAD-TabPFN: Uncertainty-aware Dependency-based Anomaly Detection with TabPFN
Sha Lu, Jixue Liu, Stefan Peters +4
Anomaly detection in tabular data is challenging due to high dimensionality, complex feature dependencies, and heterogeneous noise. Many existing methods rely on proximity-based cu…
Global Update Guided Federated Learning
Qilong Wu, Lin Liu, Shibei Xue
Federated learning protects data privacy and security by exchanging models instead of data. However, unbalanced data distributions among participating clients compromise the accura…
From Observational Studies to Causal Rule Mining
Jiuyong Li, Thuc Duy Le, Lin Liu +4
Randomised controlled trials (RCTs) are the most effective approach to causal discovery, but in many circumstances it is impossible to conduct RCTs. Therefore observational studies…
Exploring Effective Mask Sampling Modeling for Neural Image Compression
Lin Liu, Mingming Zhao, Shanxin Yuan +5
Image compression aims to reduce the information redundancy in images. Most existing neural image compression methods rely on side information from hyperprior or context models to…
Interaction-Data-guided Conditional Instrumental Variables for Debiasing Recommender Systems
Zhirong Huang, Debo Cheng, Jiuyong Li +3
It is often challenging to identify a valid instrumental variable (IV), although the IV methods have been regarded as effective tools of addressing the confounding bias introduced…
Live Avatar: Streaming Real-time Audio-Driven Avatar Generation with Infinite Length
Yubo Huang, Hailong Guo, Fangtai Wu +9
Audio-driven avatar interaction demands real-time, streaming, and infinite-length generation -- capabilities fundamentally at odds with the sequential denoising and long-horizon dr…
Method-of-Moments Inference for GLMs and Doubly Robust Functionals under Proportional Asymptotics
Xingyu Chen, Lin Liu, Rajarshi Mukherjee
In this paper, we consider the estimation of regression coefficients and signal-to-noise (SNR) ratio in high-dimensional Generalized Linear Models (GLMs), and explore their implica…
SAR ATR under Limited Training Data Via MobileNetV3
Chenwei Wang, Siyi Luo, Lin Liu +4
In recent years, deep learning has been widely used to solve the bottleneck problem of synthetic aperture radar (SAR) automatic target recognition (ATR). However, most current meth…
Enhancing Dynamic Image Advertising with Vision-Language Pre-training
Zhoufutu Wen, Xinyu Zhao, Zhipeng Jin +5
In the multimedia era, image is an effective medium in search advertising. Dynamic Image Advertising (DIA), a system that matches queries with ad images and generates multimodal ad…
From Correlation to Causation: Max-Pooling-Based Multi-Instance Learning Leads to More Robust Whole Slide Image Classification
Xin Liu, Weijia Zhang, Wei Tang +4
In whole slide images (WSIs) analysis, attention-based multi-instance learning (MIL) models are susceptible to spurious correlations and degrade under domain shift. These methods m…
A linear mixed model approach for measurement error adjustment: applications to sedentary behavior assessment from wearable devices
Ruohui Chen, Dori Rosenberg, Chongzhi Di +6
In recent years, wearable devices have become more common to capture a wide range of health behaviors, especially for physical activity and sedentary behavior. These sensor-based m…
SparseDet: A Simple and Effective Framework for Fully Sparse LiDAR-based 3D Object Detection
Lin Liu, Ziying Song, Qiming Xia +4
LiDAR-based sparse 3D object detection plays a crucial role in autonomous driving applications due to its computational efficiency advantages. Existing methods either use the featu…
PREFER: Prompt Ensemble Learning via Feedback-Reflect-Refine
Chenrui Zhang, Lin Liu, Jinpeng Wang +4
As an effective tool for eliciting the power of Large Language Models (LLMs), prompting has recently demonstrated unprecedented abilities across a variety of complex tasks. To furt…
Assessing Classifier Fairness with Collider Bias
Zhenlong Xu, Ziqi Xu, Jixue Liu +5
The increasing application of machine learning techniques in everyday decision-making processes has brought concerns about the fairness of algorithmic decision-making. This paper c…
GraphBEV: Towards Robust BEV Feature Alignment for Multi-Modal 3D Object Detection
Ziying Song, Lei Yang, Shaoqing Xu +5
Integrating LiDAR and camera information into Bird's-Eye-View (BEV) representation has emerged as a crucial aspect of 3D object detection in autonomous driving. However, existing m…
SPEX: A Vision-Language Model for Land Cover Extraction on Spectral Remote Sensing Images
Dongchen Si, Di Wang, Erzhong Gao +9
Spectral information has long been recognized as a critical cue in remote sensing observations. Although numerous vision-language models have been developed for pixel-level interpr…
Clinically Relevant Mediation Analysis using Controlled Indirect Effect
Haoqi Sun, Michael J. Leone, Lin Liu +3
Mediation analysis allows one to use observational data to estimate the importance of each potential mediating pathway involved in the causal effect of an exposure on an outcome. H…
GenEraser: Generalizable Video Object Removal via Balanced Text-Mask Guidance and Decoupled Locator-Preserver
Yuqing Chen, Lin Liu, Haisu Wu +4
Video object removal frequently struggles to simultaneously eliminate target objects and their associated physical effects (e.g., smoke, reflections, light, and ripples) in out-of-…
Treatment effect estimation with disentangled latent factors
Weijia Zhang, Lin Liu, Jiuyong Li
Much research has been devoted to the problem of estimating treatment effects from observational data; however, most methods assume that the observed variables only contain confoun…
Boosting AI Reliability with an FSM-Driven Streaming Inference Pipeline: An Industrial Case
Yutian Zhang, Zhongyi Pei, Yi Mao +3
The widespread adoption of AI in industry is often hampered by its limited robustness when faced with scenarios absent from training data, leading to prediction bias and vulnerabil…
A fast PC algorithm for high dimensional causal discovery with multi-core PCs
Thuc Duy Le, Tao Hoang, Jiuyong Li +2
Discovering causal relationships from observational data is a crucial problem and it has applications in many research areas. The PC algorithm is the state-of-the-art constraint ba…
Linear Causal Representation Learning by Topological Ordering, Pruning, and Disentanglement
Hao Chen, Lin Liu, Yu Guang Wang
Causal representation learning (CRL) has garnered increasing interest from the causal inference and artificial intelligence communities due to its potential to disentangle complex…
Desiree: a Refinement Calculus for Requirements Problems
Feng-Lin Li, Alexander Borgida, Giancarlo Guizzardi +3
The requirements elicited from stakeholders are typically informal, incomplete, ambiguous, and inconsistent. It is the task of Requirements Engineering to transform them into an el…
Seed-TTS: A Family of High-Quality Versatile Speech Generation Models
Philip Anastassiou, Jiawei Chen, Jitong Chen +43
We introduce Seed-TTS, a family of large-scale autoregressive text-to-speech (TTS) models capable of generating speech that is virtually indistinguishable from human speech. Seed-T…
MTP: Advancing Remote Sensing Foundation Model via Multi-Task Pretraining
Di Wang, Jing Zhang, Minqiang Xu +8
Foundation models have reshaped the landscape of Remote Sensing (RS) by enhancing various image interpretation tasks. Pretraining is an active research topic, encompassing supervis…
Efficient estimation of optimal regimes under a no direct effect assumption
Lin Liu, Zach Shahn, James M. Robins +1
We derive new estimators of an optimal joint testing and treatment regime under the no direct effect (NDE) assumption that a given laboratory, diagnostic, or screening test has no…
Spatial Modulation: an Attractive Secure Solution to Future Wireless Network
Feng Shu, Lin Liu, LiLi Yang +7
As a green and secure wireless transmission method, secure spatial modulation (SM) is becoming a hot research area. Its basic idea is to exploit both the index of activated transmi…
Debiased Contrastive Representation Learning for Mitigating Dual Biases in Recommender Systems
Zhirong Huang, Shichao Zhang, Debo Cheng +3
In recommender systems, popularity and conformity biases undermine recommender effectiveness by disproportionately favouring popular items, leading to their over-representation in…
GraphBEV++: Multi-Modal Feature Alignment for Autonomous Driving
Ziying Song, Caiyan Jia, Lin Liu +3
Feature misalignment in BEV perception is a critical yet often overlooked challenge in autonomous driving, especially under calibration uncertainties between LiDAR and camera senso…
Towards Fair Graph Representation Learning in Social Networks
Guixian Zhang, Guan Yuan, Debo Cheng +3
With the widespread use of Graph Neural Networks (GNNs) for representation learning from network data, the fairness of GNN models has raised great attention lately. Fair GNNs aim t…
Low-Light Video Enhancement with Synthetic Event Guidance
Lin Liu, Junfeng An, Jianzhuang Liu +6
Low-light video enhancement (LLVE) is an important yet challenging task with many applications such as photographing and autonomous driving. Unlike single image low-light enhanceme…
See What You Need: Query-Aware Visual Intelligence through Reasoning-Perception Loops
Zixuan Dong, Baoyun Peng, Yufei Wang +4
Human video comprehension demonstrates dynamic coordination between reasoning and visual attention, adaptively focusing on query-relevant details. However, current long-form video…
Assumption-lean falsification tests of rate double-robustness of double-machine-learning estimators
Lin Liu, Rajarshi Mukherjee, James M. Robins
The class of doubly-robust (DR) functionals studied by Rotnitzky et al. (2021) is of central importance in economics and biostatistics. It strictly includes both (i) the class of m…
Could the 47 UMa Planetary System be a Second Solar System: predicting the Earth-like planets
Jianghui Ji, Lin Liu, H. Kinoshita +1
(Abridged)We numerically investigated the dynamical architecture of 47 UMa with the planetary configuration of the best-fit orbital solutions by Fischer et al. We systematically st…
Assumption-lean covariate adjustment under covariate adaptive randomization when
Yujia Gu, Lin Liu, Wei Ma
Adjusting for (baseline) covariates with working regression models becomes standard practice in the analysis of randomized clinical trials (RCT). When the dimension of the cova…
AST-SED: An Effective Sound Event Detection Method Based on Audio Spectrogram Transformer
Kang Li, Yan Song, Li-Rong Dai +3
In this paper, we propose an effective sound event detection (SED) method based on the audio spectrogram transformer (AST) model, pretrained on the large-scale AudioSet for audio t…
Occlusion-Aware Physics-Semantic Keyframe Selection for Robust Video Editing
Lin Liu, Zhihan Xiao, Haohang Xu +4
Video editing has recently achieved remarkable progress with diffusion-based generative models, enabling diverse object-level manipulations from natural language instructions. Howe…
Federated Large Language Models: Feasibility, Robustness, Security and Future Directions
Wenhao Jiang, Yuchuan Luo, Guilin Deng +6
The integration of Large Language Models (LLMs) and Federated Learning (FL) presents a promising solution for joint training on distributed data while preserving privacy and addres…
Conditional Instrumental Variable Regression with Representation Learning for Causal Inference
Debo Cheng, Ziqi Xu, Jiuyong Li +3
This paper studies the challenging problem of estimating causal effects from observational data, in the presence of unobserved confounders. The two-stage least square (TSLS) method…
Secuer: ultrafast, scalable and accurate clustering of single-cell RNA-seq data
Nana Wei, Yating Nie, Lin Liu +2
Identifying cell clusters is a critical step for single-cell transcriptomics study. Despite the numerous clustering tools developed recently, the rapid growth of scRNA-seq volumes…
An Ultra-high Numerical Aperture Metalens at Visible Wavelengths
Haowen Liang, Qiaoling Lin, Xiangsheng Xie +8
We demonstrate a metalens with NA = 0.98 in air, a bandwidth (FWHM) of 274 nm and a focusing efficiency of 67% at 532 nm wavelength, which is close to the transmission performance…
Learning causal representations for robust domain adaptation
Shuai Yang, Kui Yu, Fuyuan Cao +3
Domain adaptation solves the learning problem in a target domain by leveraging the knowledge in a relevant source domain. While remarkable advances have been made, almost all exist…
The Stability Analysis of the Extrasolar Planetary Systems
Jianghui Ji, Lin Liu, H. Kinoshita +2
To date, more than 100 giant Jupiter-like planets have been discovered in Doppler surveys of solar-type stars. In this paper, we perform simulations to investigate three systems: G…
DriveWorld-VLA: Unified Latent-Space World Modeling with Vision-Language-Action for Autonomous Driving
Feiyang jia, Lin Liu, Ziying Song +4
End-to-end (E2E) autonomous driving has recently attracted increasing interest in unifying Vision-Language-Action (VLA) with World Models to enhance decision-making and forward-loo…
Forensic Taxonomy of Popular Android mHealth Apps
Abdullah Azfar, Kim-Kwang Raymond Choo, Lin Liu
Mobile health applications (or mHealth apps, as they are commonly known) are increasingly popular with both individual end users and user groups such as physicians. Due to their ab…
Breaking the Hourglass Phenomenon of Residual Quantization: Enhancing the Upper Bound of Generative Retrieval
Zhirui Kuai, Zuxu Chen, Huimu Wang +11
Generative retrieval (GR) has emerged as a transformative paradigm in search and recommender systems, leveraging numeric-based identifier representations to enhance efficiency and…
O-DisCo-Edit: Object Distortion Control for Unified Realistic Video Editing
Yuqing Chen, Junjie Wang, Lin Liu +4
Diffusion models have recently advanced video editing, yet controllable editing remains challenging due to the need for precise manipulation of diverse object properties. Current m…
Beyond Imitation: Constraint-Aware Trajectory Generation with Flow Matching For End-to-End Autonomous Driving
Lin Liu, Guanyi Yu, Ziying Song +5
Planning is a critical component of end-to-end autonomous driving. However, prevailing imitation learning methods often suffer from mode collapse, failing to produce diverse trajec…
Linear mixed model vs two-stage methods: Developing prognostic models of diabetic kidney disease progression
Brian Kwan, Lin Liu, David Strong +2
Identifying prognostic factors for disease progression is a cornerstone of medical research. Repeated assessments of a marker outcome are often used to evaluate disease progression…
QUIZ: An Arbitrary Volumetric Point Matching Method for Medical Image Registration
Lin Liu, Xinxin Fan, Haoyang Liu +6
Rigid pre-registration involving local-global matching or other large deformation scenarios is crucial. Current popular methods rely on unsupervised learning based on grayscale sim…
Feature Selection for Efficient Local-to-Global Bayesian Network Structure Learning
Kui Yu, Zhaolong Ling, Lin Liu +2
Local-to-global learning approach plays an essential role in Bayesian network (BN) structure learning. Existing local-to-global learning algorithms first construct the skeleton of…
UNSCT-HRNet: Modeling Anatomical Uncertainty for Landmark Detection in Total Hip Arthroplasty
Jiaxin Wan, Lin Liu, Haoran Wang +9
Total hip arthroplasty (THA) relies on accurate landmark detection from radiographic images, but unstructured data caused by irregular patient postures or occluded anatomical marke…
Higher-Order Debiased Estimators for General Treatment Models
Yulin Zhang, Lin Liu, Zheng Zhang
It is now well known that estimators based on influence functions can be sub-optimal in terms of convergence rates in various settings. To address this issue, higher-order influenc…
ENSI: Efficient Non-Interactive Secure Inference for Large Language Models
Zhiyu He, Maojiang Wang, Xinwen Gao +3
Secure inference enables privacy-preserving machine learning by leveraging cryptographic protocols that support computations on sensitive user data without exposing it. However, in…
A doubly robust estimator for the Mann Whitney Wilcoxon Rank Sum Test when applied for causal inference in observational studies
Ruohui Chen, Tuo Lin, Lin Liu +8
The Mann-Whitney-Wilcoxon rank sum test (MWWRST) is a widely used method for comparing two treatment groups in randomized control trials, particularly when dealing with highly skew…
ParaUni: Enhance Generation in Unified Multimodal Model with Reinforcement-driven Hierarchical Parallel Information Interaction
Jiangtong Tan, Lin Liu, Jie Huanng +3
Unified multimodal models significantly improve visual generation by combining vision-language models (VLMs) with diffusion models. However, existing methods struggle to fully bala…
Discovering Ancestral Instrumental Variables for Causal Inference from Observational Data
Debo Cheng, Jiuyong Li, Lin Liu +3
Instrumental variable (IV) is a powerful approach to inferring the causal effect of a treatment on an outcome of interest from observational data even when there exist latent confo…
Discovering Markov Blanket from Multiple interventional Datasets
Kui Yu, Lin Liu, Jiuyong Li
In this paper, we study the problem of discovering the Markov blanket (MB) of a target variable from multiple interventional datasets. Datasets attained from interventional experim…
Honor of Kings Arena: an Environment for Generalization in Competitive Reinforcement Learning
Hua Wei, Jingxiao Chen, Xiyang Ji +11
This paper introduces Honor of Kings Arena, a reinforcement learning (RL) environment based on Honor of Kings, one of the world's most popular games at present. Compared to other e…
Any Part of Bayesian Network Structure Learning
Zhaolong Ling, Kui Yu, Hao Wang +2
We study an interesting and challenging problem, learning any part of a Bayesian network (BN) structure. In this challenge, it will be computationally inefficient using existing gl…
Denoising GER: A Noise-Robust Generative Error Correction with LLM for Speech Recognition
Yanyan Liu, Minqiang Xu, Yihao Chen +4
In recent years, large language models (LLM) have made significant progress in the task of generation error correction (GER) for automatic speech recognition (ASR) post-processing.…
Causal Inference with the Napkin Graph
Anna Guo, Lin Liu, David Benkeser +1
Unmeasured confounding can render identification strategies based on adjustment functionals invalid. We study the "Napkin" graph, a causal structure that encapsulates features of M…
Semantic-enhanced Modality-asymmetric Retrieval for Online E-commerce Search
Zhigong Zhou, Ning Ding, Xiaochuan Fan +8
Semantic retrieval, which retrieves semantically matched items given a textual query, has been an essential component to enhance system effectiveness in e-commerce search. In this…
Learn from Your Mistakes: Tree-like Self-Play for Secure Code LLMs
Wenqi Chen, Ziyan Zhang, Bin Wang +3
While Large Language Models (LLMs) excel in code generation, they remain prone to replicating subtle yet critical vulnerabilities endemic to their training data. Current alignment…
Linking Model Intervention to Causal Interpretation in Model Explanation
Debo Cheng, Ziqi Xu, Jiuyong Li +4
Intervention intuition is often used in model explanation where the intervention effect of a feature on the outcome is quantified by the difference of a model prediction when the f…
Intestinal Microecology in Pediatric Surgery-Related Gastrointestinal Diseases Current Insights and Future Perspectives
Yingchao Li, Yuqing Wu, Suolin Li +4
Intestinal microecology is established from birth and is constantly changing until homeostasis is reached. Intestinal microecology is involved in the immune inflammatory response o…
A Learning-based Stochastic Driving Model for Autonomous Vehicle Testing
Lin Liu, Shuo Feng, Yiheng Feng +2
In the simulation-based testing and evaluation of autonomous vehicles (AVs), how background vehicles (BVs) drive directly influences the AV's driving behavior and further impacts t…
A Structural Representation Learning for Multi-relational Networks
Xin Li, Huiting Hong, Lin Liu +1
Most of the existing multi-relational network embedding methods, e.g., TransE, are formulated to preserve pair-wise connectivity structures in the networks. With the observations t…
A robust score test in g-computation for covariate adjustment in randomized clinical trials leveraging different variance estimators via influence functions
Xin Zhang, Haitao Chu, Lin Liu +1
G-computation has become a widely used robust method for estimating unconditional (marginal) treatment effects with covariate adjustment in the analysis of randomized clinical tria…
Dynamic Network Embedding via Incremental Skip-gram with Negative Sampling
Hao Peng, Jianxin Li, Hao Yan +5
Network representation learning, as an approach to learn low dimensional representations of vertices, has attracted considerable research attention recently. It has been proven ext…
Self-supervised Hierarchical Visual Reasoning with World Model
Yuanfei Xu, Lin Liu, Wengang Zhou +2
3D open-world environments with adversarial opponents remain a core challenge for reinforcement learning due to their vast state spaces. Effective reasoning representations are ess…
Linking a predictive model to causal effect estimation
Jiuyong Li, Lin Liu, Ziqi Xu +3
A predictive model makes outcome predictions based on some given features, i.e., it estimates the conditional probability of the outcome given a feature vector. In general, a predi…
OMG-Avatar: One-shot Multi-LOD Gaussian Head Avatar
Jianqiang Ren, Lin Liu, Steven Hoi
We propose OMG-Avatar, a novel One-shot method that leverages a Multi-LOD (Level-of-Detail) Gaussian representation for animatable 3D head reconstruction from a single image in 0.2…
Evidence for the Meissner effect in the nickelate superconductor La3Ni2O7-delta single crystal using diamond quantum sensors
Lin Liu, Jianning Guo, Deyuan Hu +6
Quantum sensing with nitrogen-vacancy (NV) centers in diamond enables the characterization of magnetic properties in the extreme situation of tiny sample with defects. Recent studi…
MEPG:Multi-Expert Planning and Generation for Compositionally-Rich Image Generation
Yuan Zhao, Lin Liu
Text-to-image diffusion models have achieved remarkable image quality, but they still struggle with complex, multiele ment prompts, and limited stylistic diversity. To address thes…
Order Dependence in Regression by Composition: Discussion on "Regression by Composition'' by Farewell, Daniel, Stensrud, and Huitfeldt
Mei Dong, Linbo Wang, Lin Liu +1
We discuss the regression-by-composition framework of Farewell, Daniel, Stensrud and Huitfeldt, highlighting a key consequence of its sequential construction: order dependence. Reo…
Toward Variation-Independent Regression by Composition
Ruixuan Zhao, Oliver Dukes, Linbo Wang +1
Discussion on "Regression by Composition" by Farewell, Daniel, Stensrud, and Huitfeldt.
PIP: Prototypes-Injected Prompt for Federated Class Incremental Learning
Muhammad Anwar Ma'sum, Mahardhika Pratama, Savitha Ramasamy +3
Federated Class Incremental Learning (FCIL) is a new direction in continual learning (CL) for addressing catastrophic forgetting and non-IID data distribution simultaneously. Exist…
Three-Stream Temporal-Shift Attention Network Based on Self-Knowledge Distillation for Micro-Expression Recognition
Guanghao Zhu, Lin Liu, Yuhao Hu +8
Micro-expressions are subtle facial movements that occur spontaneously when people try to conceal real emotions. Micro-expression recognition is crucial in many fields, including c…
Enhancing Long Video Question Answering with Scene-Localized Frame Grouping
Xuyi Yang, Wenhao Zhang, Hongbo Jin +5
Current Multimodal Large Language Models (MLLMs) often perform poorly in long video understanding, primarily due to resource limitations that prevent them from processing all video…
Advancing Re-Ranking with Multimodal Fusion and Target-Oriented Auxiliary Tasks in E-Commerce Search
Enqiang Xu, Xinhui Li, Zhigong Zhou +6
In the rapidly evolving field of e-commerce, the effectiveness of search re-ranking models is crucial for enhancing user experience and driving conversion rates. Despite significan…
Multimodal Information Interaction for Medical Image Segmentation
Xinxin Fan, Lin Liu, Haoran Zhang
The use of multimodal data in assisted diagnosis and segmentation has emerged as a prominent area of interest in current research. However, one of the primary challenges is how to…
Toward an Asymptotic Efficiency Theory on Regular Parameter Manifolds
Lvfang Sun, Zhenhua Lin, Lin Liu
Asymptotic efficiency theory is one of the pillars in the foundations of modern mathematical statistics. Not only does it serve as a rigorous theoretical benchmark for evaluating s…
Root-n consistent semiparametric learning with high-dimensional nuisance functions under minimal sparsity
Lin Liu, Xinbo Wang, Yuhao Wang
Treatment effect estimation under unconfoundedness is a fundamental task in causal inference. In response to the challenge of analyzing high-dimensional datasets collected in subst…
LEA: Label Enumeration Attack in Vertical Federated Learning
Wenhao Jiang, Shaojing Fu, Yuchuan Luo +1
A typical Vertical Federated Learning (VFL) scenario involves several participants collaboratively training a machine learning model, where each party has different features for th…
Inclusion Arena: An Open Platform for Evaluating Large Foundation Models with Real-World Apps
Kangyu Wang, Hongliang He, Lin Liu +3
Large Language Models (LLMs) and Multimodal Large Language Models (MLLMs) have ushered in a new era of AI capabilities, demonstrating near-human-level performance across diverse sc…
KBest: Efficient Vector Search on Kunpeng CPU
Kaihao Ma, Meiling Wang, Senkevich Oleg +19
Vector search, which returns the vectors most similar to a given query vector from a large vector dataset, underlies many important applications such as search, recommendation, and…
AstMatch: Adversarial Self-training Consistency Framework for Semi-Supervised Medical Image Segmentation
Guanghao Zhu, Jing Zhang, Juanxiu Liu +4
Semi-supervised learning (SSL) has shown considerable potential in medical image segmentation, primarily leveraging consistency regularization and pseudo-labeling. However, many SS…
GuideFlow: Constraint-Guided Flow Matching for Planning in End-to-End Autonomous Driving
Lin Liu, Caiyan Jia, Guanyi Yu +6
Driving planning is a critical component of end-to-end (E2E) autonomous driving. However, prevailing Imitative E2E Planners often suffer from multimodal trajectory mode collapse, f…
A Middle Path for On-Premises LLM Deployment: Preserving Privacy Without Sacrificing Model Confidentiality
Hanbo Huang, Yihan Li, Bowen Jiang +5
Privacy-sensitive users require deploying large language models (LLMs) within their own infrastructure (on-premises) to safeguard private data and enable customization. However, vu…
Adversarial Mixture Of Experts with Category Hierarchy Soft Constraint
Zhuojian Xiao, Yunjiang jiang, Guoyu Tang +4
Product search is the most common way for people to satisfy their shopping needs on e-commerce websites. Products are typically annotated with one of several broad categorical tags…
Covariate Adjustment in Randomized Experiments Motivated by Higher-Order Influence Functions
Sihui Zhao, Xinbo Wang, Lin Liu +1
Higher-Order Influence Functions (HOIF), developed in a series of papers over the past twenty years, are a fundamental theoretical device for constructing rate-optimal causal-effec…
Disentangled Representation for Causal Mediation Analysis
Ziqi Xu, Debo Cheng, Jiuyong Li +3
Estimating direct and indirect causal effects from observational data is crucial to understanding the causal mechanisms and predicting the behaviour under different interventions.…
A Parameter-Centric View on Regression
Jingxin Yan, Lin Liu, Oliver Dukes +2
Discussion on ``Regression by Composition'' by Farewell, Daniel, Stensrud, and Huitfeldt
Sufficient Dimension Reduction for Average Causal Effect Estimation
Debo Cheng, Jiuyong Li, Lin Liu +1
Having a large number of covariates can have a negative impact on the quality of causal effect estimation since confounding adjustment becomes unreliable when the number of covaria…
Multi-Cause Deconfounding for Recommender Systems with Latent Confounders
Zhirong Huang, Shichao Zhang, Debo Cheng +3
In recommender systems, various latent confounding factors (e.g., user social environment and item public attractiveness) can affect user behavior, item exposure, and feedback in d…
Efficient LLM-based Advertising via Model Compression and Parallel Verification
Wenxin Dong, Chang Gao, Guanghui Yu +9
Large language models (LLMs) have shown remarkable potential in advertising scenarios such as ad creative generation and targeted advertising. However, deploying LLMs in real-time…
Causal Inference with Conditional Front-Door Adjustment and Identifiable Variational Autoencoder
Ziqi Xu, Debo Cheng, Jiuyong Li +3
An essential and challenging problem in causal inference is causal effect estimation from observational data. The problem becomes more difficult with the presence of unobserved con…
Peer Effect Estimation in the Presence of Simultaneous Feedback and Unobserved Confounders
Xiaojing Du, Jiuyong Li, Lin Liu +2
Estimating peer causal effects within complex real-world networks such as social networks is challenging, primarily due to simultaneous feedback between peers and unobserved confou…