Search Results for author:
Found 45 papers, 17 papers with code
On Transferability of Histological Tissue Labels in Computational Pathology
Deep learning tools in computational pathology, unlike natural vision tasks, face with limited histological tissue labels for classification.
Deep Probabilistic Modeling of User Behavior for Anomaly Detection via Mixture Density Networks
To improve the identification of potential anomaly patterns in complex user behavior, this paper proposes an anomaly detection method based on a deep mixture density network.
Deep Graph Reinforcement Learning for UAV-Enabled Multi-User Secure Communications
While unmanned aerial vehicles (UAVs) with flexible mobility are envisioned to enhance physical layer security in wireless communications, the efficient security design that adapts to such high network dynamics is rather challenging.
Feature Learning beyond the Lazy-Rich Dichotomy: Insights from Representational Geometry
Our framework provides a novel geometric perspective for understanding and quantifying feature learning in both artificial and biological neural networks.
Test-Time Backdoor Detection for Object Detection Models
To this end, we design TRAnsformation Consistency Evaluation (TRACE), a brand-new method for detecting poisoned samples at test time in object detection.
Can A Society of Generative Agents Simulate Human Behavior and Inform Public Health Policy? A Case Study on Vaccine Hesitancy
Can we simulate a sandbox society with generative agents to model human behavior, thereby reducing the over-reliance on real human trials for assessing public policies?
The Shape of Generalization through the Lens of Norm-based Capacity Control
Understanding how the test risk scales with model complexity is a central question in machine learning.
Breaking Barriers in Physical-World Adversarial Examples: Improving Robustness and Transferability via Robust Feature
In the second stage, we use attention-based feature fusion to overlay these RFs onto predictive features of clean images and remove unnecessary perturbations.
CSP-AIT-Net: A contrastive learning-enhanced spatiotemporal graph attention framework for short-term metro OD flow prediction with asynchronous inflow tracking
To address these issues, we propose CSP-AIT-Net, a novel spatiotemporal graph attention framework designed to enhance OD flow prediction by incorporating asynchronous inflow tracking and advanced station semantics representation.
Jailbreak Large Vision-Language Models Through Multi-Modal Linkage
With the significant advancement of Large Vision-Language Models (VLMs), concerns about their potential misuse and abuse have grown rapidly.
Perturbation Ontology based Graph Attention Networks
In recent years, graph representation learning has undergone a paradigm shift, driven by the emergence and proliferation of graph neural networks (GNNs) and their heterogeneous counterparts.
SentiXRL: An advanced large language Model Framework for Multilingual Fine-Grained Emotion Classification in Complex Text Environment
With strong expressive capabilities in Large Language Models(LLMs), generative models effectively capture sentiment structures and deep semantics, however, challenges remain in fine-grained sentiment classification across multi-lingual and complex contexts.
Multiscale spatiotemporal heterogeneity analysis of bike-sharing system's self-loop phenomenon: Evidence from Shanghai
Marginal treatment effects of residential land use is higher on streets with middle-aged residents, high fixed employment, and low car ownership.
Navigating Spatial Inequities in Freight Truck Crash Severity via Counterfactual Inference in Los Angeles
Freight truck-related crashes pose significant challenges, leading to substantial economic losses, injuries, and fatalities, with pronounced spatial disparities across different regions.
TrojanRobot: Physical-World Backdoor Attacks Against VLM-based Robotic Manipulation
To address this, we propose \textit{TrojanRobot}, a highly stealthy and broadly effective robotic backdoor attack in the physical world.
BadRobot: Jailbreaking Embodied LLMs in the Physical World
Embodied AI represents systems where AI is integrated into physical entities.
Concentrate Attention: Towards Domain-Generalizable Prompt Optimization for Language Models
Recent advances in prompt optimization have notably enhanced the performance of pre-trained language models (PLMs) on downstream tasks.
Deconstructing The Ethics of Large Language Models from Long-standing Issues to New-emerging Dilemmas: A Survey
Large Language Models (LLMs) have achieved unparalleled success across diverse language modeling tasks in recent years.
Detector Collapse: Physical-World Backdooring Object Detection to Catastrophic Overload or Blindness in Autonomous Driving
This paper is dedicated to bridging this gap by introducing Detector Collapse} (DC), a brand-new backdoor attack paradigm tailored for object detection.
Stumbling Blocks: Stress Testing the Robustness of Machine-Generated Text Detectors Under Attacks
Our experiments reveal that almost none of the existing detectors remain robust under all the attacks, and all detectors exhibit different loopholes.
k-SemStamp: A Clustering-Based Semantic Watermark for Detection of Machine-Generated Text
Recent watermarked generation algorithms inject detectable signatures during language generation to facilitate post-hoc detection.
Does DetectGPT Fully Utilize Perturbation? Bridging Selective Perturbation to Fine-tuned Contrastive Learning Detector would be Better
Hence, we propose a novel fine-tuned detector, Pecola, bridging metric-based and fine-tuned methods by contrastive learning on selective perturbation.
Improving Pacing in Long-Form Story Planning
Existing LLM-based systems for writing long-form stories or story outlines frequently suffer from unnatural pacing, whether glossing over important events or over-elaborating on insignificant details, resulting in a jarring experience for the reader.
Fuzzy-NMS: Improving 3D Object Detection with Fuzzy Classification in NMS
The proposed Fuzzy-NMS module combines the volume and clustering density of candidate bounding boxes, refining them with a fuzzy classification method and optimizing the appropriate suppression thresholds to reduce uncertainty in the NMS process.
Dual Radar: A Multi-modal Dataset with Dual 4D Radar for Autonomous Driving
Compared with commonly used 3D radars, the latest 4D radars have precise vertical resolution and higher point cloud density, making it a highly promising sensor for autonomous driving in complex environmental perception.
SemStamp: A Semantic Watermark with Paraphrastic Robustness for Text Generation
Existing watermarking algorithms are vulnerable to paraphrase attacks because of their token-level design.
Self-explainable Graph Neural Network for Alzheimer's Disease And Related Dementias Risk Prediction
Objective: Our goal is to utilize Graph Neural Networks (GNNs) with claims data for ADRD risk prediction.
Dialogue for Prompting: a Policy-Gradient-Based Discrete Prompt Generation for Few-shot Learning
However, prior discrete prompt optimization methods require expert knowledge to design the base prompt set and identify high-quality prompts, which is costly, inefficient, and subjective.
Score Attack: A Lower Bound Technique for Optimal Differentially Private Learning
The score attack method is based on the tracing attack concept in differential privacy and can be applied to any statistical model with a well-defined score statistic.
Improved Differentially Private Regression via Gradient Boosting
We revisit the problem of differentially private squared error linear regression.
CoCo: Coherence-Enhanced Machine-Generated Text Detection Under Data Limitation With Contrastive Learning
Machine-Generated Text (MGT) detection, a task that discriminates MGT from Human-Written Text (HWT), plays a crucial role in preventing misuse of text generative models, which excel in mimicking human writing style recently.
The Cost of Privacy in Generalized Linear Models: Algorithms and Minimax Lower Bounds
We propose differentially private algorithms for parameter estimation in both low-dimensional and high-dimensional sparse generalized linear models (GLMs) by constructing private versions of projected gradient descent.
Learning unbiased zero-shot semantic segmentation networks via transductive transfer
Our method assumes that both the source images with full pixel-level labels and unlabeled target images are available during training.
Hierarchical Temporal Convolutional Networks for Dynamic Recommender Systems
Recommender systems that can learn from cross-session data to dynamically predict the next item a user will choose are crucial for online platforms.
The Cost of Privacy: Optimal Rates of Convergence for Parameter Estimation with Differential Privacy
By refining the "tracing adversary" technique for lower bounds in the theoretical computer science literature, we formulate a general lower bound argument for minimax risks with differential privacy constraints, and apply this argument to high-dimensional mean estimation and linear regression problems.
Learning to Optimize via Wasserstein Deep Inverse Optimal Control
We first propose a unified KL framework that generalizes existing maximum entropy inverse optimal control methods.
Predicting User Activity Level In Point Processes With Mass Transport Equation
Point processes are powerful tools to model user activities and have a plethora of applications in social sciences.
Know-Evolve: Deep Temporal Reasoning for Dynamic Knowledge Graphs
The occurrence of a fact (edge) is modeled as a multivariate point process whose intensity function is modulated by the score for that fact computed based on the learned entity embeddings.
Variational Policy for Guiding Point Processes
Temporal point processes have been widely applied to model event sequence data generated by online users.
Coevolutionary Latent Feature Processes for Continuous-Time User-Item Interactions
Matching users to the right items at the right time is a fundamental task in recommendation systems.
Deep Coevolutionary Network: Embedding User and Item Features for Recommendation
DeepCoevolve use recurrent neural network (RNN) over evolving networks to define the intensity function in point processes, which allows the model to capture complex mutual influence between users and items, and the feature evolution over time.
Fast and Simple Optimization for Poisson Likelihood Models
Since almost all gradient-based optimization algorithms rely on Lipschitz-continuity, optimizing Poisson likelihood models with a guarantee of convergence can be challenging, especially for large-scale problems.
Time-Sensitive Recommendation From Recurrent User Activities
By making personalized suggestions, a recommender system is playing a crucial role in improving the engagement of users in modern web-services.
COEVOLVE: A Joint Point Process Model for Information Diffusion and Network Co-evolution
Information diffusion in online social networks is affected by the underlying network topology, but it also has the power to change it.
