Search Results for author:
Found 64 papers, 30 papers with code
Driving with Regulation: Interpretable Decision-Making for Autonomous Vehicles with Retrieval-Augmented Reasoning via LLM
This work presents an interpretable decision-making framework for autonomous vehicles that integrates traffic regulations, norms, and safety guidelines comprehensively and enables seamless adaptation to different regions.
Reconstructing Human Mobility Pattern: A Semi-Supervised Approach for Cross-Dataset Transfer Learning
Our model is validated using comprehensive datasets from the United States, where it effectively reconstructs activity chains and generates high-quality synthetic mobility data, achieving a low Jensen-Shannon Divergence (JSD) value of 0. 001, indicating a close similarity between synthetic and real data.
Human Mobility Modeling with Limited Information via Large Language Models
Understanding human mobility patterns has traditionally been a complex challenge in transportation modeling.
NUMOSIM: A Synthetic Mobility Dataset with Anomaly Detection Benchmarks
Collecting real-world mobility data is challenging.
Multi-scale Temporal Fusion Transformer for Incomplete Vehicle Trajectory Prediction
Motion prediction plays an essential role in autonomous driving systems, enabling autonomous vehicles to achieve more accurate local-path planning and driving decisions based on predictions of the surrounding vehicles.
Perceive-IR: Learning to Perceive Degradation Better for All-in-One Image Restoration
In the prompt learning stage, we leverage prompt learning to acquire a fine-grained quality perceiver capable of distinguishing three-tier quality levels by constraining the prompt-image similarity in the CLIP perception space.
CooPre: Cooperative Pretraining for V2X Cooperative Perception
Existing Vehicle-to-Everything (V2X) cooperative perception methods rely on accurate multi-agent 3D annotations.
MSTF: Multiscale Transformer for Incomplete Trajectory Prediction
MSTF integrates a Multiscale Attention Head (MAH) and an Information Increment-based Pattern Adaptive (IIPA) module.
HyperSIGMA: Hyperspectral Intelligence Comprehension Foundation Model
To tackle the spectral and spatial redundancy challenges in HSIs, we introduce a novel sparse sampling attention (SSA) mechanism, which effectively promotes the learning of diverse contextual features and serves as the basic block of HyperSIGMA.
Deploying scalable traffic prediction models for efficient management in real-world large transportation networks during hurricane evacuations
Accurate traffic prediction is vital for effective traffic management during hurricane evacuation.
DCA-Bench: A Benchmark for Dataset Curation Agents
Despite the proliferation of open dataset platforms nowadays, data quality issues, such as insufficient documentation, inaccurate annotations, and ethical concerns, remain common in datasets widely used in AI.
An Attention-Based Multi-Context Convolutional Encoder-Decoder Neural Network for Work Zone Traffic Impact Prediction
Work zone is one of the major causes of non-recurrent traffic congestion and road incidents.
AI Risk Management Should Incorporate Both Safety and Security
The exposure of security vulnerabilities in safety-aligned language models, e. g., susceptibility to adversarial attacks, has shed light on the intricate interplay between AI safety and AI security.
A Two-sided Model for EV Market Dynamics and Policy Implications
The diffusion of Electric Vehicles (EVs) plays a pivotal role in mitigating greenhouse gas emissions, particularly in the U. S., where ambitious zero-emission and carbon neutrality objectives have been set.
Efficient Ensembles Improve Training Data Attribution
Training data attribution (TDA) methods aim to quantify the influence of individual training data points on the model predictions, with broad applications in data-centric AI, such as mislabel detection, data selection, and copyright compensation.
Semantic Trajectory Data Mining with LLM-Informed POI Classification
In our evaluation using the OpenStreetMap (OSM) POI dataset, our approach achieves a 93. 4% accuracy and a 96. 1% F-1 score in POI classification, and a 91. 7% accuracy with a 92. 3% F-1 score in activity inference.
Towards Reliable Empirical Machine Unlearning Evaluation: A Game-Theoretic View
Machine unlearning is the process of updating machine learning models to remove the information of specific training data samples, in order to comply with data protection regulations that allow individuals to request the removal of their personal data.
V2X-Real: a Largs-Scale Dataset for Vehicle-to-Everything Cooperative Perception
Recent advancements in Vehicle-to-Everything (V2X) technologies have enabled autonomous vehicles to share sensing information to see through occlusions, greatly boosting the perception capability.
OpenHEXAI: An Open-Source Framework for Human-Centered Evaluation of Explainable Machine Learning
However, properly evaluating the effectiveness of the XAI methods inevitably requires the involvement of human subjects, and conducting human-centered benchmarks is challenging in a number of ways: designing and implementing user studies is complex; numerous design choices in the design space of user study lead to problems of reproducibility; and running user studies can be challenging and even daunting for machine learning researchers.
Breaking Data Silos: Cross-Domain Learning for Multi-Agent Perception from Independent Private Sources
However, the data source to train the various agents is independent and private in each company, leading to the Distribution Gap of different private data for training distinct agents in multi-agent perception system.
Computational Copyright: Towards A Royalty Model for Music Generative AI
This research is one of the early attempts to integrate technical advancements with economic and legal considerations in the field of music generative AI, offering a computational copyright solution for the challenges posed by the opaque nature of AI technologies.
Confronting LLMs with Traditional ML: Rethinking the Fairness of Large Language Models in Tabular Classifications
Recent literature has suggested the potential of using large language models (LLMs) to make classifications for tabular tasks.
Optimizing the Placement of Roadside LiDARs for Autonomous Driving
We define perceptual gain as the increased perceptual capability when a new LiDAR is placed.
Can LLMs Effectively Leverage Graph Structural Information through Prompts, and Why?
We aim to understand why the incorporation of structural information inherent in graph data can improve the prediction performance of LLMs.
Towards Vehicle-to-everything Autonomous Driving: A Survey on Collaborative Perception
Specifically, we analyze the performance changes of different methods under different bandwidths, providing a deep insight into the performance-bandwidth trade-off issue.
Accurate, Explainable, and Private Models: Providing Recourse While Minimizing Training Data Leakage
We present two novel methods to generate differentially private recourse: Differentially Private Model (DPM) and Laplace Recourse (LR).
Fair Machine Unlearning: Data Removal while Mitigating Disparities
In this work, we demonstrate that most efficient unlearning methods cannot accommodate popular fairness interventions, and we propose the first fair machine unlearning method that can efficiently unlearn data instances from a fair objective.
Analyzing Chain-of-Thought Prompting in Large Language Models via Gradient-based Feature Attributions
Chain-of-thought (CoT) prompting has been shown to empirically improve the accuracy of large language models (LLMs) on various question answering tasks.
Domain Adaptation based Object Detection for Autonomous Driving in Foggy and Rainy Weather
To bridge the domain gap and improve the performance of object detection in foggy and rainy weather, this paper presents a novel framework for domain-adaptive object detection.
S2R-ViT for Multi-Agent Cooperative Perception: Bridging the Gap from Simulation to Reality
We investigate the effects of these two types of domain gaps and propose a novel uncertainty-aware vision transformer to effectively relief the Deployment Gap and an agent-based feature adaptation module with inter-agent and ego-agent discriminators to reduce the Feature Gap.
ProRes: Exploring Degradation-aware Visual Prompt for Universal Image Restoration
We then leverage degradation-aware visual prompts to establish a controllable and universal model for image restoration, called ProRes, which is applicable to an extensive range of image restoration tasks.
Post Hoc Explanations of Language Models Can Improve Language Models
Large Language Models (LLMs) have demonstrated remarkable capabilities in performing complex tasks.
HM-ViT: Hetero-modal Vehicle-to-Vehicle Cooperative perception with vision transformer
We present HM-ViT, the first unified multi-agent hetero-modal cooperative perception framework that can collaboratively predict 3D objects for highly dynamic vehicle-to-vehicle (V2V) collaborations with varying numbers and types of agents.
FedBEVT: Federated Learning Bird's Eye View Perception Transformer in Road Traffic Systems
Our findings suggest that FedBEVT outperforms the baseline approaches in all four use cases, demonstrating the potential of our approach for improving BEV perception in autonomous driving.
V2V4Real: A Real-world Large-scale Dataset for Vehicle-to-Vehicle Cooperative Perception
To facilitate the development of cooperative perception, we present V2V4Real, the first large-scale real-world multi-modal dataset for V2V perception.
Towards Bridging the Gaps between the Right to Explanation and the Right to be Forgotten
The Right to Explanation and the Right to be Forgotten are two important principles outlined to regulate algorithmic decision making and data usage in real-world applications.
Learning for Vehicle-to-Vehicle Cooperative Perception under Lossy Communication
Due to the beneficial Vehicle-to-Vehicle (V2V) communication, the deep learning based features from other agents can be shared to the ego vehicle so as to improve the perception of the ego vehicle.
Graph Learning Indexer: A Contributor-Friendly and Metadata-Rich Platform for Graph Learning Benchmarks
First, GLI is designed to incentivize \emph{dataset contributors}.
Analyzing Infrastructure LiDAR Placement with Realistic LiDAR Simulation Library
Through simulating point cloud data in different LiDAR placements, we can evaluate the perception accuracy of these placements using multiple detection models.
Domain Adaptive Object Detection for Autonomous Driving under Foggy Weather
This paper proposes a novel domain adaptive object detection framework for autonomous driving under foggy weather.
Bridging the Domain Gap for Multi-Agent Perception
Existing multi-agent perception algorithms usually select to share deep neural features extracted from raw sensing data between agents, achieving a trade-off between accuracy and communication bandwidth limit.
V2XP-ASG: Generating Adversarial Scenes for Vehicle-to-Everything Perception
Recent advancements in Vehicle-to-Everything communication technology have enabled autonomous vehicles to share sensory information to obtain better perception performance.
ELMformer: Efficient Raw Image Restoration with a Locally Multiplicative Transformer
In order to get raw images of high quality for downstream Image Signal Process (ISP), in this paper we present an Efficient Locally Multiplicative Transformer called ELMformer for raw image restoration.
CoBEVT: Cooperative Bird's Eye View Semantic Segmentation with Sparse Transformers
The extensive experiments on the V2V perception dataset, OPV2V, demonstrate that CoBEVT achieves state-of-the-art performance for cooperative BEV semantic segmentation.
Pik-Fix: Restoring and Colorizing Old Photos
Our proposed framework consists of three modules: a restoration sub-network that conducts restoration from degradations, a similarity network that performs color histogram matching and color transfer, and a colorization subnet that learns to predict the chroma elements of images conditioned on chromatic reference signals.
V2X-ViT: Vehicle-to-Everything Cooperative Perception with Vision Transformer
In this paper, we investigate the application of Vehicle-to-Everything (V2X) communication to improve the perception performance of autonomous vehicles.
Ranked #1 on
3D Object Detection
on V2XSet
ROMNet: Renovate the Old Memories
Renovating the memories in old photos is an intriguing research topic in computer vision fields.
Partition-Based Active Learning for Graph Neural Networks
We study the problem of semi-supervised learning with Graph Neural Networks (GNNs) in an active learning setup.
Fast Learning of MNL Model from General Partial Rankings with Application to Network Formation Modeling
The problem of learning mixture of MNL models from partial rankings naturally arises in such applications.
How Much Space Has Been Explored? Measuring the Chemical Space Covered by Databases and Machine-Generated Molecules
We further evaluate how well the existing databases and generation models cover the chemical space in terms of #Circles.
OPV2V: An Open Benchmark Dataset and Fusion Pipeline for Perception with Vehicle-to-Vehicle Communication
We then construct a comprehensive benchmark with a total of 16 implemented models to evaluate several information fusion strategies~(i. e. early, late, and intermediate fusion) with state-of-the-art LiDAR detection algorithms.
Ranked #2 on
3D Object Detection
on OPV2V
Subgroup Generalization and Fairness of Graph Neural Networks
Despite enormous successful applications of graph neural networks (GNNs), theoretical understanding of their generalization ability, especially for node-level tasks where data are not independent and identically-distributed (IID), has been sparse.
Adversarial Attack on Graph Neural Networks as An Influence Maximization Problem
This connection not only enhances our understanding on the problem of adversarial attack on GNNs, but also allows us to propose a group of effective and practical attack strategies.
Pseudo Facial Generation With Extreme Poses for Face Recognition
Many of them settle it by generating fake frontal faces from extreme ones, whereas they are tough to maintain the identity information with high computational consumption and uncontrolled disturbances.
Black-Box Adversarial Attacks on Graph Neural Networks as An Influence Maximization Problem
This connection not only enhances our understanding on the problem of adversarial attack on GNNs, but also allows us to propose a group of effective black-box attack strategies.
CopulaGNN: Towards Integrating Representational and Correlational Roles of Graphs in Graph Neural Networks
In this paper, we distinguish the \textit{representational} and the \textit{correlational} roles played by the graphs in node-level prediction tasks, and we investigate how Graph Neural Network (GNN) models can effectively leverage both types of information.
SODEN: A Scalable Continuous-Time Survival Model through Ordinary Differential Equation Networks
In this paper, we propose a flexible model for survival analysis using neural networks along with scalable optimization algorithms.
Learning-to-Rank with Partitioned Preference: Fast Estimation for the Plackett-Luce Model
We investigate the Plackett-Luce (PL) model based listwise learning-to-rank (LTR) on data with partitioned preference, where a set of items are sliced into ordered and disjoint partitions, but the ranking of items within a partition is unknown.
Towards More Practical Adversarial Attacks on Graph Neural Networks
Our theoretical and empirical analyses suggest that there is a discrepancy between the loss and mis-classification rate, as the latter presents a diminishing-return pattern when the number of attacked nodes increases.
Graph Representation Learning via Multi-task Knowledge Distillation
In this work, we demonstrate that, if available, the domain expertise used for designing handcraft graph features can improve the graph-level representation learning when training labels are scarce.
A Flexible Generative Framework for Graph-based Semi-supervised Learning
In this work, we propose a flexible generative framework for graph-based semi-supervised learning, which approaches the joint distribution of the node features, labels, and the graph structure.
Measuring Human Perception to Improve Handwritten Document Transcription
The subtleties of human perception, as measured by vision scientists through the use of psychophysics, are important clues to the internal workings of visual recognition.
Modeling Task Relationships in Multi-task Learning with Multi-gate Mixture-of-Experts
In this work, we propose a novel multi-task learning approach, Multi-gate Mixture-of-Experts (MMoE), which explicitly learns to model task relationships from data.
DeepCas: an End-to-end Predictor of Information Cascades
While many believe that they are inherently unpredictable, recent work has shown that some key properties of information cascades, such as size, growth, and shape, can be predicted by a machine learning algorithm that combines many features.
