Search Results for author:
Found 241 papers, 72 papers with code
Modeling Hierarchical Syntax Structure with Triplet Position for Source Code Summarization
In this paper, we propose CODESCRIBE to model the hierarchical syntax structure of code by introducing a novel triplet position for code summarization.
Privacy Protection Against Personalized Text-to-Image Synthesis via Cross-image Consistency Constraints
The rapid advancement of diffusion models and personalization techniques has made it possible to recreate individual portraits from just a few publicly available images.
Driving-RAG: Driving Scenarios Embedding, Search, and RAG Applications
Driving scenario data play an increasingly vital role in the development of intelligent vehicles and autonomous driving.
JailDAM: Jailbreak Detection with Adaptive Memory for Vision-Language Model
Multimodal large language models (MLLMs) excel in vision-language tasks but also pose significant risks of generating harmful content, particularly through jailbreak attacks.
Towards Understanding the Optimization Mechanisms in Deep Learning
In this paper, we adopt a probability distribution estimation perspective to explore the optimization mechanisms of supervised classification using deep neural networks.
Multi-Scale Invertible Neural Network for Wide-Range Variable-Rate Learned Image Compression
Autoencoder-based structures have dominated recent learned image compression methods.
Equivariant Image Modeling
Current generative models, such as autoregressive and diffusion approaches, decompose high-dimensional data distribution learning into a series of simpler subtasks.
Voxel-based Point Cloud Geometry Compression with Space-to-Channel Context
To overcome this issue, we introduce a stage-wise Space-to-Channel (S2C) context model for both dense point clouds and low-level sparse point clouds.
A Survey on Federated Fine-tuning of Large Language Models
Large Language Models (LLMs) have achieved remarkable success across a wide range of tasks, with fine-tuning playing a pivotal role in adapting them to specific downstream applications.
A Survey on Knowledge-Oriented Retrieval-Augmented Generation
Retrieval-Augmented Generation (RAG) has gained significant attention in recent years for its potential to enhance natural language understanding and generation by combining large-scale retrieval systems with generative models.
Treble Counterfactual VLMs: A Causal Approach to Hallucination
To address this, we construct a causal graph for VLMs and employ counterfactual analysis to estimate the Natural Direct Effect (NDE) of vision, text, and their cross-modal interaction on the output.
Dur360BEV: A Real-world 360-degree Single Camera Dataset and Benchmark for Bird-Eye View Mapping in Autonomous Driving
We present Dur360BEV, a novel spherical camera autonomous driving dataset equipped with a high-resolution 128-channel 3D LiDAR and a RTK-refined GNSS/INS system, along with a benchmark architecture designed to generate Bird-Eye-View (BEV) maps using only a single spherical camera.
AsymLoRA: Harmonizing Data Conflicts and Commonalities in MLLMs
Effective instruction fine-tuning on diverse image-text datasets is crucial for developing a versatile Multimodal Large Language Model (MLLM), where dataset composition dictates the model's adaptability across multimodal tasks.
Towards Seamless Hierarchical Federated Learning under Intermittent Client Participation: A Stagewise Decision-Making Methodology
Current research on HFL mainly focus on enhancing model accuracy, latency, and energy consumption in scenarios with a stable/fixed set of clients.
EICopilot: Search and Explore Enterprise Information over Large-scale Knowledge Graphs with LLM-driven Agents
The paper introduces EICopilot, an novel agent-based solution enhancing search and exploration of enterprise registration data within extensive online knowledge graphs like those detailing legal entities, registered capital, and major shareholders.
Sparse Point Clouds Assisted Learned Image Compression
In this paper, motivated by the recent success of learned image compression, we propose a new framework that uses sparse point clouds to assist in learned image compression in the autonomous driving scenario.
Comprehensive Survey on Adversarial Examples in Cybersecurity: Impacts, Challenges, and Mitigation Strategies
This paper provides a comprehensive review of the impact of AE attacks on key cybersecurity applications, highlighting both their theoretical and practical implications.
Protect Your Secrets: Understanding and Measuring Data Exposure in VSCode Extensions
Recent years have witnessed the emerging trend of extensions in modern Integrated Development Environments (IDEs) like Visual Studio Code (VSCode) that significantly enhance developer productivity.
Multi-Objective Communication Optimization for Temporal Continuity in Dynamic Vehicular Networks
Addressing these challenges, this paper presents a novel temporal-aware multi-objective robust optimization framework, which for the first time formally incorporates temporal continuity into the optimization of dynamic multi-hop VANETs.
Generalized Gaussian Model for Learned Image Compression
Probabilistic models with more parameters, such as the Gaussian mixture models, can fit the distribution of latent variables more precisely, but the corresponding complexity is higher.
Consistency Regularization for Complementary Clothing Recommendations
This paper reports on the development of a Consistency Regularized model for Bayesian Personalized Ranking (CR-BPR), addressing to the drawbacks in existing complementary clothing recommendation methods, namely limited consistency and biased learning caused by diverse feature scale of multi-modal data.
COOD: Concept-based Zero-shot OOD Detection
Existing OOD detection methods struggle to capture the intricate semantic relationships and label co-occurrences inherent in multi-label settings, often requiring large amounts of training data and failing to generalize to unseen label combinations.
Adaptive Genetic Selection based Pinning Control with Asymmetric Coupling for Multi-Network Heterogeneous Vehicular Systems
To alleviate computational load on RSUs and cloud platforms, reduce communication bandwidth requirements, and provide a more stable vehicular network service, this paper proposes an optimized pinning control approach for heterogeneous multi-network vehicular ad-hoc networks (VANETs).
On Deep Learning for Geometric and Semantic Scene Understanding Using On-Vehicle 3D LiDAR
3D LiDAR point cloud data is crucial for scene perception in computer vision, robotics, and autonomous driving.
Enhancing the Traditional Chinese Medicine Capabilities of Large Language Model through Reinforcement Learning from AI Feedback
In this work, we propose a framework to improve the performance of large language models for TCM tasks using only a small amount of data.
Breaking the Memory Wall for Heterogeneous Federated Learning via Model Splitting
In this paper, we propose SmartSplit, a framework that effectively reduces the memory footprint on the device side while guaranteeing the training progress and model accuracy for heterogeneous FL through model splitting. Towards this end, SmartSplit employs a hierarchical structure to adaptively guide the overall training process.
Extended convexity and smoothness and their applications in deep learning
This paper introduces an optimization framework aimed at providing a theoretical foundation for a class of composite optimization problems, particularly those encountered in deep learning.
AI-Based Fully Automatic Analysis of Retinal Vascular Morphology in Pediatric High Myopia
Results: There were 279 (12. 38%) images in normal group and 384 (16. 23%) images in the high myopia group.
Pre-trained Language Model and Knowledge Distillation for Lightweight Sequential Recommendation
The algorithm operates in two stages: in the first stage, we fine-tune the pre-trained language model on the recommendation dataset to transfer the pre-trained knowledge to the recommendation task; in the second stage, we distill the trained language model to transfer the learned knowledge to a lightweight model.
PathSeeker: Exploring LLM Security Vulnerabilities with a Reinforcement Learning-Based Jailbreak Approach
During our manual attempts to perform jailbreak attacks, we found that the vocabulary of the response of the target model gradually became richer and eventually produced harmful responses.
A Survey on Large Language Model-empowered Autonomous Driving
We further analyze the potential limitations and challenges that LLMs may encounter in promoting the development of AD technology.
Scalable Multi-Objective Optimization for Robust Traffic Signal Control in Uncertain Environments
This paper presents a scalable multi-objective optimization approach for robust traffic signal control in dynamic and uncertain urban environments.
Few-Shot Domain Adaptation for Learned Image Compression
Learned image compression (LIC) has achieved state-of-the-art rate-distortion performance, deemed promising for next-generation image compression techniques.
Heterogeneity-Aware Coordination for Federated Learning via Stitching Pre-trained blocks
However, large memory footprint and high energy consumption during the training process excludes the low-end devices from contributing to the global model with their own data, which severely deteriorates the model performance in real-world scenarios.
Large Language Models in Drug Discovery and Development: From Disease Mechanisms to Clinical Trials
The integration of Large Language Models (LLMs) into the drug discovery and development field marks a significant paradigm shift, offering novel methodologies for understanding disease mechanisms, facilitating drug discovery, and optimizing clinical trial processes.
TraIL-Det: Transformation-Invariant Local Feature Networks for 3D LiDAR Object Detection with Unsupervised Pre-Training
3D point clouds are essential for perceiving outdoor scenes, especially within the realm of autonomous driving.
LaneTCA: Enhancing Video Lane Detection with Temporal Context Aggregation
In this work, we propose LaneTCA to bridge the individual video frames and explore how to effectively aggregate the temporal context.
Bi-Directional Deep Contextual Video Compression
In this paper, we introduce a bi-directional deep contextual video compression scheme tailored for B-frames, termed DCVC-B, to improve the compression performance of deep B-frame coding.
GlitchProber: Advancing Effective Detection and Mitigation of Glitch Tokens in Large Language Models
In this work, we aim to enhance the understanding of glitch tokens and propose techniques for their detection and mitigation.
SwinShadow: Shifted Window for Ambiguous Adjacent Shadow Detection
In this case, when the color of the object is similar to that of the shadow, existing methods struggle to achieve accurate detection.
LLM as Runtime Error Handler: A Promising Pathway to Adaptive Self-Healing of Software Systems
Inspired by their remarkable capabilities in understanding and generating code, we propose to deal with the runtime errors in a real-time manner using LLMs.
NVC-1B: A Large Neural Video Coding Model
Based on a small baseline model, we gradually scale up the model sizes of its different coding parts, including the motion encoder-decoder, motion entropy model, contextual encoder-decoder, contextual entropy model, and temporal context mining module, and analyze the influence of model sizes on video compression performance.
CRASH: Crash Recognition and Anticipation System Harnessing with Context-Aware and Temporal Focus Attentions
To capture a wider range of visual cues, we further propose a multi-layer fusion that dynamically computes the temporal dependencies between different scenes and iteratively updates the correlations between different visual features for accurate and timely accident prediction.
When, Where, and What? A Novel Benchmark for Accident Anticipation and Localization with Large Language Models
As autonomous driving systems increasingly become part of daily transportation, the ability to accurately anticipate and mitigate potential traffic accidents is paramount.
Uniformly Accelerated Motion Model for Inter Prediction
To address these issues, we introduce a uniformly accelerated motion model (UAMM) to exploit motion-related elements (velocity, acceleration) of moving objects between the video frames, and further combine them to assist the inter prediction methods to handle the variable motion in the temporal domain.
Building Intelligence Identification System via Large Language Model Watermarking: A Survey and Beyond
Large Language Models (LLMs) are increasingly integrated into diverse industries, posing substantial security risks due to unauthorized replication and misuse.
In-Loop Filtering via Trained Look-Up Tables
Recently, neural network-based in-loop filtering methods achieve remarkable coding gains beyond the capability of advanced video coding standards, which becomes a powerful coding tool candidate for future video coding standards.
RAPiD-Seg: Range-Aware Pointwise Distance Distribution Networks for 3D LiDAR Segmentation
To effectively embed high-dimensional RAPiD features, we propose a double-nested autoencoder structure with a novel class-aware embedding objective to encode high-dimensional features into manageable voxel-wise embeddings.
TVR-Ranking: A Dataset for Ranked Video Moment Retrieval with Imprecise Queries
To facilitate research in RVMR, we develop the TVR-Ranking dataset, based on the raw videos and existing moment annotations provided in the TVR dataset.
Forest2Seq: Revitalizing Order Prior for Sequential Indoor Scene Synthesis
Synthesizing realistic 3D indoor scenes is a challenging task that traditionally relies on manual arrangement and annotation by expert designers.
IVCA: Inter-Relation-Aware Video Complexity Analyzer
To begin with, we improve the accuracy of temporal features by integrating feature-domain motion estimation into the IVCA framework, which allows for a more nuanced understanding of motion across frames.
Prediction and Reference Quality Adaptation for Learned Video Compression
With these filters, our codec can adapt to different reference qualities, making it easier to achieve the target reconstruction quality and reduce the reconstruction error propagation.
DurLAR: A High-fidelity 128-channel LiDAR Dataset with Panoramic Ambient and Reflectivity Imagery for Multi-modal Autonomous Driving Applications
We present DurLAR, a high-fidelity 128-channel 3D LiDAR dataset with panoramic ambient (near infrared) and reflectivity imagery, as well as a sample benchmark task using depth estimation for autonomous driving applications.
Async Learned User Embeddings for Ads Delivery Optimization
In recommendation systems, high-quality user embeddings can capture subtle preferences, enable precise similarity calculations, and adapt to changing preferences over time to maintain relevance.
Towards Federated Domain Unlearning: Verification Methodologies and Challenges
Federated Learning (FL) has evolved as a powerful tool for collaborative model training across multiple entities, ensuring data privacy in sensitive sectors such as healthcare and finance.
An Empirical Study of Training State-of-the-Art LiDAR Segmentation Models
In the rapidly evolving field of autonomous driving, precise segmentation of LiDAR data is crucial for understanding complex 3D environments.
Backpropagation-Free Multi-modal On-Device Model Adaptation via Cloud-Device Collaboration
As these systems grapple with shifting data distributions between the cloud and devices, the traditional approach of fine-tuning-based adaptation (FTA) exists the following issues: the costly and time-consuming data annotation required by FTA and the looming risk of model overfitting.
MGS-SLAM: Monocular Sparse Tracking and Gaussian Mapping with Depth Smooth Regularization
This letter introduces a novel framework for dense Visual Simultaneous Localization and Mapping (VSLAM) based on Gaussian Splatting.
FedGCS: A Generative Framework for Efficient Client Selection in Federated Learning via Gradient-based Optimization
Federated Learning faces significant challenges in statistical and system heterogeneity, along with high energy consumption, necessitating efficient client selection strategies.
Ranking-based Client Selection with Imitation Learning for Efficient Federated Learning
Federated Learning (FL) enables multiple devices to collaboratively train a shared model while ensuring data privacy.
DMOFC: Discrimination Metric-Optimized Feature Compression
To maintain the feature discriminability of reconstructed features, we introduce a discrimination metric for feature compression.
Leverage Multi-source Traffic Demand Data Fusion with Transformer Model for Urban Parking Prediction
The escalation in urban private car ownership has worsened the urban parking predicament, necessitating effective parking availability prediction for urban planning and management.
HydraLoRA: An Asymmetric LoRA Architecture for Efficient Fine-Tuning
Through a series of experiments, we have uncovered two critical insights that shed light on the training and parameter inefficiency of LoRA.
AI Coders Are Among Us: Rethinking Programming Language Grammar Towards Efficient Code Generation
To improve inference efficiency and reduce computational costs, we propose the concept of AI-oriented grammar.
Breaking the Memory Wall for Heterogeneous Federated Learning with Progressive Training
In order to preserve the feature representation of each block, we decouple the whole training process into two stages: progressive model shrinking and progressive model growing.
Open-Source AI-based SE Tools: Opportunities and Challenges of Collaborative Software Learning
We introduce a governance framework centered on federated learning (FL), designed to foster the joint development and maintenance of open-source AI code models while safeguarding data privacy and security.
Object Segmentation-Assisted Inter Prediction for Versatile Video Coding
Moreover, the segmentation mask is considered in the joint rate-distortion optimization for motion estimation and partition estimation to derive the motion vector of different regions and partition more accurately.
Motion-aware 3D Gaussian Splatting for Efficient Dynamic Scene Reconstruction
To address the above problem, we propose a novel motion-aware enhancement framework for dynamic scene reconstruction, which mines useful motion cues from optical flow to improve different paradigms of dynamic 3DGS.
Towards Personalized Evaluation of Large Language Models with An Anonymous Crowd-Sourcing Platform
Through this gateway, users have the opportunity to submit their questions, testing the models on a personalized and potentially broader range of capabilities.
Wavelet-Like Transform-Based Technology in Response to the Call for Proposals on Neural Network-Based Image Coding
Neural network-based image coding has been developing rapidly since its birth.
DLP-GAN: learning to draw modern Chinese landscape photos with generative adversarial network
To solve such problems, in this paper, we (1) propose DLP-GAN (Draw Modern Chinese Landscape Photos with Generative Adversarial Network), an unsupervised cross-domain image translation framework with a novel asymmetric cycle mapping, and (2) introduce a generator based on a dense-fusion module to match different translation directions.
LoRA-as-an-Attack! Piercing LLM Safety Under The Share-and-Play Scenario
Our aim is to raise awareness of the potential risks under the emerging share-and-play scenario, so as to proactively prevent potential consequences caused by LoRA-as-an-Attack.
Instance-aware Exploration-Verification-Exploitation for Instance ImageGoal Navigation
As a new embodied vision task, Instance ImageGoal Navigation (IIN) aims to navigate to a specified object depicted by a goal image in an unexplored environment.
Investigating White-Box Attacks for On-Device Models
Our findings emphasize the need for developers to carefully consider their model deployment strategies, and use white-box methods to evaluate the vulnerability of on-device models.
Spatial Decomposition and Temporal Fusion based Inter Prediction for Learned Video Compression
With the SDD-based motion model and long short-term temporal contexts fusion, our proposed learned video codec can obtain more accurate inter prediction.
PL-FSCIL: Harnessing the Power of Prompts for Few-Shot Class-Incremental Learning
In this paper, we propose a novel approach called Prompt Learning for FSCIL (PL-FSCIL), which harnesses the power of prompts in conjunction with a pre-trained Vision Transformer (ViT) model to address the challenges of FSCIL effectively.
class-incremental learning
Few-Shot Class-Incremental Learning
+2
Shift-ConvNets: Small Convolutional Kernel with Large Kernel Effects
Experimental results show that our shift-wise operator significantly improves the accuracy of a regular CNN while markedly reducing computational requirements.
When Neural Code Completion Models Size up the Situation: Attaining Cheaper and Faster Completion through Dynamic Model Inference
These findings motivate our exploration of dynamic inference in code completion and inspire us to enhance it with a decision-making mechanism that stops the generation of incorrect code.
Multi-objective Optimal Roadside Units Deployment in Urban Vehicular Networks
Therefore, the deployment of RSUs is of utmost importance in ensuring the quality of communication services.
DarkShot: Lighting Dark Images with Low-Compute and High-Quality
This paper proposes a lightweight network that outperforms existing state-of-the-art (SOTA) methods in low-light enhancement tasks while minimizing computation.
How to Configure Good In-Context Sequence for Visual Question Answering
Inspired by the success of Large Language Models in dealing with new tasks via In-Context Learning (ICL) in NLP, researchers have also developed Large Vision-Language Models (LVLMs) with ICL capabilities.
Progressive Recurrent Network for Shadow Removal
To handle this issue, we consider removing the shadow in a coarse-to-fine fashion and propose a simple but effective Progressive Recurrent Network (PRNet).
Pitfalls in Language Models for Code Intelligence: A Taxonomy and Survey
After carefully examining these studies, we designed a taxonomy of pitfalls in LM4Code research and conducted a systematic study to summarize the issues, implications, current solutions, and challenges of different pitfalls for LM4Code systems.
Domain-wise Invariant Learning for Panoptic Scene Graph Generation
Panoptic Scene Graph Generation (PSG) involves the detection of objects and the prediction of their corresponding relationships (predicates).
Towards Complex-query Referring Image Segmentation: A Novel Benchmark
Referring Image Understanding (RIS) has been extensively studied over the past decade, leading to the development of advanced algorithms.
On Uniform Scalar Quantization for Learned Image Compression
In principle, we find two factors crucial: one is the discrepancy between the surrogate and rounding, leading to train-test mismatch; the other is gradient estimation risk due to the surrogate, which consists of bias and variance of the gradient estimation.
Forecasting large collections of time series: feature-based methods
In economics and many other forecasting domains, the real world problems are too complex for a single model that assumes a specific data generation process.
Pop Quiz! Do Pre-trained Code Models Possess Knowledge of Correct API Names?
The correctness and unambiguity of API usage among these code models are crucial for achieving desirable program functionalities, requiring them to learn various API fully qualified names structurally and semantically.
A boundary-aware point clustering approach in Euclidean and embedding spaces for roof plane segmentation
To solve this problem, we propose a boundary-aware point clustering approach in Euclidean and embedding spaces constructed by a multi-task deep network for roof plane segmentation.
CodeMark: Imperceptible Watermarking for Code Datasets against Neural Code Completion Models
Even worse, the ``black-box'' nature of neural models sets a high barrier for externals to audit their training datasets, which further connives these unauthorized usages.
Learning Cyber Defence Tactics from Scratch with Multi-Agent Reinforcement Learning
Recent advancements in deep learning techniques have opened new possibilities for designing solutions for autonomous cyber defence.
Large Language Models for Software Engineering: A Systematic Literature Review
Nevertheless, a comprehensive understanding of the application, effects, and possible limitations of LLMs on SE is still in its early stages.
Causal SAR ATR with Limited Data via Dual Invariance
As a result, it has a detrimental causal effect damaging the efficacy of feature $X$ extracted from SAR images, leading to weak generalization of SAR ATR with limited data.
SimFIR: A Simple Framework for Fisheye Image Rectification with Self-supervised Representation Learning
To make the best of such rectification cues, we introduce SimFIR, a simple framework for fisheye image rectification based on self-supervised representation learning.
Cyclic-Bootstrap Labeling for Weakly Supervised Object Detection
These inaccurate high-scoring region proposals will mislead the training of subsequent refinement modules and thus hamper the detection performance.
Deep Semantic Graph Matching for Large-scale Outdoor Point Clouds Registration
The adjacent points with the same category labels are then clustered together using the Euclidean clustering algorithm to obtain the semantic instances, which are represented by three kinds of attributes including spatial location information, semantic categorical information, and global geometric shape information.
Exploiting Spatial-Temporal Context for Interacting Hand Reconstruction on Monocular RGB Video
Reconstructing interacting hands from monocular RGB data is a challenging task, as it involves many interfering factors, e. g. self- and mutual occlusion and similar textures.
Efficient Temporal Sentence Grounding in Videos with Multi-Teacher Knowledge Distillation
To tackle this problem, we propose a novel efficient multi-teacher model (EMTM) based on knowledge distillation to transfer diverse knowledge from both heterogeneous and isomorphic networks.
Panoptic Scene Graph Generation with Semantics-Prototype Learning
To promise consistency and accuracy during the transfer process, we propose to measure the invariance of representations in each predicate class, and learn unbiased prototypes of predicates with different intensities.
Ranked #3 on
Panoptic Scene Graph Generation
on PSG Dataset
HTP: Exploiting Holistic Temporal Patterns for Sequential Recommendation
In this paper, we systematically investigate various temporal information for sequential recommendation and identify three types of advantageous temporal patterns beyond order, including absolute time information, relative item time intervals and relative recommendation time intervals.
IR Design for Application-Specific Natural Language: A Case Study on Traffic Data
In the realm of software applications in the transportation industry, Domain-Specific Languages (DSLs) have enjoyed widespread adoption due to their ease of use and various other benefits.
Offline and Online Optical Flow Enhancement for Deep Video Compression
In the offline stage, we fine-tune a trained optical flow estimation network with the motion information provided by a traditional (non-deep) video compression scheme, e. g. H. 266/VVC, as we believe the motion information of H. 266/VVC achieves a better rate-distortion trade-off.
Spatio-Temporal Classification of Lung Ventilation Patterns using 3D EIT Images: A General Approach for Individualized Lung Function Evaluation
A simple convolutional neural network is used for classification.
VNVC: A Versatile Neural Video Coding Framework for Efficient Human-Machine Vision
Such compact representations need to be decoded back to pixels before being displayed to humans and - as usual - before being enhanced/analyzed by machine vision algorithms.
Breaking On-device Training Memory Wall: A Systematic Survey
In this systematic survey, we aim to explore the current state-of-the-art techniques for breaking on-device training memory walls, focusing on methods that can enable larger and more complex models to be trained on resource-constrained devices.
Enlarging Stability Region of Urban Networks with Imminent Supply Prediction
Urban traffic network is such a system.
Source Code Data Augmentation for Deep Learning: A Survey
This paper fills this gap by conducting a comprehensive and integrative survey of data augmentation for source code, wherein we systematically compile and encapsulate existing literature to provide a comprehensive overview of the field.
Continuous and Noninvasive Measurement of Arterial Pulse Pressure and Pressure Waveform using an Image-free Ultrasound System
In in vitro cardiovascular phantom experiments, the results demonstrated high accuracy in the measurement of PP (error < 3 mmHg) and blood pressure waveform (root-mean-square-errors (RMSE) < 2 mmHg, correlation coefficient (r) > textgreater 0. 99).
An Efficient Safety-oriented Car-following Model for Connected Automated Vehicles Considering Discrete Signals
This paper proposes an efficient safety-oriented car-following model for CAVs considering the impact of discrete signals.
AdaptGear: Accelerating GNN Training via Adaptive Subgraph-Level Kernels on GPUs
Graph neural networks (GNNs) are powerful tools for exploring and learning from graph structures and features.
TransWorldNG: Traffic Simulation via Foundation Model
To the best of our knowledge, this is the first traffic simulator that can automatically learn traffic patterns from real-world data and efficiently generate accurate and realistic traffic environments.
Editable Graph Neural Network for Node Classifications
However, model editing for graph neural networks (GNNs) is rarely explored, despite GNNs' widespread applicability.
LMs: Understanding Code Syntax and Semantics for Code Analysis
We break down the abilities needed for artificial intelligence~(AI) models to address SE tasks related to code analysis into three categories: 1) syntax understanding, 2) static behavior understanding, and 3) dynamic behavior understanding.
Milestones in Autonomous Driving and Intelligent Vehicles Part I: Control, Computing System Design, Communication, HD Map, Testing, and Human Behaviors
Our work is divided into 3 independent articles and the first part is a Survey of Surveys (SoS) for total technologies of AD and IVs that involves the history, summarizes the milestones, and provides the perspectives, ethics, and future research directions.
VPGTrans: Transfer Visual Prompt Generator across LLMs
While developing a new multimodal LLM (MLLM) by pre-training on tremendous image-text pairs from scratch can be exceedingly resource-consuming, connecting an existing LLM with a comparatively lightweight visual prompt generator (VPG) becomes a feasible paradigm.
Enabling A Network AI Gym for Autonomous Cyber Agents
This work aims to enable autonomous agents for network cyber operations (CyOps) by applying reinforcement and deep reinforcement learning (RL/DRL).
Unified Emulation-Simulation Training Environment for Autonomous Cyber Agents
This work presents a systematic solution to automatically generate a high-fidelity simulator in the Cyber Gym for Intelligent Learning (CyGIL).
A Multiagent CyberBattleSim for RL Cyber Operation Agents
In particular, training a blue agent jointly with a red agent increases the blue agent's capability to thwart sophisticated red agents.
Milestones in Autonomous Driving and Intelligent Vehicles: Survey of Surveys
Interest in autonomous driving (AD) and intelligent vehicles (IVs) is growing at a rapid pace due to the convenience, safety, and economic benefits.
HandNeRF: Neural Radiance Fields for Animatable Interacting Hands
We propose a novel framework to reconstruct accurate appearance and geometry with neural radiance fields (NeRF) for interacting hands, enabling the rendering of photo-realistic images and videos for gesture animation from arbitrary views.
Less is More: Reducing Task and Model Complexity for 3D Point Cloud Semantic Segmentation
Whilst the availability of 3D LiDAR point cloud data has significantly grown in recent years, annotation remains expensive and time-consuming, leading to a demand for semi-supervised semantic segmentation methods with application domains such as autonomous driving.
Ranked #1 on
3D Semantic Segmentation
on ScribbleKITTI
(mIoU-1% metric)
An Adaptive Plug-and-Play Network for Few-Shot Learning
Few-shot learning (FSL) requires a model to classify new samples after learning from only a few samples.
Denoising and Prompt-Tuning for Multi-Behavior Recommendation
In practical recommendation scenarios, users often interact with items under multi-typed behaviors (e. g., click, add-to-cart, and purchase).
Differentiable modeling to unify machine learning and physical models and advance Geosciences
Here we present differentiable geoscientific modeling as a powerful pathway toward dissolving the perceived barrier between them and ushering in a paradigm shift.
Neural Characteristic Function Learning for Conditional Image Generation
The emergence of conditional generative adversarial networks (cGANs) has revolutionised the way we approach and control the generation, by means of adversarially learning joint distributions of data and auxiliary information.
Bring Your Own View: Graph Neural Networks for Link Prediction with Personalized Subgraph Selection
To bridge the gap, we introduce a Personalized Subgraph Selector (PS2) as a plug-and-play framework to automatically, personally, and inductively identify optimal subgraphs for different edges when performing GNNLP.
CLIP2GAN: Towards Bridging Text with the Latent Space of GANs
The key idea of our CLIP2GAN is to bridge the output feature embedding space of CLIP and the input latent space of StyleGAN, which is realized by introducing a mapping network.
Coordinating CAV Swarms at Intersections with a Deep Learning Model
Connected and automated vehicles (CAVs) are viewed as a special kind of robots that have the potential to significantly improve the safety and efficiency of traffic.
Phonetic-assisted Multi-Target Units Modeling for Improving Conformer-Transducer ASR system
Exploiting effective target modeling units is very important and has always been a concern in end-to-end automatic speech recognition (ASR).
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
DeepMLE: A Robust Deep Maximum Likelihood Estimator for Two-view Structure from Motion
In addition, in order to increase the robustness of our framework, we formulate the likelihood function of the correlations of 2D image matches as a Gaussian and Uniform mixture distribution which takes the uncertainty caused by illumination changes, image noise and moving objects into account.
Don't Complete It! Preventing Unhelpful Code Completion for Productive and Sustainable Neural Code Completion Systems
To fill this significant gap, we first investigate the prompts of unhelpful code completions, called "low-return prompts".
Improved Fuzzy $H_{\infty}$ Filter Design Method for Nonlinear Systems with Time-Varing Delay
This paper investigates the fuzzy $H_{\infty}$ filter design issue for nonlinear systems with time-varying delay.
A New Fuzzy $H_{\infty}$ Filter Design for Nonlinear Time-Delay Systems with Mismatched Premise Membership Functions
This paper is concerned with the fuzzy $H_{\infty}$ filter design issue for nonlinear systems with time-varying delay.
Energy Minimization in RIS-Assisted UAV-Enabled Wireless Power Transfer Systems
Then, we investigate the general scenario in which the RF signals are radiated during the flight, aiming to minimize the total energy consumption of the UAV by jointly optimizing the UAV's trajectory, flight time and the RIS's reflection coefficients.
Towards Hybrid-Optimization Video Coding
Our idea is to provide multiple discrete starting points in the global space and optimize the local optimum around each point by numerical algorithm efficiently.
Piecewise Linear Neural Networks and Deep Learning
To apply PWLNN methods, both the representation and the learning have long been studied.
CODE-MVP: Learning to Represent Source Code from Multiple Views with Contrastive Pre-Training
Specifically, we first extract multiple code views using compiler tools, and learn the complementary information among them under a contrastive learning framework.
Multiple EffNet/ResNet Architectures for Melanoma Classification
Melanoma is the most malignant skin tumor and usually cancerates from normal moles, which is difficult to distinguish benign from malignant in the early stage.
Image Captioning In the Transformer Age
This drawback inspires the researchers to develop a homogeneous architecture that facilitates end-to-end training, for which Transformer is the perfect one that has proven its huge potential in both vision and language domains and thus can be used as the basic component of the visual encoder and language decoder in an IC pipeline.
FedDC: Federated Learning with Non-IID Data via Local Drift Decoupling and Correction
Federated learning (FL) allows multiple clients to collectively train a high-performance global model without sharing their private data.
aiWave: Volumetric Image Compression with 3-D Trained Affine Wavelet-like Transform
Volumetric image compression has become an urgent task to effectively transmit and store images produced in biological research and clinical practice.
Evolving symbolic density functionals
Systematic development of accurate density functionals has been a decades-long challenge for scientists.
On the Importance of Building High-quality Training Datasets for Neural Code Search
The performance of neural code search is significantly influenced by the quality of the training data from which the neural models are derived.
Autonomous Driving on Curvy Roads Without Reliance on Frenet Frame: A Cartesian-Based Trajectory Planning Method
This paper is focused on the trajectory planning task for autonomous driving on a curvy road.
Towards understanding retrosynthesis by energy-based models
In this paper, we propose a framework that unifies sequence- and graph-based methods as energy-based models (EBMs) with different energy functions.
Attribute Artifacts Removal for Geometry-based Point Cloud Compression
In this paper, we propose a Multi-Scale Graph Attention Network (MS-GAT) to remove the artifacts of point cloud attributes compressed by G-PCC.
Temporal Context Mining for Learned Video Compression
From the stored propagated features, we propose to learn multi-scale temporal contexts, and re-fill the learned temporal contexts into the modules of our compression scheme, including the contextual encoder-decoder, the frame generator, and the temporal context encoder.
Distributed Policy Gradient with Variance Reduction in Multi-Agent Reinforcement Learning
This paper studies a distributed policy gradient in collaborative multi-agent reinforcement learning (MARL), where agents over a communication network aim to find the optimal policy to maximize the average of all agents' local returns.
Multi-agent Reinforcement Learning
reinforcement-learning
+2
MFNet: Multi-class Few-shot Segmentation Network with Pixel-wise Metric Learning
Last, to enhance the embedding space learning, an additional pixel-wise metric learning module is introduced with triplet loss formulated on the pixel-level embedding of the input image.
How Well Does Kohn-Sham Regularizer Work for Weakly Correlated Systems?
Kohn-Sham regularizer (KSR) is a differentiable machine learning approach to finding the exchange-correlation functional in Kohn-Sham density functional theory (DFT) that works for strongly correlated systems.
CoProtector: Protect Open-Source Code against Unauthorized Training Usage with Data Poisoning
Github Copilot, trained on billions of lines of public code, has recently become the buzzword in the computer science research and practice community.
End-to-End Image Compression with Probabilistic Decoding
However, this nature was seldom considered in previous studies on image compression, which usually chose one possible image as reconstruction, e. g. the one with the maximal a posteriori probability.
An Information Fusion Approach to Learning with Instance-Dependent Label Noise
Instance-dependent label noise (IDN) widely exists in real-world datasets and usually misleads the training of deep neural networks.
EXACT: Scalable Graph Neural Networks Training via Extreme Activation Compression
Based on the implementation, we propose a memory-efficient framework called ``EXACT'', which for the first time demonstrate the potential and evaluate the feasibility of training GNNs with compressed activations.
FedDrop: Trajectory-weighted Dropout for Efficient Federated Learning
Federated learning (FL) enables edge clients to train collaboratively while preserving individual's data privacy.
iWave3D: End-to-end Brain Image Compression with Trainable 3-D Wavelet Transform
With the rapid development of whole brain imaging technology, a large number of brain images have been produced, which puts forward a great demand for efficient brain image compression methods.
CyGIL: A Cyber Gym for Training Autonomous Agents over Emulated Network Systems
Given the success of reinforcement learning (RL) in various domains, it is promising to explore the application of its methods to the development of intelligent and autonomous cyber agents.
On Faster Convergence of Scaled Sign Gradient Descent
For the first two cases, it can be shown that the scaled signGD converges at a linear rate.
Adaptive Label Smoothing To Regularize Large-Scale Graph Training
Graph neural networks (GNNs), which learn the node representations by recursively aggregating information from its neighbors, have become a predominant computational tool in many domains.
SynCoBERT: Syntax-Guided Multi-Modal Contrastive Pre-Training for Code Representation
Code representation learning, which aims to encode the semantics of source code into distributed vectors, plays an important role in recent deep-learning-based models for code intelligence.
Bayesian forecast combination using time-varying features
In this work, we propose a novel framework for density forecast combination by constructing time-varying weights based on time series features, which is called Feature-based Bayesian Forecasting Model Averaging (FEBAMA).
Fast and Accurate Neural Machine Translation with Translation Memory
It is generally believed that a translation memory (TM) should be beneficial for machine translation tasks.
Dirichlet Energy Constrained Learning for Deep Graph Neural Networks
To this end, we analyze the bottleneck of deep GNNs by leveraging the Dirichlet energy of node embeddings, and propose a generalizable principle to guide the training of deep GNNs.
Federated Noisy Client Learning
Federated learning (FL) collaboratively trains a shared global model depending on multiple local clients, while keeping the training data decentralized in order to preserve data privacy.
Composition and Application of Current Advanced Driving Assistance System: A Review
Due to the growing awareness of driving safety and the development of sophisticated technologies, advanced driving assistance system (ADAS) has been equipped in more and more vehicles with higher accuracy and lower price.
Learning Graph Meta Embeddings for Cold-Start Ads in Click-Through Rate Prediction
For existing old ads, GMEs first build a graph to connect them with new ads, and then adaptively distill useful information.
Drill the Cork of Information Bottleneck by Inputting the Most Important Data
As a promising tool to better understand the learning dynamic of minibatch SGD, the information bottleneck (IB) theory claims that the optimization process consists of an initial fitting phase and the following compression phase.
Unsupervised domain adaptation via double classifiers based on high confidence pseudo label
In addition to aligning the global distribution, the real domain adaptation should also align the meso distribution and the micro distribution.
Performance Evaluation of Adversarial Attacks: Discrepancies and Solutions
Recently, adversarial attack methods have been developed to challenge the robustness of machine learning models.
Distributed Cooperative Driving in Multi-Intersection Road Networks
Cooperative driving at isolated intersections attracted great interest and had been well discussed in recent years.
CSAFL: A Clustered Semi-Asynchronous Federated Learning Framework
Asynchronous FL has a natural advantage in mitigating the straggler effect, but there are threats of model quality degradation and server crash.
FedSAE: A Novel Self-Adaptive Federated Learning Framework in Heterogeneous Systems
In our framework, the server evaluates devices' value of training based on their training loss.
The SARAS Endoscopic Surgeon Action Detection (ESAD) dataset: Challenges and methods
For an autonomous robotic system, monitoring surgeon actions and assisting the main surgeon during a procedure can be very challenging.
Density-aware Haze Image Synthesis by Self-Supervised Content-Style Disentanglement
The key procedure of haze image translation through adversarial training lies in the disentanglement between the feature only involved in haze synthesis, i. e. style feature, and the feature representing the invariant semantic content, i. e. content feature.
Deep Learning for Android Malware Defenses: a Systematic Literature Review
In this paper, we conducted a systematic literature review to search and analyze how deep learning approaches have been applied in the context of malware defenses in the Android environment.
Restoring Execution Environments of Jupyter Notebooks
More than ninety percent of published Jupyter notebooks do not state dependencies on external packages.
Software Engineering
Distributed quantum phase estimation with entangled photons
Distributed quantum metrology can enhance the sensitivity for sensing spatially distributed parameters beyond the classical limits.
Quantum Physics
DEAL: Decremental Energy-Aware Learning in a Federated System
To address the conflict between learning SLO and energy efficiency, we propose DEAL, an energy efficient learning system that saves energy and preserves privacy with a decremental learning design.
A 3D Non-stationary MmWave Channel Model for Vacuum Tube Ultra-High-Speed Train Channels
As a potential development direction of future transportation, the vacuum tube ultra-high-speed train (UHST) wireless communication systems have newly different channel characteristics from existing high-speed train (HST) scenarios.
Offline Meta-level Model-based Reinforcement Learning Approach for Cold-Start Recommendation
To improve adaptation efficiency, we learn to recover the user policy and reward from only a few interactions via an inverse reinforcement learning method to assist a meta-level recommendation agent.
Model-based Reinforcement Learning
Recommendation Systems
+3
Learnability and Complexity of Quantum Samples
Given a quantum circuit, a quantum computer can sample the output distribution exponentially faster in the number of bits than classical computers.
Kohn-Sham equations as regularizer: building prior knowledge into machine-learned physics
Including prior knowledge is important for effective machine learning models in physics, and is usually achieved by explicitly adding loss terms or constraints on model architectures.
Explainable Recommender Systems via Resolving Learning Representations
Different from previous work, in our model, factor discovery and representation learning are simultaneously conducted, and we are able to handle extra attribute information and knowledge.
Defending Adversarial Examples via DNN Bottleneck Reinforcement
This paper presents a DNN bottleneck reinforcement scheme to alleviate the vulnerability of Deep Neural Networks (DNN) against adversarial attacks.
Energy-based View of Retrosynthesis
Retrosynthesis -- the process of identifying a set of reactants to synthesize a target molecule -- is of vital importance to material design and drug discovery.
Ranked #5 on
Single-step retrosynthesis
on USPTO-50k
Active Crowd Counting with Limited Supervision
To learn a reliable people counter from crowd images, head center annotations are normally required.
Scaling Symbolic Methods using Gradients for Neural Model Explanation
In this work, we propose a technique for combining gradient-based methods with symbolic techniques to scale such analyses and demonstrate its application for model explanation.
A Real-Time Dispatching Strategy for Shared Automated Electric Vehicles with Performance Guarantees
To overcome this complexity, we employ an online minimum drift plus penalty (MDPP) approach for SAEV systems that (i) does not require a priori knowledge of customer arrival rates to the different parts of the system (i. e. it is practical from a real-world deployment perspective), (ii) ensures the stability of customer waiting times, (iii) ensures that the deviation of dispatch costs from a desirable dispatch cost can be controlled, and (iv) has a computational time-complexity that allows for real-time implementation.
A New Modal Autoencoder for Functionally Independent Feature Extraction
Autoencoders have been widely used for dimensional reduction and feature extraction.
Multiuser Full-Duplex Two-Way Communications via Intelligent Reflecting Surface
Low-cost passive intelligent reflecting surfaces (IRSs) have recently been envisioned as a revolutionary technology capable of reconfiguring the wireless propagation environment through carefully tuning reflection elements.
Ontology-based systematic classification and analysis of coronaviruses, hosts, and host-coronavirus interactions towards deep understanding of COVID-19
We hypothesized that ontology can be used as an integrative platform to classify and analyze HCI and disease outcomes.
Other Quantitative Biology
Investigating Quantum Approximate Optimization Algorithms under Bang-bang Protocols
The quantum approximate optimization algorithm (QAOA) is widely seen as a possible usage of noisy intermediate-scale quantum (NISQ) devices.
Quantum Physics
A Framework for Behavioral Biometric Authentication using Deep Metric Learning on Mobile Devices
We show the feasibility of training with mobile CPUs, where training 100 epochs takes less than 10 mins and can be boosted 3-5 times with feature transfer.
Warwick Image Forensics Dataset for Device Fingerprinting In Multimedia Forensics
Device fingerprints like sensor pattern noise (SPN) are widely used for provenance analysis and image authentication.
Incorporating Multiple Cluster Centers for Multi-Label Learning
In this article, we propose to leverage the data augmentation technique to improve the performance of multi-label learning.
Vanishing Point Guided Natural Image Stitching
Recently, works on improving the naturalness of stitching images gain more and more extensive attention.
Developing Multi-Task Recommendations with Long-Term Rewards via Policy Distilled Reinforcement Learning
With the explosive growth of online products and content, recommendation techniques have been considered as an effective tool to overcome information overload, improve user experience, and boost business revenue.
Software tools for quantum control: Improving quantum computer performance through noise and error suppression
Manipulating quantum computing hardware in the presence of imperfect devices and control systems is a central challenge in realizing useful quantum computers.
Quantum Physics
