Search Results for author:
Found 100 papers, 27 papers with code
Inconsistency Matters: A Knowledge-guided Dual-inconsistency Network for Multi-modal Rumor Detection
Rumor spreaders are increasingly utilizing multimedia content to attract the attention and trust of news consumers.
Navigating the Black Box: Leveraging LLMs for Effective Text-Level Graph Injection Attacks
This method efficiently perturbs the target node with minimal training costs in a strict black-box setting, ensuring a text-level graph injection attack for TAGs.
Structured Labeling Enables Faster Vision-Language Models for End-to-End Autonomous Driving
In contrast to existing VLMs with over 7B parameters and unstructured language processing(e. g., LLaVA-1. 5), FastDrive understands structured and concise descriptions and generates machine-friendly driving decisions with high efficiency.
Look Before You Leap: A GUI-Critic-R1 Model for Pre-Operative Error Diagnosis in GUI Automation
In recent years, Multimodal Large Language Models (MLLMs) have been extensively utilized for multimodal reasoning tasks, including Graphical User Interface (GUI) automation.
Hadaptive-Net: Efficient Vision Models via Adaptive Cross-Hadamard Synergy
Recent studies have revealed the immense potential of Hadamard product in enhancing network representational capacity and dimensional compression.
3DGS Compression with Sparsity-guided Hierarchical Transform Coding
3D Gaussian Splatting (3DGS) has gained popularity for its fast and high-quality rendering, but it has a very large memory footprint incurring high transmission and storage overhead.
CogniBench: A Legal-inspired Framework and Dataset for Assessing Cognitive Faithfulness of Large Language Models
Faithfulness hallucinations are claims generated by a Large Language Model (LLM) not supported by contexts provided to the LLM.
Mobile-Agent-V: A Video-Guided Approach for Effortless and Efficient Operational Knowledge Injection in Mobile Automation
The exponential rise in mobile device usage necessitates streamlined automation for effective task management, yet many AI frameworks fall short due to inadequate operational expertise.
MirrorShield: Towards Universal Defense Against Jailbreaks via Entropy-Guided Mirror Crafting
Defending large language models (LLMs) against jailbreak attacks is crucial for ensuring their safe deployment.
Composite Nonlinear Trajectory Tracking Control of Co-Driving Vehicles Using Self-Triggered Adaptive Dynamic Programming
This article presents a composite nonlinear feedback (CNF) control method using self-triggered (ST) adaptive dynamic programming (ADP) algorithm in a human-machine shared steering framework.
Mobile-Agent-V: Learning Mobile Device Operation Through Video-Guided Multi-Agent Collaboration
The rapid increase in mobile device usage necessitates improved automation for seamless task management.
PC-Agent: A Hierarchical Multi-Agent Collaboration Framework for Complex Task Automation on PC
From the decision-making perspective, to handle complex user instructions and interdependent subtasks more effectively, we propose a hierarchical multi-agent collaboration architecture that decomposes decision-making processes into Instruction-Subtask-Action levels.
Qwen2.5-VL Technical Report
We introduce Qwen2. 5-VL, the latest flagship model of Qwen vision-language series, which demonstrates significant advancements in both foundational capabilities and innovative functionalities.
Ranked #2 on
Visual Question Answering (VQA)
on VLM2-Bench
Data-driven Super-Resolution of Flood Inundation Maps using Synthetic Simulations
The frequency of extreme flood events is increasing throughout the world.
SCCD: A Session-based Dataset for Chinese Cyberbullying Detection
The rampant spread of cyberbullying content poses a growing threat to societal well-being.
Mobile-Agent-E: Self-Evolving Mobile Assistant for Complex Tasks
By hierarchical, we mean an explicit separation of high-level planning and low-level action execution.
Analyzing the Role of the DSO in Electricity Trading of VPPs via a Stackelberg Game Model
In order to study the role of DSO as a stakeholder, a Stackelberg game is represented via a bi-level model: the DSO maximizes profits at the upper level, while the VPPs minimize operating costs at the lower level.
Multirate Neural Image Compression with Adaptive Lattice Vector Quantization
Recent research has explored integrating lattice vector quantization (LVQ) into learned image compression models.
Gla-AI4BioMed at RRG24: Visual Instruction-tuned Adaptation for Radiology Report Generation
We introduce a radiology-focused visual language model designed to generate radiology reports from chest X-rays.
TSUBF-Net: Trans-Spatial UNet-like Network with Bi-direction Fusion for Segmentation of Adenoid Hypertrophy in CT
The results in the other two public datasets also demonstrate that our methods can robustly and effectively address the challenges of 3D segmentation in CT scans.
Libra: Leveraging Temporal Images for Biomedical Radiology Analysis
Radiology report generation (RRG) is a challenging task, as it requires a thorough understanding of medical images, integration of multiple temporal inputs, and accurate report generation.
Learning Optimal Lattice Vector Quantizers for End-to-end Neural Image Compression
It is customary to deploy uniform scalar quantization in the end-to-end optimized Neural image compression methods, instead of more powerful vector quantization, due to the high complexity of the latter.
Development of a Comprehensive Physics-Based Battery Model and Its Multidimensional Comparison with an Equivalent-Circuit Model: Accuracy, Complexity, and Real-World Performance under Varying Conditions
This paper develops a comprehensive physics-based model (PBM) that spans a wide operational range, including varying temperatures, charge/discharge conditions, and real-world field data cycles.
Trajectory Flow Matching with Applications to Clinical Time Series Modeling
To address this, we propose Trajectory Flow Matching (TFM), which trains a Neural SDE in a simulation-free manner, bypassing backpropagation through the dynamics.
Feint and Attack: Attention-Based Strategies for Jailbreaking and Protecting LLMs
Therefore, both ABA and ABD can be used to access the security of the LLMs.
CCDepth: A Lightweight Self-supervised Depth Estimation Network with Enhanced Interpretability
To mitigate these issues, this study proposes a novel hybrid self-supervised depth estimation network, CCDepth, comprising convolutional neural networks (CNNs) and the white-box CRATE (Coding RAte reduction TransformEr) network.
Meta Flow Matching: Integrating Vector Fields on the Wasserstein Manifold
Flow-based models allow for learning these dynamics at the population level - they model the evolution of the entire distribution of samples.
Fast Point Cloud Geometry Compression with Context-based Residual Coding and INR-based Refinement
This gives us a means to determine the spatial context in which the latent features of 3D points are compressed by arithmetic coding.
Beyond Entity Alignment: Towards Complete Knowledge Graph Alignment via Entity-Relation Synergy
Knowledge Graph Alignment (KGA) aims to integrate knowledge from multiple sources to address the limitations of individual Knowledge Graphs (KGs) in terms of coverage and depth.
MIBench: Evaluating Multimodal Large Language Models over Multiple Images
However, most existing MLLMs and benchmarks primarily focus on single-image input scenarios, leaving the performance of MLLMs when handling realistic multiple images underexplored.
GPT4Rec: Graph Prompt Tuning for Streaming Recommendation
Secondly, structure-level prompts guide the model in adapting to broader patterns of connectivity and relationships within the graph.
Mobile-Agent-v2: Mobile Device Operation Assistant with Effective Navigation via Multi-Agent Collaboration
However, the two major navigation challenges in mobile device operation tasks, task progress navigation and focus content navigation, are significantly complicated under the single-agent architecture of existing work.
Uncertainty Quantification on Graph Learning: A Survey
Graphical models, including Graph Neural Networks (GNNs) and Probabilistic Graphical Models (PGMs), have demonstrated their exceptional capabilities across numerous fields.
Explainable Survival Analysis with Uncertainty using Convolution-Involved Vision Transformer
Highlights•Without patching WSIs, a novel ViT-based model is proposed for survival predictions.•We first introduce aleatoric uncertainty into the survival loss function.•We explain survival prediction using a post-hoc explainable method.•Our method outperforms baselines in accuracy, explainability, and reliability.
Design as Desired: Utilizing Visual Question Answering for Multimodal Pre-training
We leverage descriptions in medical reports to design multi-granular question-answer pairs associated with different diseases, which assist the framework in pre-training without requiring extra annotations from experts.
FineFake: A Knowledge-Enriched Dataset for Fine-Grained Multi-Domain Fake News Detection
Existing benchmarks for fake news detection have significantly contributed to the advancement of models in assessing the authenticity of news content.
A Differential Geometric View and Explainability of GNN on Evolving Graphs
Graphs are ubiquitous in social networks and biochemistry, where Graph Neural Networks (GNN) are the state-of-the-art models for prediction.
FLLIC: Functionally Lossless Image Compression
Extensive experiments show that FLLIC achieves state-of-the-art performance in joint denoising and compression of noisy images and does so at a lower computational cost.
A Survey of Text Watermarking in the Era of Large Language Models
This paper conducts a comprehensive survey of the current state of text watermarking technology, covering four main aspects: (1) an overview and comparison of different text watermarking techniques; (2) evaluation methods for text watermarking algorithms, including their detectability, impact on text or LLM quality, robustness under target or untargeted attacks; (3) potential application scenarios for text watermarking technology; (4) current challenges and future directions for text watermarking.
Visual Commonsense based Heterogeneous Graph Contrastive Learning
Specifically, our model contains two key components: the Commonsense-based Contrastive Learning and the Graph Relation Network.
TransGNN: Harnessing the Collaborative Power of Transformers and Graph Neural Networks for Recommender Systems
Graph Neural Networks (GNNs) have emerged as promising solutions for collaborative filtering (CF) through the modeling of user-item interaction graphs.
Robust Ranking Explanations
Robust explanations of machine learning models are critical to establish human trust in the models.
Inconsistent Matters: A Knowledge-guided Dual-consistency Network for Multi-modal Rumor Detection
Rumor spreaders are increasingly utilizing multimedia content to attract the attention and trust of news consumers.
LVQAC: Lattice Vector Quantization Coupled with Spatially Adaptive Companding for Efficient Learned Image Compression
Recently, numerous end-to-end optimized image compression neural networks have been developed and proved themselves as leaders in rate-distortion performance.
HR-NeuS: Recovering High-Frequency Surface Geometry via Neural Implicit Surfaces
Recent advances in neural implicit surfaces for multi-view 3D reconstruction primarily focus on improving large-scale surface reconstruction accuracy, but often produce over-smoothed geometries that lack fine surface details.
Dual-layer Image Compression via Adaptive Downsampling and Spatially Varying Upconversion
In the ADDL compression system, an image is reduced in resolution by learned content-adaptive downsampling kernels and compressed to form a coded base layer.
Word-Graph2vec: An efficient word embedding approach on word co-occurrence graph using random walk technique
Word embedding has become ubiquitous and is widely used in various natural language processing (NLP) tasks, such as web retrieval, web semantic analysis, and machine translation, and so on.
VQACL: A Novel Visual Question Answering Continual Learning Setting
Research on continual learning has recently led to a variety of work in unimodal community, however little attention has been paid to multimodal tasks like visual question answering (VQA).
Provable Robust Saliency-based Explanations
To foster trust in machine learning models, explanations must be faithful and stable for consistent insights.
SemanticBEVFusion: Rethink LiDAR-Camera Fusion in Unified Bird's-Eye View Representation for 3D Object Detection
LiDAR and camera are two essential sensors for 3D object detection in autonomous driving.
Unsupervised Scene Sketch to Photo Synthesis
Taking this advantage, we synthesize a photo-realistic image by combining the structure of a sketch and the visual style of a reference photo.
MFAN: Multi-modal Feature-enhanced Attention Networks for Rumor Detection
Rumor spreaders are increasingly taking advantage of multimedia content to attract and mislead news consumers on social media.
Are Your Reviewers Being Treated Equally? Discovering Subgroup Structures to Improve Fairness in Spam Detection
We first identify subgroup structures in the review graph that lead to discrepant accuracy in the groups.
Heterogeneous Information Network based Default Analysis on Banking Micro and Small Enterprise Users
Risk assessment is a substantial problem for financial institutions that has been extensively studied both for its methodological richness and its various practical applications.
Structured Graph Variational Autoencoders for Indoor Furniture layout Generation
The architecture consists of a graph encoder that maps the input graph to a structured latent space, and a graph decoder that generates a furniture graph, given a latent code and the room graph.
Values of Coordinated Residential Space Heating in Demand Response Provision
Demand-side response from space heating in residential buildings can potentially provide a huge amount of flexibility for the power system, particularly with deep electrification of the heat sector.
DDGCN: Dual Dynamic Graph Convolutional Networks for Rumor Detection on Social Media
Moreover, the dynamics of knowledge information associated with the comments are not involved, either.
Deep Decoding of $\ell_\infty$-coded Light Field Images
To enrich the functionalities of traditional cameras, light field cameras record both the intensity and direction of light rays, so that images can be rendered with user-defined camera parameters via computations.
Interpretable and Effective Reinforcement Learning for Attacking against Graph-based Rumor Detection
To discover subtle vulnerabilities, we design a powerful attacking algorithm to camouflage rumors in social networks based on reinforcement learning that can interact with and attack any black-box detectors.
Multi-objective Explanations of GNN Predictions
We design a user study to investigate such joint effects and use the findings to design a multi-objective optimization (MOO) algorithm to find Pareto optimal explanations that are well-balanced in simulatability and counterfactual.
Explaining GNN over Evolving Graphs using Information Flow
We define the problem of explaining evolving GNN predictions and propose an axiomatic attribution method to uniquely decompose the change in a prediction to paths on computation graphs.
ABO: Dataset and Benchmarks for Real-World 3D Object Understanding
ABO contains product catalog images, metadata, and artist-created 3D models with complex geometries and physically-based materials that correspond to real, household objects.
RoomStructNet: Learning to Rank Non-Cuboidal Room Layouts From Single View
In addition to using learnt robust features, our approach learns an additional ranking function to estimate the final layout instead of using optimization.
Self-learn to Explain Siamese Networks Robustly
Learning to compare two objects are essential in applications, such as digital forensics, face recognition, and brain network analysis, especially when labeled data is scarce and imbalanced.
Multi-modality Deep Restoration of Extremely Compressed Face Videos
Arguably the most common and salient object in daily video communications is the talking head, as encountered in social media, virtual classrooms, teleconferences, news broadcasting, talk shows, etc.
THP: Topological Hawkes Processes for Learning Causal Structure on Event Sequences
We further propose a causal structure learning method on THP in a likelihood framework.
An Influence-based Approach for Root Cause Alarm Discovery in Telecom Networks
Alarm root cause analysis is a significant component in the day-to-day telecommunication network maintenance, and it is critical for efficient and accurate fault localization and failure recovery.
Attention-guided Image Compression by Deep Reconstruction of Compressive Sensed Saliency Skeleton
We propose a deep learning system for attention-guided dual-layer image compression (AGDL).
Probing quasi-long-range ordering by magnetostriction in monolayer CoPS3
Mermin-Wagner-Coleman theorem predicts no long-range magnetic order at finite temperature in the two-dimensional (2D) isotropic systems, but a quasi-long-range order with a divergent correlation length at the Kosterlitz-Thouless (KT) transition for planar magnets.
Mesoscale and Nanoscale Physics
Haze Formation on Triton
We simulated the formation of sphere and aggregate hazes with and without condensation of the C$_2$H$_4$ ice.
Earth and Planetary Astrophysics
On Numerosity of Deep Neural Networks
With the above critique we ask the question what if a deep convolutional neural network is carefully trained for numerosity?
Deep Multi-modality Soft-decoding of Very Low Bit-rate Face Videos
We propose a novel deep multi-modality neural network for restoring very low bit rate videos of talking heads.
Local Causal Structure Learning and its Discovery Between Type 2 Diabetes and Bone Mineral Density
To illustrate the importance of prior knowledge, the result of the algorithm without prior knowledge is also investigated.
DAVD-Net: Deep Audio-Aided Video Decompression of Talking Heads
Close-up talking heads are among the most common and salient object in video contents, such as face-to-face conversations in social media, teleconferences, news broadcasting, talk shows, etc.
Rigorous Explanation of Inference on Probabilistic Graphical Models
There is no existing method to rigorously attribute the inference outcomes to the contributing factors of the graphical models.
Ultra High Fidelity Image Compression with $\ell_\infty$-constrained Encoding and Deep Decoding
We make a major progress in $\ell_\infty$-constrained image coding after two decades, by developing a novel CNN-based soft $\ell_\infty$-constrained decoding method.
MDLdroid: a ChainSGD-reduce Approach to Mobile Deep Learning for Personal Mobile Sensing
Towards pushing deep learning on devices, we present MDLdroid, a novel decentralized mobile deep learning framework to enable resource-aware on-device collaborative learning for personal mobile sensing applications.
Scalable Explanation of Inferences on Large Graphs
Probabilistic inferences distill knowledge from graphs to aid human make important decisions.
Challenge of Spatial Cognition for Deep Learning
Given the success of the deep convolutional neural networks (DCNNs) in applications of visual recognition and classification, it would be tantalizing to test if DCNNs can also learn spatial concepts, such as straightness, convexity, left/right, front/back, relative size, aspect ratio, polygons, etc., from varied visual examples of these concepts that are simple and yet vital for spatial reasoning.
Intervention Aided Reinforcement Learning for Safe and Practical Policy Optimization in Navigation
We built neural networks as our policy to map sensor readings to control signals on the UAV.
Nonlinear Prediction of Multidimensional Signals via Deep Regression with Applications to Image Coding
Deep convolutional neural networks (DCNN) have enjoyed great successes in many signal processing applications because they can learn complex, non-linear causal relationships from input to output.
Enhancing Stock Market Prediction with Extended Coupled Hidden Markov Model over Multi-Sourced Data
In this work, we study how to explore multiple data sources to improve the performance of the stock prediction.
Attention-aware Deep Adversarial Hashing for Cross-Modal Retrieval
The proposed new deep adversarial network consists of three building blocks: 1) the feature learning module to obtain the feature representations; 2) the attention module to generate an attention mask, which is used to divide the feature representations into the attended and unattended feature representations; and 3) the hashing module to learn hash functions that preserve the similarities between different modalities.
Generating Image Sequence from Description with LSTM Conditional GAN
Generating images from word descriptions is a challenging task.
Multi-region segmentation of bladder cancer structures in MRI with progressive dilated convolutional networks
Precise segmentation of bladder walls and tumor regions is an essential step towards non-invasive identification of tumor stage and grade, which is critical for treatment decision and prognosis of patients with bladder cancer (BC).
A Tensor-Based Sub-Mode Coordinate Algorithm for Stock Prediction
The results demonstrate the improvement on the prediction accuracy and the effectiveness of the proposed model.
Layered Optical Flow Estimation Using a Deep Neural Network with a Soft Mask
We show that by using masks the motion estimate results in a quadratic function of input features in the output layer.
Cognitive Deficit of Deep Learning in Numerosity
Subitizing, or the sense of small natural numbers, is an innate cognitive function of humans and primates; it responds to visual stimuli prior to the development of any symbolic skills, language or arithmetic.
Near-lossless $\ell_\infty$-constrained Image Decompression via Deep Neural Network
Recently a number of CNN-based techniques were proposed to remove image compression artifacts.
Lecture video indexing using boosted margin maximizing neural networks
This paper presents a novel approach for lecture video indexing using a boosted deep convolutional neural network system.
HashGAN:Attention-aware Deep Adversarial Hashing for Cross Modal Retrieval
The proposed new adversarial network, HashGAN, consists of three building blocks: 1) the feature learning module to obtain feature representations, 2) the generative attention module to generate an attention mask, which is used to obtain the attended (foreground) and the unattended (background) feature representations, 3) the discriminative hash coding module to learn hash functions that preserve the similarities between different modalities.
Aicyber's System for NLPCC 2017 Shared Task 2: Voting of Baselines
This paper presents Aicyber's system for NLPCC 2017 shared task 2.
Patient Subtyping via Time-Aware LSTM Networks
We propose a patient subtyping model that leverages the proposed T-LSTM in an auto-encoder to learn a powerful single representation for sequential records of patients, which are then used to cluster patients into clinical subtypes.
Ranked #5 on
Multivariate Time Series Forecasting
on USHCN-Daily
Automated Inference on Sociopsychological Impressions of Attractive Female Faces
This article is a sequel to our earlier work [25].
Responses to Critiques on Machine Learning of Criminality Perceptions (Addendum of arXiv:1611.04135)
In November 2016 we submitted to arXiv our paper "Automated Inference on Criminality Using Face Images".
CGMOS: Certainty Guided Minority OverSampling
In this paper we propose a novel extension to the SMOTE algorithm with a theoretical guarantee for improved classification performance.
Modular Decomposition and Analysis of Registration based Trackers
We show how existing trackers can be broken down using the suggested methodology and compare the performance of the default configuration chosen by the authors against other possible combinations to demonstrate the new insights that can be gained by such an approach.
Learning from Synthetic Data Using a Stacked Multichannel Autoencoder
In this paper, we investigate and formalize a general framework-Stacked Multichannel Autoencoder (SMCAE) that enables bridging the synthetic gap and learning from synthetic data more efficiently.
Learning Classifiers from Synthetic Data Using a Multichannel Autoencoder
Experimental results on two datasets validate the efficiency of our MCAE model and our methodology of generating synthetic data.
