Papers
Fri 4 Aug 2023
156 papers
- Vulnerabilities in AI Code Generators: Exploring Targeted Data Poisoning AttacksLLM safety and security → Backdoor and data poisoning attacks
- ReCLIP: Refine Contrastive Language Image Pre-Training with Source Free Domain AdaptationMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
- Exploiting On-chip Heterogeneity of Versal Architecture for GNN Inference AccelerationEfficient LLM inference and serving → Early exit and edge inference
- MM-Vet: Evaluating Large Multimodal Models for Integrated CapabilitiesMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
- RAHNet: Retrieval Augmented Hybrid Network for Long-tailed Graph ClassificationRetrieval-augmented generation → Knowledge-graph and structured-knowledge RAG
- Painterly Image Harmonization using Diffusion ModelDiffusion models → Image generation, text-to-image and editing
- Diffusion probabilistic models enhance variational autoencoder for crystal structure generative modelingDiffusion models → Flow matching, time series and science
- Improved Order Analysis and Design of Exponential Integrator for Diffusion Models SamplingDiffusion models → Diffusion foundations and sampling
- SDDM: Score-Decomposed Diffusion Models on Manifolds for Unpaired Image-to-Image TranslationDiffusion models → Diffusion foundations and sampling
- Retroformer: Retrospective Large Language Agents with Policy Gradient OptimizationLLM agents and tool use → Reinforcement learning for LLM agents
- World-Model-Based Control for Industrial box-packing of Multiple Objects using NewtonianVAEWorld models → Embodied and robot world models
- ParaFuzz: An Interpretability-Driven Technique for Detecting Poisoned Samples in NLPLLM safety and security → Backdoor and data poisoning attacks
- VQGraph: Rethinking Graph Representation Space for Bridging GNNs and MLPsKnowledge distillation → Graph neural network distillation
- Multimodal machine learning for materials science: composition-structure bimodal learning for experimentally measured properties
- Large-Scale Public Data Improves Differentially Private Image Generation Quality
- Event-based Dynamic Graph Representation Learning for Patent Application Trend Prediction
- Recurrent Neural Networks with more flexible memory: better predictions than rough volatility
- Deep learning for spike detection in deep brain stimulation surgery
- Can Attention Be Used to Explain EHR-Based Mortality Prediction Tasks: A Case Study on Hemorrhagic Stroke
- Capturing Spectral and Long-term Contextual Information for Speech Emotion Recognition Using Deep Learning Techniques
- High-Accuracy Prediction of Metal-Insulator-Metal Metasurface with Deep Learning
- Legal Summarisation through LLMs: The PRODIGIT Project
- On The Suitability of Differential Dataflow For Datalog Interpretation In Highly Dynamic Settings
- Deep neural networks from the perspective of ergodic theory
- Enhancing Cell Tracking with a Time-Symmetric Deep Learning Approach
- Toward Zero-Shot Instruction Following
- Multi-attacks: Many images + the same adversarial attack → many target labels
- Semantic Channel Equalizer: Modelling Language Mismatch in Multi-User Semantic Communications
- Analysis and Optimization of Wireless Federated Learning with Data Heterogeneity
- Discrimination of Radiologists Utilizing Eye-Tracking Technology and Machine Learning: A Case Study
- SureFED: Robust Federated Learning via Uncertainty-Aware Inward and Outward Inspection
- Meta-Tsallis-Entropy Minimization: A New Self-Training Approach for Domain Adaptation on Text Classification
- Nonlinear Controller Design for a Quadrotor with Inverted Pendulum
- Exploring Part-Informed Visual-Language Learning for Person Re-Identification
- Learning to Schedule in Non-Stationary Wireless Networks With Unknown Statistics
- Personalization of Stress Mobile Sensing using Self-Supervised Learning
- Assessing the impact of emergency department short stay units using length-of-stay prediction and discrete event simulation
- Synthesizing Programmatic Policies with Actor-Critic Algorithms and ReLU Networks
- How Good Are SOTA Fake News Detectors
- Towards Improving Harmonic Sensitivity and Prediction Stability for Singing Melody Extraction
- EndoDepthL: Lightweight Endoscopic Monocular Depth Estimation with CNN-Transformer
- Fluid Viscosity Prediction Leveraging Computer Vision and Robot Interaction
- Exploring the Effect of Sparse Recovery on the Quality of Image Superresolution
- Scalable Computation of Causal Bounds
- FPR Estimation for Fraud Detection in the Presence of Class-Conditional Label Noise
- Explainable Deep Learning-based Solar Flare Prediction with post hoc Attention for Operational Forecasting
- EDI: ESKF-based Disjoint Initialization for Visual-Inertial SLAM Systems
- Solving Witness-type Triangle Puzzles Faster with an Automatically Learned Human-Explainable Predicate
- Let's Give a Voice to Conversational Agents in Virtual Reality
- A Review of Change of Variable Formulas for Generative Modeling
- Learning from Topology: Cosmological Parameter Estimation from the Large-scale Structure
- Generation of Realistic Synthetic Raw Radar Data for Automated Driving Applications using Generative Adversarial Networks
- Uncertainty Estimation and Propagation in Accelerated MRI Reconstruction
- Harnessing the Web and Knowledge Graphs for Automated Impact Investing Scoring
- Color Image Recovery Using Generalized Matrix Completion over Higher-Order Finite Dimensional Algebra
- Frequency Disentangled Features in Neural Image Compression
- ChatGPT for GTFS: Benchmarking LLMs on GTFS Understanding and Retrieval
- An Intrinsic Approach to Scalar-Curvature Estimation for Point Clouds
- Vehicles Control: Collision Avoidance using Federated Deep Reinforcement Learning
- From research to clinic: Accelerating the translation of clinical decision support systems by making synthetic data interoperable
- Unravelling Responsibility for AI
- Improving Human-Object Interaction Detection via Virtual Image Learning
- Knowledge-Driven Multi-Agent Reinforcement Learning for Computation Offloading in Cybertwin-Enabled Internet of Vehicles
- On stable wrapper-based parameter selection method for efficient ANN-based data-driven modeling of turbulent flows
- Branched Latent Neural Maps
- Designing a Deep Learning-Driven Resource-Efficient Diagnostic System for Metastatic Breast Cancer: Reducing Long Delays of Clinical Diagnosis and Improving Patient Survival in Developing Countries
- Convolutions Die Hard: Open-Vocabulary Segmentation with Single Frozen Convolutional CLIP
- Adapting the NICT-JLE Corpus for Disfluency Detection Models
- Label Inference Attacks against Node-level Vertical Federated GNNs
- Universal Approximation of Linear Time-Invariant (LTI) Systems through RNNs: Power of Randomness in Reservoir Computing
- Towards Generalist Foundation Model for Radiology by Leveraging Web-scale 2D&3D Medical Data
- Fast and Accurate Reduced-Order Modeling of a MOOSE-based Additive Manufacturing Model with Operator Learning
- Nonprehensile Planar Manipulation through Reinforcement Learning with Multimodal Categorical Exploration
- A Survey on Temporal Knowledge Graph Completion: Taxonomy, Progress, and Prospects
- Generative Modelling of L'evy Area for High Order SDE Simulation
- Pruning a neural network using Bayesian inference
- From Military to Healthcare: Adopting and Expanding Ethical Principles for Generative Artificial Intelligence
- Distribution-Informed Adaptation for kNN Graph Construction
- A State-Space Perspective on Modelling and Inference for Online Skill Rating
- A Bi-variant Variational Model for Diffeomorphic Image Registration with Relaxed Jacobian Determinant Constraints
- Learning Optimal Admission Control in Partially Observable Queueing Networks
- Scaling Survival Analysis in Healthcare with Federated Survival Forests: A Comparative Study on Heart Failure and Breast Cancer Genomics
- Classifying Causal Structures: Ascertaining when Classical Correlations are Constrained by Inequalities
- A Machine Learning Method for Predicting Traffic Signal Timing from Probe Vehicle Data
- Universal Defensive Underpainting Patch: Making Your Text Invisible to Optical Character Recognition
- Brain MRI Segmentation using Template-Based Training and Visual Perception Augmentation
- Intensity-free Integral-based Learning of Marked Temporal Point Processes
- Text2KGBench: A Benchmark for Ontology-Driven Knowledge Graph Generation from Text
- T-UNet: Triplet UNet for Change Detection in High-Resolution Remote Sensing Images
- Adapting to Change: Robust Counterfactual Explanations in Dynamic Data Landscapes
- A Parameter-efficient Multi-subject Model for Predicting fMRI Activity
- RobustMQ: Benchmarking Robustness of Quantized Models
- Stability and Generalization of Hypergraph Collaborative Networks
- Class Incremental Learning with Self-Supervised Pre-Training and Prototype Learning
- Learning Networks from Gaussian Graphical Models and Gaussian Free Fields
- Generative Priors for MRI Reconstruction Trained from Magnitude-Only Images Using Phase Augmentation
- Improving Scene Graph Generation with Superpixel-Based Interaction Learning
- Dataflow Dialogue Generation
- A Controllable Co-Creative Agent for Game System Design
- Is Stack Overflow Obsolete? An Empirical Study of the Characteristics of ChatGPT Answers to Stack Overflow Questions
All 156
- Learning to Select the Relevant History Turns in Conversational Question Answering
- Outlier-robust neural network training: variation regularization meets trimmed loss to prevent functional breakdown
- Frustratingly Easy Model Generalization by Dummy Risk Minimization
- Diffusion-Augmented Depth Prediction with Sparse Annotations
- DIVERSIFY: A General Framework for Time Series Out-of-distribution Detection and Generalization
- Redundancy Aware Multi-Reference Based Gainwise Evaluation of Extractive Summarization
- SURE-Val: Safe Urban Relevance Extension and Validation
- Efficient Monaural Speech Enhancement using Spectrum Attention Fusion
- Adaptive Proximal Gradient Method for Convex Optimization
- Finding Tori: Self-supervised Learning for Analyzing Korean Folk Song
- On the Calibration of Uncertainty Estimation in LiDAR-based Semantic Segmentation
- DTF-Net: Category-Level Pose Estimation and Shape Reconstruction via Deformable Template Field
- MSECNet: Accurate and Robust Normal Estimation for 3D Point Clouds by Multi-Scale Edge Conditioning
- FB-BEV: BEV Representation from Forward-Backward View Transformations
- Sinhala-English Parallel Word Dictionary Dataset
- Self-Normalizing Neural Network, Enabling One Shot Transfer Learning for Modeling EDFA Wavelength Dependent Gain
- Should we trust web-scraped data?
- Learning to Paraphrase Sentences to Different Complexity Levels
- Deep Semantic Model Fusion for Ancient Agricultural Terrace Detection
- ESRL: Efficient Sampling-based Reinforcement Learning for Sequence Generation
- Likelihood-ratio-based confidence intervals for neural networks
- Federated Learning: Organizational Opportunities, Challenges, and Adoption Strategies
- Balanced Classification: A Unified Framework for Long-Tailed Object Detection
- GEMRec: Towards Generative Model Recommendation
- A Survey of Spanish Clinical Language Models
- Paired Competing Neurons Improving STDP Supervised Local Learning In Spiking Neural Networks
- Explaining Relation Classification Models with Semantic Extents
- ES-MVSNet: Efficient Framework for End-to-end Self-supervised Multi-View Stereo
- Emo-DNA: Emotion Decoupling and Alignment Learning for Cross-Corpus Speech Emotion Recognition
- From Fake to Hyperpartisan News Detection Using Domain Adaptation
- Synthetic outlier generation for anomaly detection in autonomous driving
- AutoML4ETC: Automated Neural Architecture Search for Real-World Encrypted Traffic Classification
- Scaling Clinical Trial Matching Using Large Language Models: A Case Study in Oncology
- Scene-aware Human Pose Generation using Transformer
- Efficient Labelling of Affective Video Datasets via Few-Shot & Multi-Task Contrastive Learning
- You talk what you read: Understanding News Comment Behavior by Dispositional and Situational Attribution
- Learning Referring Video Object Segmentation from Weak Annotation
- M2Former: Multi-Scale Patch Selection for Fine-Grained Visual Recognition
- Speaker Diarization of Scripted Audiovisual Content
- CTP-Net: Character Texture Perception Network for Document Image Forgery Localization
- Robust Self-Supervised Extrinsic Self-Calibration
- Optimization on Pareto sets: On a theory of multi-objective optimization
- Tweet Insights: A Visualization Platform to Extract Temporal Insights from Twitter
- Learning the solution operator of two-dimensional incompressible Navier-Stokes equations using physics-aware convolutional neural networks
- Cognitive TransFuser: Semantics-guided Transformer-based Sensor Fusion for Improved Waypoint Prediction
- Eva: A General Vectorized Approximation Framework for Second-order Optimization
- Model Provenance via Model DNA
- Attention-Driven Lightweight Model for Pigmented Skin Lesion Detection
- Rethinking Class Activation Maps for Segmentation: Revealing Semantic Information in Shallow Layers by Reducing Noise
- AdvFAS: A robust face anti-spoofing framework against adversarial examples
- Chinese Financial Text Emotion Mining: GCGTS -- A Character Relationship-based Approach for Simultaneous Aspect-Opinion Pair Extraction
- Prompt2Gaussia: Uncertain Prompt-learning for Script Event Prediction
- Breast Ultrasound Tumor Classification Using a Hybrid Multitask CNN-Transformer Network
- CT Reconstruction from Few Planar X-rays with Application towards Low-resource Radiotherapy
- Multi-interactive Feature Learning and a Full-time Multi-modality Benchmark for Image Fusion and Segmentation
- N-gram Boosting: Improving Contextual Biasing with Normalized N-gram Targets