Papers
Mon 13 Mar 2023
242 papers
- Erasing Concepts from Diffusion ModelsDiffusion models → Robustness, privacy and adversarial aspects
- Vision-Language Models as Success DetectorsMultimodal LLMs / vision-language models → Video understanding with MLLMs +1
- Scaling Vision-Language Models with Sparse Mixture of ExpertsMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning +1
- Parallel Vertex Diffusion for Unified Visual GroundingDiffusion models → Image generation, text-to-image and editing
- Transformer-based World Models Are Happy With 100k InteractionsWorld models → Latent dynamics models and model-based RL
- Deploying Offline Reinforcement Learning with Human FeedbackLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF +1
- Synthesizing Realistic Image Restoration Training Pairs: A Diffusion ApproachDiffusion models → Inverse problems and image restoration
- Robust Contrastive Language-Image Pre-training against Data Poisoning and Backdoor AttacksMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness +1
- DDFM: Denoising Diffusion Model for Multi-Modality Image FusionDiffusion models → Image generation, text-to-image and editing
- ODIN: On-demand Data Formulation to Mitigate Dataset Lock-inDiffusion models → Image generation, text-to-image and editing
- Kernel Density Bayesian Inverse Reinforcement LearningOffline RL and imitation learning from data → Inverse reinforcement learning
- Analyzing ChatGPT's Aptitude in an Introductory Computer Engineering Course
- Rediscovering Hashed Random Projections for Efficient Quantization of Contextualized Sentence Embeddings
- TM-vector: A Novel Forecasting Approach for Market stock movement with a Rich Representation of Twitter and Market data
- Inflation forecasting with attention based transformer neural networks
- Towards risk-informed PBSHM: Populations as hierarchical systems
- DPPMask: Masked Image Modeling with Determinantal Point Processes
- LocalEyenet: Deep Attention framework for Localization of Eyes
- A XGBoost Algorithm-based Fatigue Recognition Model Using Face Detection
- Minimizing Fuzzy Interpretations in Fuzzy Description Logics by Using Crisp Bisimulations
- Learning Model-Free Robust Precoding for Cooperative Multibeam Satellite Communications
- Detecting hidden structures from a static loading experiment: topology optimization meets physics-informed neural networks
- Model Extraction Attacks on Split Federated Learning
- Domain Generalization in Machine Learning Models for Wireless Communications: Concepts, State-of-the-Art, and Open Issues
- Model scale versus domain knowledge in statistical forecasting of chaotic systems
- Bayes Complexity of Learners vs Overfitting
- Object-based SLAM utilizing unambiguous pose parameters considering general symmetry types
- HiSSNet: Sound Event Detection and Speaker Identification via Hierarchical Prototypical Networks for Low-Resource Headphones
- Fractional dynamics foster deep learning of COPD stage prediction
- Path Planning using Reinforcement Learning: A Policy Iteration Approach
- Towards Unsupervised Learning based Denoising of Cyber Physical System Data to Mitigate Security Concerns
- Domain Generalization via Nuclear Norm Regularization
- Automated Vulnerability Detection in Source Code Using Quantum Natural Language Processing
- Audio Visual Language Maps for Robot Navigation
- Multi-class Skin Cancer Classification Architecture Based on Deep Convolutional Neural Network
- Architext: Language-Driven Generative Architecture Design
- SuperMask: Generating High-resolution object masks from multi-view, unaligned low-resolution MRIs
- Reinforcement Learning-based Wavefront Sensorless Adaptive Optics Approaches for Satellite-to-Ground Laser Communication
- Handwritten Word Recognition using Deep Learning Approach: A Novel Way of Generating Handwritten Words
- Schr"odinger's Camera: First Steps Towards a Quantum-Based Privacy Preserving Camera
- Loss of Plasticity in Continual Deep Reinforcement Learning
- Meta-learning approaches for few-shot learning: A survey of recent advances
- MRET: Multi-resolution Transformer for Video Quality Assessment
- Using VAEs to Learn Latent Variables: Observations on Applications in cryo-EM
- Guided Speech Enhancement Network
- Deep Learning Approach for Classifying the Aggressive Comments on Social Media: Machine Translated Data Vs Real Life Data
- Efficient Self-supervised Continual Learning with Progressive Task-correlated Layer Freezing
- Challenges and Practices of Deep Learning Model Reengineering: A Case Study on Computer Vision
- General Loss Functions Lead to (Approximate) Interpolation in High Dimensions
- Can Adversarial Examples Be Parsed to Reveal Victim Model Information?
- X-Former: In-Memory Acceleration of Transformers
- A Framework for Combining Entity Resolution and Query Answering in Knowledge Bases
- Superhuman Artificial Intelligence Can Improve Human Decision Making by Increasing Novelty
- AMOM: Adaptive Masking over Masking for Conditional Masked Language Model
- (1+1) Genetic Programming With Functionally Complete Instruction Sets Can Evolve Boolean Conjunctions and Disjunctions with Arbitrarily Small Error
- Network Anomaly Detection Using Federated Learning
- DRISHTI: Visual Navigation Assistant for Visually Impaired
- Blind Acoustic Room Parameter Estimation Using Phase Features
- On the ethics of constructing conscious AI
- Direct Motif Extraction from High Resolution Crystalline STEM Images
- Unsupervised Representation Learning in Partially Observable Atari Games
- Revealed Multi-Objective Utility Aggregation in Human Driving
- Discovering Multiple Algorithm Configurations
- End-to-end Deformable Attention Graph Neural Network for Single-view Liver Mesh Reconstruction
- TransNetR: Transformer-based Residual Network for Polyp Segmentation with Multi-Center Out-of-Distribution Testing
- FreeNeRF: Improving Few-shot Neural Rendering with Free Frequency Regularization
- Polar-VQA: Visual Question Answering on Remote Sensed Ice sheet Imagery from Polar Region
- Designing Deep Networks for Scene Recognition
- Tuning support vector machines and boosted trees using optimization algorithms
- RTMPose: Real-Time Multi-Person Pose Estimation based on MMPose
- Fast exploration and learning of latent graphs with aliased observations
- Many learning agents interacting with an agent-based market model
- Efficient Bayesian Physics Informed Neural Networks for Inverse Problems via Ensemble Kalman Inversion
- MetaTroll: Few-shot Detection of State-Sponsored Trolls with Transformer Adapters
- TriDet: Temporal Action Detection with Relative Boundary Modeling
- Revisiting Class-Incremental Learning with Pre-Trained Models: Generalizability and Adaptivity are All You Need
- PoseExaminer: Automated Testing of Out-of-Distribution Robustness in Human Pose and Shape Estimation
- MP-Former: Mask-Piloted Transformer for Image Segmentation
- Lite DETR : An Interleaved Multi-Scale Encoder for Efficient DETR
- Application of targeted maximum likelihood estimation in public health and epidemiological studies: a systematic review
- Unsupervised HDR Image and Video Tone Mapping via Contrastive Learning
- Collision Cross-entropy for Soft Class Labels and Deep Clustering
- Model-tuning Via Prompts Makes NLP Models Adversarially Robust
- Nearest-Neighbor Inter-Intra Contrastive Learning from Unlabeled Videos
- Learning Reduced-Order Models for Cardiovascular Simulations with Graph Neural Networks
- NeuSE: Neural SE(3)-Equivariant Embedding for Consistent Spatial Understanding with Objects
- Transformer Models for Acute Brain Dysfunction Prediction
- Meet in the Middle: A New Pre-training Paradigm
- Transformer-based approaches to Sentiment Detection
- Tight Non-asymptotic Inference via Sub-Gaussian Intrinsic Moment Norm
- Align and Attend: Multimodal Summarization with Dual Contrastive Losses
- Universal coding, intrinsic volumes, and metric complexity
- A Survey of Graph Prompting Methods: Techniques, Applications, and Challenges
- Breaking Common Sense: WHOOPS! A Vision-and-Language Benchmark of Synthetic and Compositional Images
- InPL: Pseudo-labeling the Inliers First for Imbalanced Semi-supervised Learning
- A Surface-normal Based Neural Framework for Colonoscopy Reconstruction
- Channel Estimation for Underwater Visible Light Communication: A Sparse Learning Perspective
- Are Models Trained on Indian Legal Data Fair?
- Can Workers Meaningfully Consent to Workplace Wellbeing Technologies?
- PMC-CLIP: Contrastive Language-Image Pre-training using Biomedical Documents
All 242
- Intersection Warning System for Occlusion Risks using Relational Local Dynamic Maps
- Efficient Semantic Segmentation by Altering Resolutions for Compressed Videos
- PromptFusion: Decoupling Stability and Plasticity for Continual Learning
- Optimization of the location and design of urban green spaces
- A Comprehensive Empirical Evaluation of Existing Word Embedding Approaches
- Optimizing Convolutional Neural Networks for Chronic Obstructive Pulmonary Disease Detection in Clinical Computed Tomography Imaging
- Joint Behavior and Common Belief
- Traffic Prediction with Transfer Learning: A Mutual Information-based Approach
- Mobile Mapping Mesh Change Detection and Update
- Probabilistic Uncertainty-Aware Risk Spot Detector for Naturalistic Driving
- Incomplete Multi-View Multi-Label Learning via Label-Guided Masked View- and Category-Aware Transformers
- Evaluating Visual Number Discrimination in Deep Neural Networks
- Validation of uncertainty quantification metrics: a primer based on the consistency and adaptivity concepts
- Dynamic Event-based Optical Identification and Communication
- When Respondents Don't Care Anymore: Identifying the Onset of Careless Responding
- Improved Tree Search for Automatic Program Synthesis
- Tighter Lower Bounds for Shuffling SGD: Random Permutations and Beyond
- Computing equivariant matrices on homogeneous spaces for Geometric Deep Learning and Automorphic Lie Algebras
- Differential Good Arm Identification
- SA-CNN: Application to text categorization issues using simulated annealing-based convolutional neural network optimization
- Score Attack: A Lower Bound Technique for Optimal Differentially Private Learning
- Am'elioration de la qualit'e d'images avec un algorithme d'optimisation inspir'ee par la nature
- Multi PILOT: Learned Feasible Multiple Acquisition Trajectories for Dynamic MRI
- NeuroQL: A Neuro-Symbolic Language and Dataset for Inter-Subjective Reasoning
- Multi-Microphone Speaker Separation by Spatial Regions
- Large Language Models in the Workplace: A Case Study on Prompt Engineering for Job Type Classification
- An Improved Baseline Framework for Pose Estimation Challenge at ECCV 2022 Visual Perception for Navigation in Human Environments Workshop
- Comparing statistical and machine learning methods for time series forecasting in data-driven logistics -- A simulation study
- Transferable Deep Learning Power System Short-Term Voltage Stability Assessment with Physics-Informed Topological Feature Engineering
- Evolutionary quantum feature selection
- Enhancing COVID-19 Severity Analysis through Ensemble Methods
- AdaptiveNet: Post-deployment Neural Architecture Adaptation for Diverse Edge Environments
- VMCDL: Vulnerability Mining Based on Cascaded Deep Learning Under Source Control Flow
- Improving physics-informed neural networks with meta-learned optimization
- Mirror U-Net: Marrying Multimodal Fission with Multi-task Learning for Semantic Segmentation in Medical Imaging
- Don't PANIC: Prototypical Additive Neural Network for Interpretable Classification of Alzheimer's Disease
- Modality-Agnostic Debiasing for Single Domain Generalization
- NeurEPDiff: Neural Operators to Predict Geodesics in Deformation Spaces
- Upcycling Models under Domain and Category Shift
- xASTNN: Improved Code Representations for Industrial Practice
- A Feature-based Approach for the Recognition of Image Quality Degradation in Automotive Applications
- Prototype-based Embedding Network for Scene Graph Generation
- Weakly Unsupervised Domain Adaptation for Vestibular Schwannoma Segmentation
- The challenge of representation learning: Improved accuracy in deep vision models does not come with better predictions of perceptual similarity
- Bag of Tricks with Quantized Convolutional Neural Networks for image classification
- Automatically Identifying Relations Between Self-Admitted Technical Debt Across Different Sources
- Spatial Attention and Syntax Rule Enhanced Tree Decoder for Offine Handwritten Mathematical Expression Recognition
- Generating multiple-choice questions for medical question answering with distractors and cue-masking
- n-Step Temporal Difference Learning with Optimal n
- Cross-device Federated Learning for Mobile Health Diagnostics: A First Study on COVID-19 Detection
- MSINet: Twins Contrastive Search of Multi-Scale Interaction for Object ReID
- A Generalized Multi-Modal Fusion Detection Framework
- Quantile Online Learning for Semiconductor Failure Analysis
- Bandit-supported care planning for older people with complex health and care needs
- Hybrid Variational Autoencoder for Time Series Forecasting
- Optimization of Velocity Ramps with Survival Analysis for Intersection Merge-Ins
- FireRisk: A Remote Sensing Dataset for Fire Risk Assessment with Benchmarks Using Supervised and Self-supervised Learning
- Pretrained ViTs Yield Versatile Representations For Medical Images
- SelfPromer: Self-Prompt Dehazing Transformers with Depth-Consistency
- nablaSD: Differentiable Programming for Sparse Tensors
- Visual-Policy Learning through Multi-Camera View to Single-Camera View Knowledge Distillation for Robot Manipulation Tasks
- Addressing Biases in the Texts using an End-to-End Pipeline Approach
- HOOV: Hand Out-Of-View Tracking for Proprioceptive Interaction using Inertial Sensing
- Reference-Guided Large-Scale Face Inpainting with Identity and Texture Control
- AGTGAN: Unpaired Image Translation for Photographic Ancient Character Generation
- OSIS: Efficient One-stage Network for 3D Instance Segmentation
- Symbolic Regression for PDEs using Pruned Differentiable Programs
- Review on the Feasibility of Adversarial Evasion Attacks and Defenses for Network Intrusion Detection Systems
- Predicting Density of States via Multi-modal Transformer
- Identifying Label Errors in Object Detection Datasets by Loss Inspection
- Actor-Critic learning for mean-field control in continuous time
- Improving Mutual Information Estimation with Annealed and Energy-Based Bounds
- Self-supervised learning-based general laboratory progress pretrained model for cardiovascular event detection
- Leveraging Neural Koopman Operators to Learn Continuous Representations of Dynamical Systems from Scarce Data
- A new methodology to predict the oncotype scores based on clinico-pathological data with similar tumor profiles
- Bridging the Gap between Chemical Reaction Pretraining and Conditional Molecule Generation with a Unified Model
- Improving Table Structure Recognition with Visual-Alignment Sequential Coordinate Modeling
- A Multi-Modal Simulation Framework to Enable Digital Twin-based V2X Communications in Dynamic Environments
- Context-Aware Selective Label Smoothing for Calibrating Sequence Recognition Model
- CoGANPPIS: A Coevolution-enhanced Global Attention Neural Network for Protein-Protein Interaction Site Prediction
- A Human Subject Study of Named Entity Recognition (NER) in Conversational Music Recommendation Queries
- Guiding the Guidance: A Comparative Analysis of User Guidance Signals for Interactive Segmentation of Volumetric Images
- TARGET: Federated Class-Continual Learning via Exemplar-Free Distillation
- Importance Filtering with Risk Models for Complex Driving Situations
- DeepVigor: Vulnerability Value Ranges and Factors for DNNs' Reliability Assessment
- Twin Contrastive Learning with Noisy Labels
- Super-Resolution Information Enhancement For Crowd Counting
- Pixel-wise Gradient Uncertainty for Convolutional Neural Networks applied to Out-of-Distribution Segmentation
- NeRFLiX: High-Quality Neural View Synthesis by Learning a Degradation-Driven Inter-viewpoint MiXer
- ViM: Vision Middleware for Unified Downstream Transferring
- CrossFormer++: A Versatile Vision Transformer Hinging on Cross-scale Attention
- ST360IQ: No-Reference Omnidirectional Image Quality Assessment with Spherical Vision Transformers
- DEHRFormer: Real-time Transformer for Depth Estimation and Haze Removal from Varicolored Haze Scenes
- Contextually-rich human affect perception using multimodal scene information
- Molecular Property Prediction by Semantic-invariant Contrastive Learning
- DR2: Diffusion-based Robust Degradation Remover for Blind Face Restoration
- SCPNet: Semantic Scene Completion on Point Cloud
- A Coarse-to-Fine Place Recognition Approach using Attention-guided Descriptors and Overlap Estimation
- Uni3D: A Unified Baseline for Multi-dataset 3D Object Detection
- Spacecraft Anomaly Detection with Attention Temporal Convolution Network
- The System Description of dun_oscar team for The ICPR MSR Challenge
- Progressive Open Space Expansion for Open-Set Model Attribution
- A Test Statistic Estimation-based Approach for Establishing Self-interpretable CNN-based Binary Classifiers
- Interventional Bag Multi-Instance Learning On Whole-Slide Pathological Images
- FusionLoc: Camera-2D LiDAR Fusion Using Multi-Head Self-Attention for End-to-End Serving Robot Relocalization
- Physics-driven machine learning models coupling PyTorch and Firedrake
- Three Guidelines You Should Know for Universally Slimmable Self-Supervised Learning
- Adaptive Data-Free Quantization
- Deep Learning-based Eye-Tracking Analysis for Diagnosis of Alzheimer's Disease Using 3D Comprehensive Visual Stimuli
- FlexGen: High-Throughput Generative Inference of Large Language Models with a Single GPU
- OTOV2: Automatic, Generic, User-Friendly
- View Adaptive Light Field Deblurring Networks with Depth Perception
- Learning Distortion Invariant Representation for Image Restoration from A Causality Perspective
- An automated pipeline to create an atlas of in situ hybridization gene expression data in the adult marmoset brain
- Dynamic Neural Network for Multi-Task Learning Searching across Diverse Network Topologies
- One-Shot Segmentation of Novel White Matter Tracts via Extensive Data Augmentation
- On the Regret of Online Edge Service Hosting
- Label Distribution Learning from Logical Label
- Transformer Encoder with Multiscale Deep Learning for Pain Classification Using Physiological Signals
- Hierarchical Relationships: A New Perspective to Enhance Scene Graph Generation
- Learning Transductions and Alignments with RNN Seq2seq Models
- Label Information Bottleneck for Label Enhancement
- DarkVisionNet: Low-Light Imaging via RGB-NIR Fusion with Deep Inconsistency Prior
- Transformer-based Planning for Symbolic Regression
- Best-of-three-worlds Analysis for Linear Bandits with Follow-the-regularized-leader Algorithm
- Instate: Predicting the State of Residence From Last Name
- SDF-3DGAN: A 3D Object Generative Method Based on Implicit Signed Distance Function
- Continuous sign language recognition based on cross-resolution knowledge distillation
- TranSG: Transformer-Based Skeleton Graph Prototype Contrastive Learning with Structure-Trajectory Prompted Reconstruction for Person Re-Identification
- Backdoor Defense via Deconfounded Representation Learning
- Transformation-Invariant Network for Few-Shot Object Detection in Remote Sensing Images
- On Model Compression for Neural Networks: Framework, Algorithm, and Convergence Guarantee
- Meaningful human command: Advance control directives as a method to enable moral and legal responsibility for autonomous weapons systems
- Dynamic Clustering and Cluster Contrastive Learning for Unsupervised Person Re-identification
- Boosting Source Code Learning with Text-Oriented Data Augmentation: An Empirical Study
- Vessel-Promoted OCT to OCTA Image Translation by Heuristic Contextual Constraints
- Neural Diarization with Non-autoregressive Intermediate Attractors
- Object-Centric Multi-Task Learning for Human Instances
- Gaussian Process on the Product of Directional Manifolds
- Multichannel Orthogonal Transform-Based Perceptron Layers for Efficient ResNets
- Ins-ATP: Deep Estimation of ATP for Organoid Based on High Throughput Microscopic Images
- Beyond Single Items: Exploring User Preferences in Item Sets with the Conversational Playlist Curation Dataset