Papers
Mon 27 Mar 2023
240 papers
- Mask and Restore: Blind Backdoor Defense at Test Time with Masked AutoencoderLLM safety and security → Backdoor and data poisoning attacks
- The Stable Signature: Rooting Watermarks in Latent Diffusion ModelsDiffusion models → Robustness, privacy and adversarial aspects +1
- Anti-DreamBooth: Protecting users from personalized text-to-image synthesisDiffusion models → Robustness, privacy and adversarial aspects
- Debiasing Scores and Prompts of 2D Diffusion for View-consistent Text-to-3D GenerationDiffusion models → 3D, point cloud and scene generation
- Training-free Content Injection using h-space in Diffusion ModelsDiffusion models → Image generation, text-to-image and editing
- Improving Neural Topic Models with Wasserstein Knowledge DistillationKnowledge distillation → Knowledge distillation for LLMs
- Information Maximizing Curriculum: A Curriculum-Based Approach for Imitating Diverse SkillsMixture-of-experts → MoE in reinforcement learning and robotics +1
- Exploring Continual Learning of Diffusion ModelsDiffusion models → Diffusion foundations and sampling
- Memory-Efficient 3D Denoising Diffusion Models for Medical Image ProcessingDiffusion models → Medical imaging and segmentation
- Text-to-Image Diffusion Models are Zero-Shot ClassifiersDiffusion models → Image generation, text-to-image and editing
- Troika: Multi-Path Cross-Modal Traction for Compositional Zero-Shot LearningMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
- Data Augmentation for Environmental Sound Classification Using Diffusion Probabilistic Model with Top-k Selection DiscriminatorDiffusion models → Audio, speech and music
- Learning the Unlearnable: Adversarial Augmentations Suppress Unlearnable Example AttacksLLM safety and security → Machine unlearning
- UniDistill: A Universal Cross-Modality Knowledge Distillation Framework for 3D Object Detection in Bird's-Eye ViewKnowledge distillation → Detection and dense prediction distillation
- Curriculum Learning for Compositional Visual ReasoningLLM reasoning → Multimodal reasoning
- Mutually-paced Knowledge Distillation for Cross-lingual Temporal Knowledge Graph ReasoningKnowledge distillation → Knowledge distillation for LLMs
- Seer: Language Instructed Video Prediction with Latent Diffusion ModelsDiffusion models → Diffusion and flow policies for robotics
- Model-Based Reinforcement Learning with Isolated ImaginationsWorld models → Latent dynamics models and model-based RL
- Revisiting Multimodal Representation in Contrastive Learning: From Patch and Token Embeddings to Finite Discrete TokensMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
- DiffTAD: Temporal Action Detection with Proposal Denoising DiffusionDiffusion models → Video generation
- CP-CNN: Core-Periphery Principle Guided Convolutional Neural Network
- Philosophical Foundations of GeoAI: Exploring Sustainability, Diversity, and Bias in GeoAI and Spatial Data Science
- EEGMatch: Learning with Incomplete Labels for Semi-Supervised EEG-based Cross-Subject Emotion Recognition
- CoRe-Sleep: A Multimodal Fusion Framework for Time Series Robust to Imperfect Modalities
- DexDeform: Dexterous Deformable Object Manipulation with Human Demonstrations and Differentiable Physics
- Unlocking the Potential of ChatGPT: A Comprehensive Exploration of its Applications, Advantages, Limitations, and Future Directions in Natural Language Processing
- On the Creativity of Large Language Models
- PADME-SoSci: A Platform for Analytics and Distributed Machine Learning for the Social Sciences
- Detecting Backdoors During the Inference Stage Based on Corruption Robustness Consistency
- Visual Response to Emotional State of User Interaction
- Assorted, Archetypal and Annotated Two Million (3A2M) Cooking Recipes Dataset based on Active Learning
- Not cool, calm or collected: Using emotional language to detect COVID-19 misinformation
- Meeting Action Item Detection with Regularized Context Modeling
- ACO-tagger: A Novel Method for Part-of-Speech Tagging using Ant Colony Optimization
- Scaling Pre-trained Language Models to Deeper via Parameter-efficient Architecture
- AmorProt: Amino Acid Molecular Fingerprints Repurposing based Protein Fingerprint
- Lifting uniform learners via distributional decomposition
- The Quality-Diversity Transformer: Generating Behavior-Conditioned Trajectories with Decision Transformers
- Learning Iterative Neural Optimizers for Image Steganography
- mHealth hyperspectral learning for instantaneous spatiospectral imaging of hemodynamics
- Multimodal video and IMU kinematic dataset on daily life activities using affordable devices (VIDIMU)
- Graph Neural Networks for Power Allocation in Wireless Networks with Full Duplex Nodes
- Neural Collapse Inspired Federated Learning with Non-iid Data
- Learning Rate Schedules in the Presence of Distribution Shift
- UFO: A unified method for controlling Understandability and Faithfulness Objectives in concept-based explanations for CNNs
- Multiphysics discovery with moving boundaries using Ensemble SINDy and Peridynamic Differential Operator
- A Framework for Demonstrating Practical Quantum Advantage: Racing Quantum against Classical Generative Models
- Real-Time Semantic Segmentation using Hyperspectral Images for Mapping Unstructured and Unknown Environments
- ChatGPT as a Factual Inconsistency Evaluator for Text Summarization
- Typhoon: Towards an Effective Task-Specific Masking Strategy for Pre-trained Language Models
- Online Learning for Incentive-Based Demand Response
- Fine-grained Audible Video Description
- HD-Bind: Encoding of Molecular Structure with Low Precision, Hyperdimensional Binary Representations
- Uncovering Bias in Personal Informatics
- Learning Expressive Prompting With Residuals for Vision Transformers
- Linguistically Informed ChatGPT Prompts to Enhance Japanese-Chinese Machine Translation: A Case Study on Attributive Clauses
- (Un)fair devices: Moving beyond AI accuracy in personal sensing
- Adjusted Wasserstein Distributionally Robust Estimator in Statistical Learning
- D-TrAttUnet: Dual-Decoder Transformer-Based Attention Unet Architecture for Binary and Multi-classes Covid-19 Infection Segmentation
- EMShepherd: Detecting Adversarial Samples via Side-channel Leakage
- Online Non-Destructive Moisture Content Estimation of Filter Media During Drying Using Artificial Neural Networks
- Core-Periphery Principle Guided Redesign of Self-Attention in Transformers
- Privacy-preserving machine learning for healthcare: open challenges and future perspectives
- Object Discovery from Motion-Guided Tokens
- MoViT: Memorizing Vision Transformers for Medical Image Analysis
- Multi-Flow Transmission in Wireless Interference Networks: A Convergent Graph Learning Approach
- OmniAvatar: Geometry-Guided Controllable 3D Head Synthesis
- Sequential training of GANs against GAN-classifiers reveals correlated "knowledge gaps" present among independently trained GAN instances
- Few-Shot Domain Adaptation for Low Light RAW Image Enhancement
- Learning Harmonic Molecular Representations on Riemannian Manifold
- Real-Time Bus Arrival Prediction: A Deep Learning Approach for Enhanced Urban Mobility
- Semantic-visual Guided Transformer for Few-shot Class-incremental Learning
- Binarizing Sparse Convolutional Networks for Efficient Point Cloud Analysis
- Railway Network Delay Evolution: A Heterogeneous Graph Neural Network Approach
- On the Importance of Feature Separability in Predicting Out-Of-Distribution Error
- Knowledge Enhanced Graph Neural Networks for Graph Completion
- Unimodal Training-Multimodal Prediction: Cross-modal Federated Learning with Hierarchical Aggregation
- Transfer-Once-For-All: AI Model Optimization for Edge
- Regularize implicit neural representation by itself
- SwiftFormer: Efficient Additive Attention for Transformer-based Real-time Mobile Vision Applications
- IRFL: Image Recognition of Figurative Language
- Quantum Multi-Model Fitting
- GeoNet: Benchmarking Unsupervised Adaptation across Geographies
- Zero-shot Model Diagnosis
- EFEM: Equivariant Neural Field Expectation Maximization for 3D Object Segmentation Without Scene Supervision
- On the Stepwise Nature of Self-Supervised Learning
- FaceLit: Neural 3D Relightable Faces
- TextMI: Textualize Multimodal Information for Integrating Non-verbal Cues in Pre-trained Language Models
- JAWS: Just A Wild Shot for Cinematic Transfer in Neural Radiance Fields
- KPEval: Towards Fine-Grained Semantic-Based Keyphrase Evaluation
- ACAT: Adversarial Counterfactual Attention for Classification and Detection in Medical Imaging
- Recovering 3D Hand Mesh Sequence from a Single Blurry Image: A New Dataset and Temporal Unfolding
- 3D Video Object Detection with Learnable Object-Centric Global Optimization
- Learnable Graph Matching: A Practical Paradigm for Data Association
- Human Pose Estimation in Extremely Low-Light Conditions
- Class-Conditioned Transformation for Enhanced Robust Image Classification
- Dimensionality Collapse: Optimal Measurement Selection for Low-Error Infinite-Horizon Forecasting
- Learning to Zoom and Unzoom
- EVA-CLIP: Improved Training Techniques for CLIP at Scale
- Generalizable Neural Voxels for Fast Human Radiance Fields
All 240
- Recognizing Rigid Patterns of Unlabeled Point Clouds by Complete and Continuous Isometry Invariants with no False Negatives and no False Positives
- List Online Classification
- Causal schema induction for knowledge discovery
- Hi4D: 4D Instance Segmentation of Close Human Interaction
- CoDeC: Communication-Efficient Decentralized Continual Learning
- AIR-DA: Adversarial Image Reconstruction for Unsupervised Domain Adaptive Object Detection
- 2S-UDF: A Novel Two-stage UDF Learning Method for Robust Non-watertight Model Reconstruction from Multi-view Images
- A Comprehensive Survey on Test-Time Adaptation under Distribution Shifts
- From Single-Hospital to Multi-Centre Applications: Enhancing the Generalisability of Deep Learning Models for Adverse Event Prediction in the ICU
- Sigmoid Loss for Language Image Pre-Training
- ByteTrackV2: 2D and 3D Multi-Object Tracking by Associating Every Detection Box
- Progressive Semantic-Visual Mutual Adaption for Generalized Zero-Shot Learning
- Closed-Loop Koopman Operator Approximation
- Improving Dual-Encoder Training through Dynamic Indexes for Negative Mining
- Unsupervised Adaptation from Repeated Traversals for Autonomous Driving
- Gazeformer: Scalable, Effective and Fast Prediction of Goal-Directed Human Attention
- Unified Keypoint-based Action Recognition Framework via Structured Keypoint Pooling
- Handwritten Text Generation from Visual Archetypes
- Multi-Granularity Archaeological Dating of Chinese Bronze Dings Based on a Knowledge-Guided Relation Graph
- Bilex Rx: Lexical Data Augmentation for Massively Multilingual Machine Translation
- Joint Person Identity, Gender and Age Estimation from Hand Images using Deep Multi-Task Representation Learning
- A Learning-based Adaptive Compliance Method for Symmetric Bi-manual Manipulation
- Active Self-Supervised Learning: A Few Low-Cost Relationships Are All You Need
- Zero-Shot Composed Image Retrieval with Textual Inversion
- Comparison between layer-to-layer network training and conventional network training using Deep Convolutional Neural Networks
- Manifold Learning by Mixture Models of VAEs for Inverse Problems
- Advances and Applications of Computer Vision Techniques in Vehicle Trajectory Generation and Surrogate Traffic Safety Indicators
- Interpretable machine learning of amino acid patterns in proteins: a statistical ensemble approach
- Asynchronous Online Federated Learning with Reduced Communication Requirements
- GP-PCS: One-shot Feature-Preserving Point Cloud Simplification with Gaussian Processes on Riemannian Manifolds
- How far generated data can impact Neural Networks performance?
- Knowing the Distance: Understanding the Gap Between Synthetic and Real Data For Face Parsing
- Evaluating XGBoost for Balanced and Imbalanced Data: Application to Fraud Detection
- Robust Risk-Aware Option Hedging
- Generalizable Denoising of Microscopy Images using Generative Adversarial Networks and Contrastive Learning
- Deep Ranking Ensembles for Hyperparameter Optimization
- On the Connection between Lp and Risk Consistency and its Implications on Regularized Kernel Methods
- Learning An Active Inference Model of Driver Perception and Control: Application to Vehicle Car-Following
- Probing optimisation in physics-informed neural networks
- CoCon: A Data Set on Combined Contextualized Research Artifact Use
- Evaluating self-attention interpretability through human-grounded experimental protocol
- Personalized Federated Learning on Long-Tailed Data via Adversarial Feature Augmentation
- Prompt-Guided Zero-Shot Anomaly Action Recognition using Pretrained Deep Skeleton Features
- Towards Artistic Image Aesthetics Assessment: a Large-scale Dataset and a New Method
- What Can Human Sketches Do for Object Detection?
- Pushing the Envelope for Depth-Based Semi-Supervised 3D Hand Pose Estimation with Consistency Training
- SimpleNet: A Simple Network for Image Anomaly Detection and Localization
- Cross-utterance ASR Rescoring with Graph-based Label Propagation
- NeuralPCI: Spatio-temporal Neural Field for 3D Point Cloud Multi-frame Non-linear Interpolation
- LMCanvas: Object-Oriented Interaction to Personalize Large Language Model-Powered Writing Environments
- Blind Inpainting with Object-aware Discrimination for Artificial Marker Removal
- Parameter Efficient Local Implicit Image Function Network for Face Segmentation
- Learning linear dynamical systems under convex constraints
- An ontology-aided, natural language-based approach for multi-constraint BIM model querying
- Automatic breach detection during spine pedicle drilling based on vibroacoustic sensing
- Describing and Organizing Semantic Web and Machine Learning Systems in the SWeMLS-KG
- Learning Attention as Disentangler for Compositional Zero-shot Learning
- Beyond Toxic: Toxicity Detection Datasets are Not Enough for Brand Safety
- Improving the Transferability of Adversarial Examples via Direction Tuning
- High-fidelity 3D Human Digitization from Single 2K Resolution Images
- Vision Transformer with Quadrangle Attention
- Generalizable Local Feature Pre-training for Deformable Shape Analysis
- Contrastive Learning Is Spectral Clustering On Similarity Graph
- DANI-Net: Uncalibrated Photometric Stereo by Differentiable Shadow Handling, Anisotropic Reflectance Modeling, and Neural Inverse Rendering
- An Information Extraction Study: Take In Mind the Tokenization!
- Towards secure judgments aggregation in AHP
- Defect detection using weakly supervised learning
- Prediction of Time and Distance of Trips Using Explainable Attention-based LSTMs
- Learning Action Changes by Measuring Verb-Adverb Textual Relationships
- Exemplar-based Video Colorization with Long-term Spatiotemporal Dependency
- Large Language Models are Diverse Role-Players for Summarization Evaluation
- Conjunction Data Messages for Space Collision Behave as a Poisson Process
- Exposing the Functionalities of Neurons for Gated Recurrent Unit Based Sequence-to-Sequence Model
- Intersection over Union with smoothing for bounding box regression
- Single-subject Multi-contrast MRI Super-resolution via Implicit Neural Representations
- The Devil is in the Points: Weakly Semi-Supervised Instance Segmentation via Point-Guided Mask Representation
- TMO: Textured Mesh Acquisition of Objects with a Mobile Device by using Differentiable Rendering
- Towards Unbiased Calibration using Meta-Regularization
- ChatGPT Outperforms Crowd-Workers for Text-Annotation Tasks
- Hyperparameter optimization, quantum-assisted model performance prediction, and benchmarking of AI-based High Energy Physics workloads using HPC
- InterviewBot: Real-Time End-to-End Dialogue System to Interview Students for College Admission
- Nighttime Smartphone Reflective Flare Removal Using Optical Center Symmetry Prior
- Joint Video Multi-Frame Interpolation and Deblurring under Unknown Exposure Time
- Partially Adaptive Multichannel Joint Reduction of Ego-noise and Environmental Noise
- Towards black-box parameter estimation
- Image Quality-aware Diagnosis via Meta-knowledge Co-embedding
- A Survey on Causal Discovery Methods for I.I.D. and Time Series Data
- An End-to-End Framework For Universal Lesion Detection With Missing Annotations
- ScarceNet: Animal Pose Estimation with Scarce Annotations
- Interactive Explanations by Conflict Resolution via Argumentative Exchanges
- Borrowing Human Senses: Comment-Aware Self-Training for Social Media Multimodal Classification
- Towards Open Temporal Graph Neural Networks
- Leveraging Hidden Positives for Unsupervised Semantic Segmentation
- 3D-Aware Multi-Class Image-to-Image Translation with NeRFs
- Architecturing Binarized Neural Networks for Traffic Sign Recognition
- Transformer-based Multi-Instance Learning for Weakly Supervised Object Detection
- Multi-view Cross-Modality MR Image Translation for Vestibular Schwannoma and Cochlea Segmentation
- Low-rank combinatorial optimization and statistical learning by spatial photonic Ising machine
- Regularized EM algorithm
- mSPD-NN: A Geometrically Aware Neural Framework for Biomarker Discovery from Functional Connectomics Manifolds
- Learned Image Compression with Mixed Transformer-CNN Architectures
- A novel Multi to Single Module for small object detection
- Universal Few-shot Learning of Dense Prediction Tasks with Visual Token Matching
- Blind Image Quality Assessment via Vision-Language Correspondence: A Multitask Learning Perspective
- Adaptive Federated Learning via New Entropy Approach
- Disruption Precursor Onset Time Study Based on Semi-supervised Anomaly Detection
- Learning a Deep Color Difference Metric for Photographic Images
- Variation and Instability in Dialect-Based Embedding Spaces
- Forget-free Continual Learning with Soft-Winning SubNetworks
- Diffusion Denoised Smoothing for Certified and Adversarial Robust Out-Of-Distribution Detection
- Ambiguity-Resistant Semi-Supervised Learning for Dense Object Detection
- unarXive 2022: All arXiv Publications Pre-Processed for NLP, Including Structured Full-Text and Citation Network
- Unified Text Structuralization with Instruction-tuned Language Models
- DyGait: Exploiting Dynamic Representations for High-performance Gait Recognition
- Improving Contextualized Topic Models with Negative Sampling
- On the Optimality of Misspecified Spectral Algorithms
- Explain, Adapt and Retrain: How to improve the accuracy of a PPM classifier through different explanation styles
- LEURN: Learning Explainable Univariate Rules with Neural Networks
- TabIQA: Table Questions Answering on Business Document Images
- Spatially Adaptive Self-Supervised Learning for Real-World Image Denoising
- MD-VQA: Multi-Dimensional Quality Assessment for UGC Live Videos
- Addressing the Challenges of Open-World Object Detection
- Continuous Intermediate Token Learning with Implicit Motion Manifold for Keyframe Based Motion Interpolation
- CAT:Collaborative Adversarial Training
- Adapting Pretrained Language Models for Solving Tabular Prediction Problems in the Electronic Health Record
- Identifying Suspicious Regions of Covid-19 by Abnormality-Sensitive Activation Mapping
- A Linear Weight Transfer Rule for Local Search
- Context-Aware Transformer for 3D Point Cloud Automatic Annotation
- Global Relation Modeling and Refinement for Bottom-Up Human Pose Estimation
- Text is All You Need: Personalizing ASR Models using Controllable Speech Synthesis
- A large-scale dataset for end-to-end table recognition in the wild
- TransCODE: Co-design of Transformers and Accelerators for Efficient Training and Inference
- GPT-PINN: Generative Pre-Trained Physics-Informed Neural Networks toward non-intrusive Meta-learning of parametric PDEs
- Quantum approximate optimization via learning-based adaptive optimization
- Optimal task and motion planning and execution for human-robot multi-agent systems in dynamic environments
- Coupling Artificial Neurons in BERT and Biological Neurons in the Human Brain
- Bi-Manual Block Assembly via Sim-to-Real Reinforcement Learning
- Label-Free Liver Tumor Segmentation
- The Resource Problem of Using Linear Layer Leakage Attack in Federated Learning
- Mind the Label Shift of Augmentation-based Graph OOD Generalization