Papers
Fri 23 Sep 2022
127 papers
- Variational Open-Domain Question AnsweringRetrieval-augmented generation → Generation and context integration
- JPEG Artifact Correction using Denoising Diffusion Restoration ModelsDiffusion models → Inverse problems and image restoration
- Privacy-Preserving Online Content Moderation: A Federated Learning Use CaseLLM safety and security → Federated unlearning and poisoning
- Descriptor Distillation: a Teacher-Student-Regularized Framework for Learning Local DescriptorsKnowledge distillation → General knowledge distillation methods
- Best Prompts for Text-to-Image Models and How to Find ThemDiffusion models → Image generation, text-to-image and editing
- LEADER: Learning Attention over Driving Behaviors for Planning under UncertaintyEnd-to-end autonomous driving → Imitation-learning end-to-end planners
- DeepVol: Volatility Forecasting from High-Frequency Data with Dilated Causal Convolutions
- Predicting the Future of AI with AI: High-quality link prediction in an exponentially growing knowledge network
- Ensemble-based gradient inference for particle methods in optimization and sampling
- Exact Recovery of Community Detection in dependent Gaussian Mixture Models
- Faith: An Efficient Framework for Transformer Verification on GPUs
- Accurate and Efficient Stereo Matching via Attention Concatenation Volume
- Leveraging the Potential of Novel Data in Power Line Communication of Electricity Grids
- Soft-labeling Strategies for Rapid Sub-Typing
- Recent trends and analysis of Generative Adversarial Networks in Cervical Cancer Imaging
- Deontic Meta-Rules
- Whodunit? Learning to Contrast for Authorship Attribution
- Physics-Informed Graph Neural Network for Spatial-temporal Production Forecasting
- Hebbian Deep Learning Without Feedback
- Enhancing Data Diversity for Self-training Based Unsupervised Cross-modality Vestibular Schwannoma and Cochlea Segmentation
- Tighter Variational Bounds are Not Necessarily Better. A Research Report on Implementation, Ablation Study, and Extensions
- Cem Mil Podcasts: A Spoken Portuguese Document Corpus For Multi-modal, Multi-lingual and Multi-Dialect Information Access Research
- Leveraging Self-Supervised Training for Unintentional Action Recognition
- Transformer-Based Microbubble Localization
- Wide-Area Geolocalization with a Limited Field of View Camera
- KeypartX: Graph-based Perception (Text) Representation
- Comparison of Lexical Alignment with a Teachable Robot in Human-Robot and Human-Human-Robot Interactions
- Doubly Fair Dynamic Pricing
- Creating Compact Regions of Social Determinants of Health
- Multiple-Choice Question Generation: Towards an Automated Assessment Framework
- M2TRec: Metadata-aware Multi-task Transformer for Large-scale and Cold-start free Session-based Recommendations
- Expanding the Deployment Envelope of Behavior Prediction via Adaptive Meta-Learning
- An Efficient Algorithm for Fair Multi-Agent Multi-Armed Bandit with Low Regret
- Explanations, Fairness, and Appropriate Reliance in Human-AI Decision-Making
- Periodic Graph Transformers for Crystal Material Property Prediction
- Augmenting Interpretable Models with LLMs during Training
- Composite Convolution: a Flexible Operator for Deep Learning on 3D Point Clouds
- A Neural Template Matching Method to Detect Knee Joint Areas
- SAFER: Safe Collision Avoidance using Focused and Efficient Trajectory Search with Reinforcement Learning
- Tiered Pruning for Efficient Differentialble Inference-Aware Neural Architecture Search
- A direct time-of-flight image sensor with in-pixel surface detection and dynamic vision
- Toward Smart Doors: A Position Paper
- Promptagator: Few-shot Dense Retrieval From 8 Examples
- GLSO: Grammar-guided Latent Space Optimization for Sample-efficient Robot Design Automation
- Unified Algorithms for RL with Decision-Estimation Coefficients: PAC, Reward-Free, Preference-Based Learning, and Beyond
- Visual representations in the human brain are aligned with large language models
- Dual-Cycle: Self-Supervised Dual-View Fluorescence Microscopy Image Reconstruction using CycleGAN
- Boost CTR Prediction for New Advertisements via Modeling Visual Content
- Temporal Analysis on Topics Using Word2Vec
- The "Beatrix'' Resurrections: Robust Backdoor Detection via Gram Matrices
- Multivariate Wasserstein Functional Connectivity for Autism Screening
- Linear Multidimensional Regression with Interactive Fixed-Effects
- PNeRF: Probabilistic Neural Scene Representations for Uncertain 3D Visual Mapping
- Image-to-Image Translation for Autonomous Driving from Coarsely-Aligned Image Pairs
- Exact conservation laws for neural network integrators of dynamical systems
- View-Invariant Skeleton-based Action Recognition via Global-Local Contrastive Learning
- From Weakly Supervised Learning to Active Learning
- A Neural Model for Regular Grammar Induction
- The SpeakIn Speaker Verification System for Far-Field Speaker Verification Challenge 2022
- Robust Domain Adaptation for Machine Reading Comprehension
- Differentiable physics-enabled closure modeling for Burgers' turbulence
- I-SPLIT: Deep Network Interpretability for Split Computing
- Neural Clamping: Joint Input Perturbation and Temperature Scaling for Neural Network Calibration
- Machine Learning and Analytical Power Consumption Models for 5G Base Stations
- Quantification before Selection: Active Dynamics Preference for Robust Reinforcement Learning
- Differentially private partitioned variational inference
- involve-MI: Informative Planning with High-Dimensional Non-Parametric Beliefs
- Learning Articulated Rigid Body Dynamics with Lagrangian Graph Neural Network
- Multi-Granularity Graph Pooling for Video-based Person Re-Identification
- Pose-Aided Video-based Person Re-Identification via Recurrent Graph Convolutional Network
- Towards Complete-View and High-Level Pose-based Gait Recognition
- Multi-Modal Cross-Domain Alignment Network for Video Moment Retrieval
- Query-based Hard-Image Retrieval for Object Detection at Test Time
- Applications of Machine Learning in Chemical and Biological Oceanography
- On Efficient Reinforcement Learning for Full-length Game of StarCraft II
- MAGIC: Mask-Guided Image Synthesis by Inverting a Quasi-Robust Classifier
- Quantile-constrained Wasserstein projections for robust interpretability of numerical and machine learning models
- An Interdisciplinary Perspective on Evaluation and Experimental Design for Visual Text Analytics: Position Paper
- A Unified Perspective on Natural Gradient Variational Inference with Gaussian Mixture Models
- Deep Learning-based Anonymization of Chest Radiographs: A Utility-preserving Measure for Patient Privacy
- An artificial neural network-based system for detecting machine failures using tiny sound data: A case study
- Statistical shape representations for temporal registration of plant components in 3D
- WS-3D-Lane: Weakly Supervised 3D Lane Detection With 2D Lane Labels
- Power Management in Smart Residential Building with Deep Learning Model for Occupancy Detection by Usage Pattern of Electric Appliances
- Vector Quantized Semantic Communication System
- Marine Video Kit: A New Marine Video Dataset for Content-based Analysis and Retrieval
- Error Mitigation-Aided Optimization of Parameterized Quantum Circuits: Convergence Analysis
- The complexity of unsupervised learning of lexicographic preferences
- Time Series Causal Link Estimation under Hidden Confounding using Knockoff Interventions
- Image Classification using Sequence of Pixels
- Comparison of synthetic dataset generation methods for medical intervention rooms using medical clothing detection as an example
- Grouped Adaptive Loss Weighting for Person Search
- GIDP: Learning a Good Initialization and Inducing Descriptor Post-enhancing for Large-scale Place Recognition
- MetaPrompting: Learning to Learn Better Prompts
- ET5: A Novel End-to-end Framework for Conversational Machine Reading Comprehension
- Active Few-Shot Classification: a New Paradigm for Data-Scarce Learning Settings
- Weakly Supervised Two-Stage Training Scheme for Deep Video Fight Detection Model
- Unsupervised Hashing with Semantic Concept Mining
- Optimizing Class Distribution in Memory for Multi-Label Online Continual Learning
- Smart Active Sampling to enhance Quality Assurance Efficiency
All 127
- TeST: Test-time Self-Training under Distribution Shift
- Segmentation-based Information Extraction and Amalgamation in Fundus Images for Glaucoma Detection
- Modular Degradation Simulation and Restoration for Under-Display Camera
- A Preliminary Investigation of MLOps Practices in GitHub
- Motion Guided Deep Dynamic 3D Garments
- Rethinking Performance Gains in Image Dehazing Networks
- Understanding Open-Set Recognition by Jacobian Norm and Inter-Class Separation
- Learning to screen Glaucoma like the ophthalmologists
- News Category Dataset
- A Robust and Explainable Data-Driven Anomaly Detection Approach For Power Electronics
- Enabling Homogeneous GNNs to Handle Heterogeneous Graphs via Relation Embedding
- Zero-shot Domain Adaptation for Neural Machine Translation with Retrieved Phrase-level Prompts
- IDEA: Interactive DoublE Attentions from Label Embedding for Text Classification
- Towards Frame Rate Agnostic Multi-Object Tracking
- Feature selection in stratification estimators of causal effects: lessons from potential outcomes, causal diagrams, and structural equations
- Conversational QA Dataset Generation with Answer Revision
- Achieve the Minimum Width of Neural Networks for Universal Approximation
- LGDN: Language-Guided Denoising Network for Video-Language Modeling
- Improving Conversational Recommender System via Contextual and Time-Aware Modeling with Less Domain-Specific Knowledge
- Do Current Multi-Task Optimization Methods in Deep Learning Even Help?
- Extending Word-Level Quality Estimation for Post-Editing Assistance
- Tensor-Based Multi-Modality Feature Selection and Regression for Alzheimer's Disease Diagnosis
- Jensen-Shannon Divergence Based Novel Loss Functions for Bayesian Neural Networks
- CUTS: A Deep Learning and Topological Framework for Multigranular Unsupervised Medical Image Segmentation
- NasHD: Efficient ViT Architecture Performance Ranking using Hyperdimensional Computing
- Learning Interpretable Dynamics from Images of a Freely Rotating 3D Rigid Body
- Convolutional Learning on Multigraphs