Papers
Tue 4 Oct 2022
216 papers
- Domain Discrepancy Aware Distillation for Model Aggregation in Federated LearningKnowledge distillation → Federated, robust and private distillation
- When and why vision-language models behave like bags-of-words, and what to do about it?Multimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
- Differentiable Raycasting for Self-supervised Occupancy ForecastingWorld models → World models for autonomous driving
- Learning Perception-Aware Agile Flight in Cluttered EnvironmentsOffline RL and imitation learning from data → Imitation learning methods
- Maximum-Likelihood Inverse Reinforcement Learning with Finite-Time GuaranteesOffline RL and imitation learning from data → Inverse reinforcement learning
- Learning from Demonstrations of Critical Driving Behaviours Using Driver's Risk FieldEnd-to-end autonomous driving → Imitation-learning end-to-end planners +1
- Diffusion Models for Graphs Benefit From Discrete State SpacesDiffusion models → Flow matching, time series and science
- Knowledge Unlearning for Mitigating Privacy Risks in Language ModelsLLM safety and security → Machine unlearning
- Extraneousness-Aware Imitation LearningOffline RL and imitation learning from data → Imitation learning methods
- ThinkSum: Probabilistic reasoning over sets using large language modelsLLM reasoning → Test-time compute and efficient thinking
- Structural Estimation of Markov Decision Processes in High-Dimensional State Space with Finite-Time GuaranteesOffline RL and imitation learning from data → Inverse reinforcement learning
- Incentivising cooperation by rewarding the weakest member
- Double Attention-based Lightweight Network for Plant Pest Recognition
- An Improved Multi-State Constraint Kalman Filter for Visual-Inertial Odometry
- A Low-cost Humanoid Prototype Intended to assist people with disability using Raspberry Pi
- Predictive Event Segmentation and Representation with Neural Networks: A Self-Supervised Model Assessed by Psychological Experiments
- Robustness Certification of Visual Perception Models via Camera Motion Smoothing
- Stateful active facilitator: Coordination and Environmental Heterogeneity in Cooperative Multi-Agent Reinforcement Learning
- NeuDep: Neural Binary Memory Dependence Analysis
- Machine learning in bioprocess development: From promise to practice
- MTSMAE: Masked Autoencoders for Multivariate Time-Series Forecasting
- Are All Losses Created Equal: A Neural Collapse Perspective
- A Generalizable Artificial Intelligence Model for COVID-19 Classification Task Using Chest X-ray Radiographs: Evaluated Over Four Clinical Datasets with 15,097 Patients
- CFL-Net: Image Forgery Localization Using Contrastive Learning
- DISCOVER: Deep identification of symbolically concise open-form PDEs via enhanced reinforcement-learning
- Split Federated Learning on Micro-controllers: A Keyword Spotting Showcase
- Detect, Retrieve, Comprehend: A Flexible Framework for Zero-Shot Document-Level Question Answering
- Learning Dynamic Abstract Representations for Sample-Efficient Reinforcement Learning
- Robust Fair Clustering: A Novel Fairness Attack and Defense Framework
- Affection: Learning Affective Explanations for Real-World Visual Data
- A Framework for Large Scale Synthetic Graph Dataset Generation
- IGNiteR: News Recommendation in Microblogging Applications (Extended Version)
- SIMPLE: A Gradient Estimator for k-Subset Sampling
- On the Robustness of Deep Clustering Models: Adversarial Attacks and Defenses
- Regression-Based Elastic Metric Learning on Shape Spaces of Elastic Curves
- Benchmarking Learnt Radio Localisation under Distribution Shift
- Convex and Nonconvex Sublinear Regression with Application to Data-driven Learning of Reach Sets
- Nonparametric and Regularized Dynamical Wasserstein Barycenters for Sequential Observations
- Grounding Language with Visual Affordances over Unstructured Data
- Learning Signal Temporal Logic through Neural Network for Interpretable Classification
- Supervised Metric Learning to Rank for Retrieval via Contextual Similarity Optimization
- A Self-Play Posterior Sampling Algorithm for Zero-Sum Markov Games
- Tree Mover's Distance: Bridging Graph Metrics and Stability of Graph Neural Networks
- Polar Encoding: A Simple Baseline Approach for Classification with Missing Values
- Replicable Bandits
- Polysemanticity and Capacity in Neural Networks
- Adaptively Weighted Data Augmentation Consistency Regularization for Robust Optimization under Concept Shift
- Bicriteria Approximation Algorithms for Priority Matroid Median
- Collecting The Puzzle Pieces: Disentangled Self-Driven Human Pose Transfer by Permuting Textures
- Multi-view Human Body Mesh Translator
- Self-supervised Pre-training for Semantic Segmentation in an Indoor Scene
- Contrastive Learning Can Find An Optimal Basis For Approximately View-Invariant Functions
- A Collaborative Approach to the Analysis of the COVID-19 Response in Africa
- Tractable Uncertainty-Aware Meta-Learning
- A Perceptual Quality Metric for Video Frame Interpolation
- Opportunistic Qualitative Planning in Stochastic Systems with Incomplete Preferences over Reachability Objectives
- Towards Improving Faithfulness in Abstractive Summarization
- Memory in humans and deep language models: Linking hypotheses for model augmentation
- Capturing and Animation of Body and Clothing from Monocular Video
- Recycling Scraps: Improving Private Learning by Leveraging Intermediate Checkpoints
- Group Personalized Federated Learning
- ProtoBandit: Efficient Prototype Selection via Multi-Armed Bandits
- Centerpoints Are All You Need in Overhead Imagery
- Multifaceted Hierarchical Report Identification for Non-Functional Bugs in Deep Learning Frameworks
- Explaining Patterns in Data with Language Models via Interpretable Autoprompting
- Detecting Anomalies within Smart Buildings using Do-It-Yourself Internet of Things
- Invariant Aggregator for Defending against Federated Backdoor Attacks
- MOAT: Alternating Mobile Convolution and Attention Brings Strong Vision Models
- TripleE: Easy Domain Generalization via Episodic Replay
- Low-Light Image Restoration Based on Retina Model using Neural Networks
- Implicit Warping for Animation with Image Sets
- Sampling Streaming Data with Parallel Vector Quantization -- PVQ
- Real-Time Monitoring of User Stress, Heart Rate and Heart Rate Variability on Mobile Devices
- Goal Misgeneralization: Why Correct Specifications Aren't Enough For Correct Goals
- Robust self-healing prediction model for high dimensional data
- Rethinking Lipschitz Neural Networks and Certified Robustness: A Boolean Function Perspective
- TabLeak: Tabular Data Leakage in Federated Learning
- COARSE3D: Class-Prototypes for Contrastive Learning in Weakly-Supervised 3D Point Cloud Segmentation
- COPILOT: Human-Environment Collision Prediction and Localization from Egocentric Videos
- Perspective Aware Road Obstacle Detection
- DiffDock: Diffusion Steps, Twists, and Turns for Molecular Docking
- One Transformer Can Understand Both 2D & 3D Molecular Data
- A Framework for Web Services Retrieval Using Bio Inspired Clustering
- Evaluating Disentanglement in Generative Models Without Knowledge of Latent Factors
- HYPRO: A Hybridly Normalized Probabilistic Model for Long-Horizon Prediction of Event Sequences
- Modular Approach to Machine Reading Comprehension: Mixture of Task-Aware Experts
- Lightweight Strategy for XOR PUFs as Security Primitives for Resource-constrained IoT device
- Making Decisions under Outcome Performativity
- CADet: Fully Self-Supervised Out-Of-Distribution Detection With Contrastive Learning
- Neural Conservation Laws: A Divergence-Free Perspective
- ASIF: Coupled Data Turns Unimodal Models to Multimodal Without Training
- Using Entropy Measures for Monitoring the Evolution of Activity Patterns
- Text Characterization Toolkit
- MEDFAIR: Benchmarking Fairness for Medical Imaging
- Dense Prediction Transformer for Scale Estimation in Monocular Visual Odometry
- MBW: Multi-view Bootstrapping in the Wild
- Learning Temporal Resolution in Spectrogram for Audio Classification
- Anatomically constrained CT image translation for heterogeneous blood vessel segmentation
- Exploring Parameter-Efficient Fine-Tuning to Enable Foundation Models in Federated Learning
- Multiple Instance Learning for Detecting Anomalies over Sequential Real-World Datasets
All 216
- A Fuzzy Logic-based Cascade Control without Actuator Saturation for the Unmanned Underwater Vehicle Trajectory Tracking
- Improving Label-Deficient Keyword Spotting Through Self-Supervised Pretraining
- HandFlow: Quantifying View-Dependent 3D Ambiguity in Two-Hand Reconstruction with Normalizing Flow
- Adaptive Synaptic Failure Enables Sampling from Posterior Predictive Distributions in the Brain
- Vision-based Warning System for Maintenance Personnel on Short-Term Roadwork Site
- Blockchain-Based Decentralized Knowledge Marketplace Using Active Inference
- Deep Learning-based Facial Appearance Simulation Driven by Surgically Planned Craniomaxillofacial Bony Movement
- New Machine Learning Techniques for Simulation-Based Inference: InferoStatic Nets, Kernel Score Estimation, and Kernel Likelihood Ratio Estimation
- Detection and Evaluation of Clusters within Sequential Data
- Robust Target Training for Multi-Source Domain Adaptation
- Bringing motion taxonomies to continuous domains via GPLVM on hyperbolic manifolds
- Public Transit Arrival Prediction: a Seq2Seq RNN Approach
- SelfNeRF: Fast Training NeRF for Human from Monocular Self-rotating Video
- Robotic Learning the Sequence of Packing Irregular Objects from Human Demonstrations
- Mixup for Test-Time Training
- SecureFedYJ: a safe feature Gaussianization protocol for Federated Learning
- Explanation-by-Example Based on Item Response Theory
- Mining Duplicate Questions of Stack Overflow
- Type theory in human-like learning and inference
- Log-Linear-Time Gaussian Processes Using Binary Tree Kernels
- Backdoor Attacks in the Supply Chain of Masked Image Modeling
- Predicting the traffic flux in the city of Valencia with Deep Learning
- Monte Carlo Tree Search based Variable Selection for High Dimensional Bayesian Optimization
- Energy Consumption of Neural Networks on NVIDIA Edge Boards: an Empirical Model
- SAM as an Optimal Relaxation of Bayes
- Location-aware green energy availability forecasting for multiple time frames in smart buildings: The case of Estonia
- On Background Bias in Deep Metric Learning
- Mintaka: A Complex, Natural, and Multilingual Dataset for End-to-End Question Answering
- PlaneDepth: Self-supervised Depth Estimation via Orthogonal Planes
- A Generative Shape Compositional Framework to Synthesise Populations of Virtual Chimaeras
- Neural-Symbolic Recursive Machine for Systematic Generalization
- Self-improving Multiplane-to-layer Images for Novel View Synthesis
- Positive Pair Distillation Considered Harmful: Continual Meta Metric Learning for Lifelong Object Re-Identification
- ROAD-R: The Autonomous Driving Dataset with Logical Requirements
- FreDSNet: Joint Monocular Depth and Semantic Segmentation with Fast Fourier Convolutions
- Cross-Geography Generalization of Machine Learning Methods for Classification of Flooded Regions in Aerial Images
- How Image Generation Helps Visible-to-Infrared Person Re-Identification?
- FRIDA: Fisheye Re-Identification Dataset with Annotations
- Cooperative Self-Training for Multi-Target Adaptive Semantic Segmentation
- VICRegL: Self-Supervised Learning of Local Visual Features
- Causal Intervention-based Prompt Debiasing for Event Argument Extraction
- Amortized Bayesian Inference of GISAXS Data with Normalizing Flows
- Hyperbolic Deep Reinforcement Learning
- Analysis of the performance of U-Net neural networks for the segmentation of living cells
- Multi-fidelity Monte Carlo: a pseudo-marginal approach
- Concise and interpretable multi-label rule sets
- ProDMPs: A Unified Perspective on Dynamic and Probabilistic Movement Primitives
- Integrating pre-processing pipelines in ODC based framework
- DIAGNOSE: Avoiding Out-of-distribution Data using Submodular Information Measures
- Handling Sparse Rewards in Reinforcement Learning Using Model Predictive Control
- CLINICAL: Targeted Active Learning for Imbalanced Medical Image Classification
- Automatic Generation of Product Concepts from Positive Examples, with an Application to Music Streaming
- The Dynamics of Sharpness-Aware Minimization: Bouncing Across Ravines and Drifting Towards Wide Minima
- Code-Switching without Switching: Language Agnostic End-to-End Speech Translation
- How Masterly Are People at Playing with Their Vocabulary? Analysis of the Wordle Game for Latvian
- How deep convolutional neural networks lose spatial information with training
- Enhancing Spatiotemporal Prediction Model using Modular Design and Beyond
- Zeroth-Order Negative Curvature Finding: Escaping Saddle Points without Gradients
- Generative Models and Learning Algorithms for Core-Periphery Structured Graphs
- APAUNet: Axis Projection Attention UNet for Small Target in 3D Medical Segmentation
- Estimating the hardness of SAT encodings for Logical Equivalence Checking of Boolean circuits
- When to Make Exceptions: Exploring Language Models as Accounts of Human Moral Judgment
- Learning-based Design of Luenberger Observers for Autonomous Nonlinear Systems
- Geo-imagery management and statistical processing in a regional context using Open Data Cube
- Learning from the Best: Contrastive Representations Learning Across Sensor Locations for Wearable Activity Recognition
- A Compact Model of Interface-Type Memristors Linking Physical and Device Properties
- Federated Reinforcement Learning for Real-Time Electric Vehicle Charging and Discharging Control
- Certified Data Removal in Sum-Product Networks
- Rhythmic Gesticulator: Rhythm-Aware Co-Speech Gesture Synthesis with Hierarchical Neural Embeddings
- A Novel Light Field Coding Scheme Based on Deep Belief Network & Weighted Binary Images for Additive Layered Displays
- Boosting Few-shot Fine-grained Recognition with Background Suppression and Foreground Alignment
- Complementary consistency semi-supervised learning for 3D left atrial image segmentation
- Non-learning Stereo-aided Depth Completion under Mis-projection via Selective Stereo Matching
- Accurate Image Restoration with Attention Retractable Transformer
- Continuous Monte Carlo Graph Search
- Unveiling the Black Box of PLMs with Semantic Anchors: Towards Interpretable Neural Semantic Parsing
- Using Deep Reinforcement Learning for mmWave Real-Time Scheduling
- Time-Varying Propensity Score to Bridge the Gap between the Past and Present
- Tikhonov Regularization is Optimal Transport Robust under Martingale Constraints
- Selection by Prediction with Conformal p-values
- Homotopy-based training of NeuralODEs for accurate dynamics discovery
- Streaming Video Analytics On The Edge With Asynchronous Cloud Support
- Linear Convergence of Natural Policy Gradient Methods with Log-Linear Policies
- Bridged Transformer for Vision and Point Cloud 3D Object Detection
- Toward Edge-Efficient Dense Predictions with Synergistic Multi-Task Neural Architecture Search
- Generalizing Bayesian Optimization with Decision-theoretic Entropies
- Improved High-Probability Regret for Adversarial Bandits with Time-Varying Feedback Graphs
- A Study on the Efficiency and Generalization of Light Hybrid Retrievers
- Towards Flexible Inductive Bias via Progressive Reparameterization Scheduling
- RAP: Risk-Aware Prediction for Robust Planning
- Connecting Surrogate Safety Measures to Crash Probablity via Causal Probabilistic Time Series Prediction
- Uncertainty-Aware Lidar Place Recognition in Novel Environments
- Learning an Invertible Output Mapping Can Mitigate Simplicity Bias in Neural Networks
- Pay Self-Attention to Audio-Visual Navigation
- Less is More: Task-aware Layer-wise Distillation for Language Model Compression
- Distance Based Image Classification: A solution to generative classification's conundrum?
- Fast Saturating Gate for Learning Long Time Scales with Recurrent Neural Networks
- ImmFusion: Robust mmWave-RGB Fusion for 3D Human Body Reconstruction in All Weather Conditions
- Movement Analytics: Current Status, Application to Manufacturing, and Future Prospects from an AI Perspective
- The Surprising Computational Power of Nondeterministic Stack RNNs
- Learning to Collocate Visual-Linguistic Neural Modules for Image Captioning
- Active Learning for Regression with Aggregated Outputs
- Automated Medical Device Display Reading Using Deep Learning Object Detection
- ASAP: Accurate semantic segmentation for real time performance
- Representing Spatial Trajectories as Distributions
- OpBoost: A Vertical Federated Tree Boosting Framework Based on Order-Preserving Desensitization
- Concurrent build direction, part segmentation, and topology optimization for additive manufacturing using neural networks
- Beam Management in Ultra-dense mmWave Network via Federated Reinforcement Learning: An Intelligent and Secure Approach
- Nuisances via Negativa: Adjusting for Spurious Correlations via Data Augmentation
- GIDN: A Lightweight Graph Inception Diffusion Network for High-efficient Link Prediction
- Revealing Unobservables by Deep Learning: Generative Element Extraction Networks (GEEN)
- Centroid Distance Keypoint Detector for Colored Point Clouds
- Recitation-Augmented Language Models
- Max-Quantile Grouped Infinite-Arm Bandits
- Strength-Adaptive Adversarial Training
- Robot Task Planning and Situation Handling in Open Worlds