Papers
Mon 6 Feb 2023
193 papers
- Protecting Language Generation Models via Invisible WatermarkingLLM safety and security → Watermarking generated content and models
- Techniques to Improve Neural Math Word Problem SolversLLM reasoning → Mathematical reasoning
- Traffic Shaping and Hysteresis Mitigation Using Deep Reinforcement Learning in a Connected Driving EnvironmentEnd-to-end autonomous driving → Cooperative and V2X driving
- DITTO: Offline Imitation Learning with World ModelsWorld models → Embodied and robot world models +1
- A Toy Model of Universality: Reverse Engineering How Networks Learn Group OperationsMechanistic interpretability → Circuits and mechanistic analysis
- DDM2: Self-Supervised Diffusion MRI Denoising with Generative Diffusion ModelsDiffusion models → Medical imaging and segmentation
- Structure and Content-Guided Video Synthesis with Diffusion ModelsWorld models → Video-generation world models and simulators +1
- Beyond Statistical Similarity: Rethinking Metrics for Deep Generative Models in Engineering DesignDiffusion models → Diffusion foundations and sampling
- Audio Representation Learning by Distilling Video as Privileged InformationKnowledge distillation → Speech and audio distillation
- A Strong Baseline for Batch Imitation LearningOffline RL and imitation learning from data → Imitation learning methods
- Chain of Hindsight Aligns Language Models with FeedbackLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
- Target-based Surrogates for Stochastic OptimizationOffline RL and imitation learning from data → Inverse reinforcement learning
- Generative Diffusion Models on Graphs: Methods and ApplicationsDiffusion models → Flow matching, time series and science
- Offline Learning in Markov Games with General Function ApproximationOffline RL and imitation learning from data → Offline RL algorithms
- An Implicit GNN Solver for Poisson-like problems
- Find a witness or shatter: the landscape of computable PAC learning
- Closed-loop Analysis of Vision-based Autonomous Systems: A Case Study
- Intrinsic Rewards from Self-Organizing Feature Maps for Exploration in Reinforcement Learning
- Industrial computed tomography based intelligent non-destructive testing method for power capacitor
- Optimization of Topology-Aware Job Allocation on a High-Performance Computing Cluster by Neural Simulated Annealing
- A Categorical Archive of ChatGPT Failures
- APAM: Adaptive Pre-training and Adaptive Meta Learning in Language Model for Noisy Labels and Long-tailed Learning
- PIER: Permutation-Level Interest-Based End-to-End Re-ranking Framework in E-commerce
- Data Selection for Language Models via Importance Resampling
- Optimization using Parallel Gradient Evaluations on Multiple Parameters
- A distribution-free mixed-integer optimization approach to hierarchical modelling of clustered and longitudinal data
- Novel Building Detection and Location Intelligence Collection in Aerial Satellite Imagery
- Fair Minimum Representation Clustering
- It's about Time: Rethinking Evaluation on Rumor Detection Benchmarks using Chronological Splits
- ClueGAIN: Application of Transfer Learning On Generative Adversarial Imputation Nets (GAIN)
- Predicting Development of Chronic Obstructive Pulmonary Disease and its Risk Factor Analysis
- Learned Accelerator Framework for Angular-Distance-Based High-Dimensional DBSCAN
- Domain Adaptation for Time Series Under Feature and Label Shifts
- Importance attribution in neural networks by means of persistence landscapes of time series
- Spatial Functa: Scaling Functa to ImageNet Classification and Generation
- Cooperverse: A Mobile-Edge-Cloud Framework for Universal Cooperative Perception with Mixed Connectivity and Automation
- Context-Gloss Augmentation for Improving Arabic Target Sense Verification
- Autodecompose: A generative self-supervised model for semantic decomposition
- State-wise Safe Reinforcement Learning: A Survey
- Studying Therapy Effects and Disease Outcomes in Silico using Artificial Counterfactual Tissue Samples
- Easy Learning from Label Proportions
- From CAD models to soft point cloud labels: An automatic annotation pipeline for cheaply supervised 3D semantic segmentation
- On the Convergence of Federated Averaging with Cyclic Client Participation
- Efficient and Flexible Topic Modeling using Pretrained Embeddings and Bag of Sentences
- One-shot Empirical Privacy Estimation for Federated Learning
- Dividing Good and Better Items Among Agents with Bivalued Submodular Valuations
- Pic2Word: Mapping Pictures to Words for Zero-shot Composed Image Retrieval
- Five policy uses of algorithmic transparency and explainability
- Evaluating Self-Supervised Learning via Risk Decomposition
- Memory-Based Meta-Learning on Non-Stationary Distributions
- Investigating Pulse-Echo Sound Speed Estimation in Breast Ultrasound with Deep Learning
- Single Cells Are Spatial Tokens: Transformers for Spatial Transcriptomic Data Imputation
- Zero-shot Image-to-Image Translation
- Sampling-Based Accuracy Testing of Posterior Estimators for General Inference
- AIM: Adapting Image Models for Efficient Video Action Recognition
- V1T: large-scale mouse V1 response prediction using a Vision Transformer
- SurgT challenge: Benchmark of Soft-Tissue Trackers for Robotic Surgery
- RLSbench: Domain Adaptation Under Relaxed Label Shift
- Exploring and Exploiting Decision Boundary Dynamics for Adversarial Robustness
- Detection and Localization of Melanoma Skin Cancer in Histopathological Whole Slide Images
- Quantum Circuit Components for Cognitive Decision-Making
- LAVA: Granular Neuron-Level Explainable AI for Alzheimer's Disease Assessment from Fundus Images
- Neural Collapse Inspired Feature-Classifier Alignment for Few-Shot Class Incremental Learning
- OTRE: Where Optimal Transport Guided Unpaired Image-to-Image Translation Meets Regularization by Enhancing
- Erasure of Unaligned Attributes from Neural Representations
- Optimal Transport Guided Unsupervised Learning for Enhancing low-quality Retinal Images
- Asymptotically Optimal Fixed-Budget Best Arm Identification with Variance-Dependent Bounds
- Robust Subtask Learning for Compositional Generalization
- Learning disentangled representations for explainable chest X-ray classification using Dirichlet VAEs
- MuG: A Multimodal Classification Benchmark on Game Data with Tabular, Textual, and Visual Fields
- ConvoWaste: An Automatic Waste Segregation Machine Using Deep Learning
- Concrete Safety for ML Problems: System Safety for ML Development and Assessment
- U-Clip: On-Average Unbiased Stochastic Gradient Clipping
- LoFT: Enhancing Faithfulness and Diversity for Table-to-Text Generation via Logic Form Control
- Noise-cleaning the precision matrix of fMRI time series
- Adaptive Parameterization of Deep Learning Models for Federated Learning
- Efficient Online Reinforcement Learning with Offline Data
- GPS++: Reviving the Art of Message Passing for Molecular Property Prediction
- Development of an Immersive Virtual Colonoscopy Viewer for Colon Growths Diagnosis
- Learning Complementary Policies for Human-AI Teams
- On Over-Squashing in Message Passing Neural Networks: The Impact of Width, Depth, and Topology
- Integrating Eye-Gaze Data into CXR DL Approaches: A Preliminary study
- Private GANs, Revisited
- Bitrate-Constrained DRO: Beyond Worst Case Robustness To Unknown Group Shifts
- Generating Evidential BEV Maps in Continuous Driving Space
- Curriculum Graph Machine Learning: A Survey
- Dropout Injection at Test Time for Post Hoc Uncertainty Quantification in Neural Networks
- In Search of Insights, Not Magic Bullets: Towards Demystification of the Model Selection Dilemma in Heterogeneous Treatment Effect Estimation
- Joint Edge-Model Sparse Learning is Provably Efficient for Graph Neural Networks
- Holistic Deep-Reinforcement-Learning-based Training of Autonomous Navigation Systems
- Energy-based Out-of-Distribution Detection for Graph Neural Networks
- An Empirical Analysis of Fairness Notions under Differential Privacy
- Spectral Augmentations for Graph Contrastive Learning
- LexLIP: Lexicon-Bottlenecked Language-Image Pre-Training for Large-Scale Image-Text Retrieval
- GAT: Guided Adversarial Training with Pareto-optimal Auxiliary Tasks
- Rethinking Gauss-Newton for learning over-parameterized models
- Controllable Lexical Simplification for English
- Arena-Web -- A Web-based Development and Benchmarking Platform for Autonomous Navigation Approaches
- Label Assisted Autoencoder for Anomaly Detection in Power Generation Plants
- Findings of the TSAR-2022 Shared Task on Multilingual Lexical Simplification
All 193
- UVDoc: Neural Grid-based Document Unwarping
- Intra-operative Brain Tumor Detection with Deep Learning-Optimized Hyperspectral Imaging
- Variational Information Pursuit for Interpretable Predictions
- Top-Down Beats Bottom-Up in 3D Instance Segmentation
- Probabilistic Contrastive Learning Recovers the Correct Aleatoric Uncertainty of Ambiguous Inputs
- Solving Maxwell's Equation in 2D with Neural Networks with Local Converging Inputs
- A Fast Bootstrap Algorithm for Causal Inference with Large Data
- TR3D: Towards Real-Time Indoor 3D Object Detection
- NA-SODINN: a deep learning algorithm for exoplanet image detection based on residual noise regimes
- Guide the Learner: Controlling Product of Experts Debiasing Method Based on Token Attribution Similarities
- An Unsupervised Framework for Joint MRI Super Resolution and Gibbs Artifact Removal
- Surrogate uncertainty estimation for your time series forecasting black-box: learn when to trust
- Collective Robustness Certificates: Exploiting Interdependence in Graph Neural Networks
- MixFormer: End-to-End Tracking with Iterative Mixed Attention
- Migration Reframed? A multilingual analysis on the stance shift in Europe during the Ukrainian crisis
- Federated Survival Forests
- Stop overkilling simple tasks with black-box models and use transparent models instead
- Dealing With Non-stationarity in Decentralized Cooperative Multi-Agent Deep Reinforcement Learning via Multi-Timescale Learning
- Perception Datasets for Anomaly Detection in Autonomous Driving: A Survey
- Generative models for two-ground-truth partitions in networks
- An intelligent tutor for planning in large partially observable environments
- Coherence and Diversity through Noise: Self-Supervised Paraphrase Generation via Structure-Aware Denoising
- The SSL Interplay: Augmentations, Inductive Bias, and Generalization
- Generalization Bounds with Data-dependent Fractal Dimensions
- Fine-Grained Action Detection with RGB and Pose Information using Two Stream Convolutional Networks
- Baseline Method for the Sport Task of MediaEval 2022 with 3D CNNs using Attention Mechanisms
- AMD-HookNet for Glacier Front Segmentation
- Residual Information in Deep Speaker Embedding Architectures
- INCREASE: Inductive Graph Representation Learning for Spatio-Temporal Kriging
- Root Laplacian Eigenmaps with their application in spectral embedding
- On Exact Sampling in the Two-Variable Fragment of First-Order Logic
- Multipath agents for modular multitask ML systems
- A Log-Linear Non-Parametric Online Changepoint Detection Algorithm based on Functional Pruning
- Differentiable Programming of Chemical Reaction Networks
- Flat Seeking Bayesian Neural Networks
- Network-Aided Intelligent Traffic Steering in 6G O-RAN: A Multi-Layer Optimization Framework
- When the Ground Truth is not True: Modelling Human Biases in Temporal Annotations
- PatchDCT: Patch Refinement for High Quality Instance Segmentation
- HyperSLICE: HyperBand optimized Spiral for Low-latency Interactive Cardiac Examination
- Identifiability of latent-variable and structural-equation models: from linear to nonlinear
- Random Forests for time-fixed and time-dependent predictors: The DynForest R package
- A Scalable and Efficient Iterative Method for Copying Machine Learning Classifiers
- Linking data separation, visual separation, and classifier performance using pseudo-labeling by contrastive learning
- Grounding Large Language Models in Interactive Environments with Online Reinforcement Learning
- Evolution of grammatical forms: some quantitative approaches
- L'explicabilit'e au service de l'extraction de connaissances : application `a des donn'ees m'edicales
- 1st Place Solution for PSG competition with ECCV'22 SenseHuman Workshop
- Tree-Based Learning on Amperometric Time Series Data Demonstrates High Accuracy for Classification
- First steps towards quantum machine learning applied to the classification of event-related potentials
- Models and algorithms for simple disjunctive temporal problems
- Approximation of radiative transfer for surface spectral features
- Hybrid Contrastive Constraints for Multi-Scenario Ad Ranking
- Toward a normative theory of (self-)management by goal-setting
- Trust, but Verify: Using Self-Supervised Probing to Improve Trustworthiness
- Uncertainty Calibration and its Application to Object Detection
- COVID-19 Infection Analysis Framework using Novel Boosted CNNs and Radiological Images
- Rethinking Out-of-distribution (OOD) Detection: Masked Image Modeling is All You Need
- A Pre-training Framework for Knowledge Graph Completion
- Improving Domain Generalization with Domain Relations
- Toward Large Kernel Models
- Learning Representations of Bi-level Knowledge Graphs for Reasoning beyond Link Prediction
- Colossal-Auto: Unified Automation of Parallelization and Activation Checkpoint for Large-scale Models
- Cluster-aware Contrastive Learning for Unsupervised Out-of-distribution Detection
- ProbPNN: Enhancing Deep Probabilistic Forecasting with Statistical Information
- Ten Lessons We Have Learned in the New "Sparseland": A Short Handbook for Sparse Neural Network Researchers
- Clarifying Trust of Materials Property Predictions using Neural Networks with Distribution-Specific Uncertainty Quantification
- z-SignFedAvg: A Unified Stochastic Sign-based Compression for Federated Learning
- Recommender Systems: A Primer
- Topology-aware Federated Learning in Edge Computing: A Comprehensive Survey
- Improved Policy Evaluation for Randomized Trials of Algorithmic Resource Allocation
- Less is More: Understanding Word-level Textual Adversarial Attack via n-gram Frequency Descend
- Bi-level Multi-objective Evolutionary Learning: A Case Study on Multi-task Graph Neural Topology Search
- Stochastic Gradient Descent-Induced Drift of Representation in a Two-Layer Neural Network
- Domain-Indexing Variational Bayes: Interpretable Domain Index for Domain Adaptation
- Causal Estimation of Exposure Shifts with Neural Networks
- Proposing Novel Extrapolative Compounds by Nested Variational Autoencoders
- A Correction-Based Dynamic Enhancement Framework towards Underwater Detection
- Adapting to Continuous Covariate Shift via Online Density Ratio Estimation
- CHiLS: Zero-Shot Image Classification with Hierarchical Label Sets
- Domain Re-Modulation for Few-Shot Generative Domain Adaptation
- Learning Trees of ℓ0-Minimization Problems
- A Quantum Neural Network Regression for Modeling Lithium-ion Battery Capacity Degradation
- Sequential change detection via backward confidence sequences
- PaRot: Patch-Wise Rotation-Invariant Network via Feature Disentanglement and Pose Restoration
- Cross-Fusion Rule for Personalized Federated Learning
- Learning Control-Oriented Dynamical Structure from Data
- Personalized Interpretable Classification
- On Private and Robust Bandits
- Novel Fundus Image Preprocessing for Retcam Images to Improve Deep Learning Classification of Retinopathy of Prematurity
- Prior Density Learning in Variational Bayesian Phylogenetic Parameters Inference
- Exploiting Partial Common Information Microstructure for Multi-Modal Brain Tumor Segmentation
- RDFNet: Regional Dynamic FISTA-Net for Spectral Snapshot Compressive Imaging
- Deep Learning for Time Series Classification and Extrinsic Regression: A Current Survey