Papers
Fri 30 Sep 2022
239 papers
- Self-Distillation for Further Pre-training of TransformersKnowledge distillation → General knowledge distillation methods
- Adversarial Robustness of Representation Learning for Knowledge GraphsLLM safety and security → Backdoor and data poisoning attacks
- VIP: Towards Universal Visual Reward and Representation via Value-Implicit Pre-TrainingOffline RL and imitation learning from data → Robot manipulation imitation learning
- B2RL: An open-source Dataset for Building Batch Reinforcement LearningOffline RL and imitation learning from data → Offline RL algorithms
- Protein structure generation via folding diffusionDiffusion models → Flow matching, time series and science
- Designing and Training of Lightweight Neural Networks on Edge Devices using Early Halting in Knowledge DistillationKnowledge distillation → General knowledge distillation methods
- Towards a Unified View of Affinity-Based Knowledge DistillationKnowledge distillation → General knowledge distillation methods
- Medical Image Understanding with Pretrained Vision Language Models: A Comprehensive StudyMultimodal LLMs / vision-language models → Medical vision-language models
- Using Knowledge Distillation to improve interpretable models in a retail banking contextKnowledge distillation → General knowledge distillation methods
- Zero-Shot Retrieval with Search Agents and Hybrid EnvironmentsLLM agents and tool use → Web, search, and research agents
- TabDDPM: Modelling Tabular Data with Diffusion ModelsDiffusion models → Flow matching, time series and science
- Machine Unlearning Method Based On Projection ResidualLLM safety and security → Machine unlearning
- ERNIE-ViL 2.0: Multi-view Contrastive Learning for Image-Text Pre-trainingMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
- Data Poisoning Attacks Against Multimodal EncodersLLM safety and security → Vision-language and text-to-image safety
- Diffusion-based Image Translation using Disentangled Style and Content RepresentationDiffusion models → Image generation, text-to-image and editing
- S2P: State-conditioned Image Synthesis for Data Augmentation in Offline Reinforcement LearningOffline RL and imitation learning from data → Offline RL algorithms
- Mixture of experts models for multilevel data: modelling framework and approximation theoryMixture-of-experts → MoE theory and gating functions
- An Interactive Interpretability System for Breast Cancer Screening with Deep Learning
- Prioritizing emergency evacuations under compounding levels of uncertainty
- FAIR for AI: An interdisciplinary and international community building perspective
- Towards a Fully Autonomous UAV Controller for Moving Platform Detection and Landing
- A Survey on Knowledge Graph-based Methods for Automated Driving
- Machine learning frontier orbital energies of nanodiamonds
- Intra-session Context-aware Feed Recommendation in Live Systems
- A Sequence-Aware Recommendation Method Based on Complex Networks
- Multimodality Multi-Lead ECG Arrhythmia Classification using Self-Supervised Learning
- Blockchain-based Monitoring for Poison Attack Detection in Decentralized Federated Learning
- Evaluate & Evaluation on the Hub: Better Best Practices for Data and Model Measurements
- BayesFT: Bayesian Optimization for Fault Tolerant Neural Network Architecture
- Mind Reader: Reconstructing complex images from brain activities
- Disentanglement with Biological Constraints: A Theory of Functional Cell Types
- Model error and its estimation, with particular application to loss reserving
- Robust Q-learning Algorithm for Markov Decision Processes under Wasserstein Uncertainty
- On Best-Arm Identification with a Fixed Budget in Non-Parametric Multi-Armed Bandits
- A Novel Explainable Out-of-Distribution Detection Approach for Spiking Neural Networks
- Combining Efficient and Precise Sign Language Recognition: Good pose estimation library is all you need
- Information Removal at the bottleneck in Deep Neural Networks
- Efficiently Learning Small Policies for Locomotion and Manipulation
- IMB-NAS: Neural Architecture Search for Imbalanced Datasets
- Alignment-guided Temporal Attention for Video Action Recognition
- Underspecification in Language Modeling Tasks: A Causality-Informed Study of Gendered Pronoun Resolution
- An In-depth Study of Stochastic Backpropagation
- Robust Person Identification: A WiFi Vision-based Approach
- Implicit Neural Spatial Representations for Time-dependent PDEs
- Visuo-Tactile Transformers for Manipulation
- NTFields: Neural Time Fields for Physics-Informed Robot Motion Planning
- Blind Signal Dereverberation for Machine Speech Recognition
- Predicting Cellular Responses with Variational Causal Inference and Refined Relational Information
- Institutional Foundations of Adaptive Planning: Exploration of Flood Planning in the Lower Rio Grande Valley, Texas, USA
- ImpNet: Imperceptible and blackbox-undetectable backdoors in compiled neural networks
- Contrastive Corpus Attribution for Explaining Representations
- A Decade of Knowledge Graphs in Natural Language Processing: A Survey
- MLPInit: Embarrassingly Simple GNN Training Acceleration with MLP Initialization
- Image-Based Detection of Modifications in Gas Pump PCBs with Deep Convolutional Autoencoders
- Safety-Critical Adaptation in Self-Adaptive Systems
- Improving Robustness with Adaptive Weight Decay
- Federated Training of Dual Encoding Models on Small Non-IID Client Datasets
- Factorized Fusion Shrinkage for Dynamic Relational Data
- Data-driven discovery of non-Newtonian astronomy via learning non-Euclidean Hamiltonian
- A Multi-label Time Series Classification Approach for Non-intrusive Water End-Use Monitoring
- D-Align: Dual Query Co-attention Network for 3D Object Detection Based on Multi-frame Point Cloud Sequence
- Contrastive Graph Few-Shot Learning
- Causal Estimation for Text Data with (Apparent) Overlap Violations
- E-Branchformer: Branchformer with Enhanced merging for speech recognition
- Leveraging Industry 4.0 -- Deep Learning, Surrogate Model and Transfer Learning with Uncertainty Quantification Incorporated into Digital Twin for Nuclear System
- Digital Twin and Artificial Intelligence Incorporated With Surrogate Modeling for Hybrid and Sustainable Energy Systems
- Topological Singularity Detection at Multiple Scales
- Multi-Task Option Learning and Discovery for Stochastic Path Planning
- Improving Policy Learning via Language Dynamics Distillation
- Application of Deep Q Learning with Simulation Results for Elevator Optimization
- CEREAL: Few-Sample Clustering Evaluation
- DecAF: Joint Decoding of Answers and Logical Forms for Question Answering over Knowledge Bases
- Learning Robust Kernel Ensembles with Kernel Average Pooling
- FedTrees: A Novel Computation-Communication Efficient Federated Learning Framework Investigated in Smart Grids
- MaskTune: Mitigating Spurious Correlations by Forcing to Explore
- Kernel Normalized Convolutional Networks for Privacy-Preserving Machine Learning
- Calibrating Sequence likelihood Improves Conditional Language Generation
- Task Formulation Matters When Learning Continually: A Case Study in Visual Question Answering
- Direct Estimation of Porosity from Seismic Data using Rock and Wave Physics Informed Neural Networks (RW-PINN)
- Differentially Private Optimization on Large Model at Small Cost
- Differentially Private Bias-Term Fine-tuning of Foundation Models
- Neural Causal Models for Counterfactual Identification and Estimation
- Direct Embedding of Temporal Network Edges via Time-Decayed Line Graphs
- Artificial Replay: A Meta-Algorithm for Harnessing Historical Data in Bandits
- A Graph Neural Network Approach to Automated Model Building in Cryo-EM Maps
- F-VLM: Open-Vocabulary Object Detection upon Frozen Vision and Language Models
- Improving 3D-aware Image Synthesis with A Geometry-aware Discriminator
- Vertical Semi-Federated Learning for Efficient Online Advertising
- A General Framework for Sample-Efficient Function Approximation in Reinforcement Learning
- ExtrudeNet: Unsupervised Inverse Sketch-and-Extrude for Shape Parsing
- Finding NEEMo: Geometric Fitting using Neural Estimation of the Energy Mover's Distance
- Neural Unbalanced Optimal Transport via Cycle-Consistent Semi-Couplings
- Point normal orientation and surface reconstruction by incorporating isovalue constraints to Poisson equation
- Beyond Bayes-optimality: meta-learning what you know you don't know
- Towards Multi-spatiotemporal-scale Generalized PDE Modeling
- TinyTurbo: Efficient Turbo Decoders on Edge
- Phi-DVAE: Physics-Informed Dynamical Variational Autoencoders for Unstructured Data Assimilation
- Shuffled linear regression through graduated convex relaxation
- Bias Mimicking: A Simple Sampling Approach for Bias Mitigation
- MEIM: Multi-partition Embedding Interaction Beyond Block Term Format for Efficient and Expressive Link Prediction
All 239
- Individual Privacy Accounting with Gaussian Differential Privacy
- Rethinking Data Heterogeneity in Federated Learning: Introducing a New Notion and Standard Benchmarks
- Self-Stabilization: The Implicit Bias of Gradient Descent at the Edge of Stability
- Where Should I Spend My FLOPS? Efficiency Evaluations of Visual Pre-training Methods
- New Metric Formulas that Include Measurement Errors in Machine Learning for Natural Sciences
- Cloud Classification with Unsupervised Deep Learning
- Automated Characterization of Catalytically Active Inclusion Body Production in Biotechnological Screening Systems
- Physically Meaningful Uncertainty Quantification in Probabilistic Wind Turbine Power Curve Models as a Damage Sensitive Feature
- Match to Win: Analysing Sequences Lengths for Efficient Self-supervised Learning in Speech and Audio
- Convergence of weak-SINDy Surrogate Models
- Building Normalizing Flows with Stochastic Interpolants
- Fault Prognosis in Particle Accelerator Power Electronics Using Ensemble Learning
- Holographic-(V)AE: an end-to-end SO(3)-Equivariant (Variational) Autoencoder in Fourier Space
- Augmenting Operations Research with Auto-Formulation of Optimization Models from Problem Descriptions
- On the optimization and generalization of overparameterized implicit neural networks
- Out-of-Distribution Detection and Selective Generation for Conditional Language Models
- The More Secure, The Less Equally Usable: Gender and Ethnicity (Un)fairness of Deep Face Recognition along Security Thresholds
- Bayesian Neural Networks for Geothermal Resource Assessment: Prediction with Uncertainty
- TT-NF: Tensor Train Neural Fields
- Slimmable Networks for Contrastive Self-supervised Learning
- Cooperation in the Latent Space: The Benefits of Adding Mixture Components in Variational Autoencoders
- Sphere-Guided Training of Neural Implicit Surfaces
- Momentum Tracking: Momentum Acceleration for Decentralized Deep Learning on Heterogeneous Data
- Efficient LSTM Training with Eligibility Traces
- A Closer Look at Temporal Ordering in the Segmentation of Instructional Videos
- Learning Second Order Local Anomaly for General Face Forgery Detection
- Impact of Face Image Quality Estimation on Presentation Attack Detection
- Graph Neural Networks for Link Prediction with Subgraph Sketching
- Augmentation Invariant Discrete Representation for Generative Spoken Language Modeling
- Point Cloud Quality Assessment using 3D Saliency Maps
- Reliable Face Morphing Attack Detection in On-The-Fly Border Control Scenario with Variation in Image Resolution and Capture Distance
- Two-headed eye-segmentation approach for biometric identification
- Sparsity-Constrained Optimal Transport
- Melanoma Skin Cancer and Nevus Mole Classification using Intensity Value Estimation with Convolutional Neural Network
- Road Network Deterioration Monitoring Using Aerial Images and Computer Vision
- GPNet: Simplifying Graph Neural Networks via Multi-channel Geometric Polynomials
- Safe Exploration Method for Reinforcement Learning under Existence of Disturbance
- Semi-Supervised Domain Generalization for Cardiac Magnetic Resonance Image Segmentation with High Quality Pseudo Labels
- Explainable Censored Learning: Finding Critical Features with Long Term Prognostic Values for Survival Prediction
- End-to-End Label Uncertainty Modeling in Speech Emotion Recognition using Bayesian Neural Networks and Label Distribution Learning
- Fast Topological Signal Identification and Persistent Cohomological Cycle Matching
- Empowering the trustworthiness of ML-based critical systems through engineering activities
- Relative representations enable zero-shot latent space communication
- Higher-order Neural Additive Models: An Interpretable Machine Learning Model with Feature Interactions
- Equivariant Energy-Guided SDE for Inverse Molecular Design
- Entropy-driven Unsupervised Keypoint Representation Learning in Videos
- Rethinking the Learning Paradigm for Facial Expression Recognition
- Parea: multi-view ensemble clustering for cancer subtype discovery
- Evaluation of importance estimators in deep learning classifiers for Computed Tomography
- Programmable Control of Ultrasound Swarmbots through Reinforcement Learning
- Semi-Supervised Single-View 3D Reconstruction via Prototype Shape Priors
- Linear Convergence for Natural Policy Gradient with Log-linear Policy Parametrization
- Identify ambiguous tasks combining crowdsourced labels by weighting Areas Under the Margin
- DELAD: Deep Landweber-guided deconvolution with Hessian and sparse prior
- NBV-SC: Next Best View Planning based on Shape Completion for Fruit Mapping and Reconstruction
- PART: Pre-trained Authorship Representation Transformer
- Automatic Context-Driven Inference of Engagement in HMI: A Survey
- Inharmonious Region Localization by Magnifying Domain Discrepancy
- Efficient computation of the Knowledge Gradient for Bayesian Optimization
- Towards End-to-end Handwritten Document Recognition
- AudioGen: Textually Guided Audio Generation
- Emergent Communication: Generalization and Overfitting in Lewis Games
- Many-body Approximation for Non-negative Tensors
- SpeechLM: Enhanced Speech Pre-Training with Unpaired Textual Data
- Sparse Random Networks for Communication-Efficient Federated Learning
- SmallCap: Lightweight Image Captioning Prompted with Retrieval Augmentation
- Leveraging variational autoencoders for multiple data imputation
- Bounded Robustness in Reinforcement Learning via Lexicographic Objectives
- Convolutional Neural Networks Quantization with Attention
- FusionRetro: Molecule Representation Fusion via In-Context Learning for Retrosynthetic Planning
- Did You Get What You Paid For? Rethinking Annotation Cost of Deep Learning Based Computer Aided Detection in Chest Radiographs
- Effective Early Stopping of Point Cloud Neural Networks
- Hiding Visual Information via Obfuscating Adversarial Perturbations
- Medical Question Understanding and Answering with Knowledge Grounding and Semantic Self-Supervision
- A Survey: Credit Sentiment Score Prediction
- The Minority Matters: A Diversity-Promoting Collaborative Metric Learning Algorithm
- Verifiable and Energy Efficient Medical Image Analysis with Quantised Self-attentive Deep Neural Networks
- QUAK: A Synthetic Quality Estimation Dataset for Korean-English Neural Machine Translation
- Sparse tree-based initialization for neural networks
- Learning Transferable Spatiotemporal Representations from Natural Script Knowledge
- Rethinking skip connection model as a learnable Markov chain
- A Multivariate Complexity Analysis of Qualitative Reasoning Problems
- Online Multi-Agent Decentralized Byzantine-robust Gradient Estimation
- Application-Driven AI Paradigm for Human Action Recognition
- Generative Model Watermarking Based on Human Visual System
- Overparameterized ReLU Neural Networks Learn the Simplest Models: Neural Isometry and Exact Recovery
- Minimalistic Unsupervised Learning with the Sparse Manifold Transform
- A Multiple Criteria Decision Analysis based Approach to Remove Uncertainty in SMP Models
- On the Impossible Safety of Large AI Models
- Transformers for Object Detection in Large Point Clouds
- Energy Efficient Hardware Acceleration of Neural Networks with Power-of-Two Quantisation
- PointPillars Backbone Type Selection For Fast and Accurate LiDAR Object Detection
- Traffic Sign Classification Using Deep and Quantum Neural Networks
- Experts in the Loop: Conditional Variable Selection for Accelerating Post-Silicon Analysis Based on Deep Learning
- Hyperspectral and LiDAR data for the prediction via machine learning of tree species, volume and biomass: a possible contribution for updating forest management plans
- Your Out-of-Distribution Detection Method is Not Robust!
- Fed-CBS: A Heterogeneity-Aware Client Sampling Mechanism for Federated Learning via Class-Imbalance Reduction
- Universal Prompt Tuning for Graph Neural Networks
- Efficient Graph based Recommender System with Weighted Averaging of Messages
- Language-Family Adapters for Low-Resource Multilingual Neural Machine Translation
- The Replicator Dynamic, Chain Components and the Response Graph
- Robust Unsupervised Multi-task and Transfer Learning on Gaussian Mixture Models
- Optimal Query Complexities for Dynamic Trace Estimation
- Hyperbolic VAE via Latent Gaussian Distributions
- INT: Towards Infinite-frames 3D Detection with An Efficient Framework
- Construction and Applications of Billion-Scale Pre-Trained Multimodal Business Knowledge Graph
- Dual Progressive Transformations for Weakly Supervised Semantic Segmentation
- Multi-Prompt Alignment for Multi-Source Unsupervised Domain Adaptation
- Scale-invariant Bayesian Neural Networks with Connectivity Tangent Kernel
- What Makes Pre-trained Language Models Better Zero-shot Learners?
- ASPiRe:Adaptive Skill Priors for Reinforcement Learning
- Downlink Compression Improves TopK Sparsification
- Synonym Detection Using Syntactic Dependency And Neural Embeddings
- An efficient encoder-decoder architecture with top-down attention for speech separation
- Evaluation of taxonomic and neural embedding methods for calculating semantic similarity
- Neural Integral Equations
- Learning by Distilling Context
- RL-MD: A Novel Reinforcement Learning Approach for DNA Motif Discovery
- SCI: A Spectrum Concentrated Implicit Neural Compression for Biomedical Data
- Physical Adversarial Attack meets Computer Vision: A Decade Survey
- Domain Generalization -- A Causal Perspective
- Adaptive Sparse and Monotonic Attention for Transformer-based Automatic Speech Recognition
- Music Source Separation with Band-split RNN
- Understanding Pure CLIP Guidance for Voxel Grid NeRF Models
- State-specific protein-ligand complex structure prediction with a multi-scale deep generative model
- Depth-Wise Attention (DWAtt): A Layer Fusion Method for Data-Efficient Classification
- Reward Shaping for User Satisfaction in a REINFORCE Recommender
- Distilling Style from Image Pairs for Global Forward and Inverse Tone Mapping
- Blur the Linguistic Boundary: Interpreting Chinese Buddhist Sutra in English via Neural Machine Translation
- Linearly Mapping from Image to Text Space
- MobileViTv3: Mobile-Friendly Vision Transformer with Simple and Effective Fusion of Local, Global and Input Features
- Rethinking and Recomputing the Value of Machine Learning Models
- Variable-Based Calibration for Machine Learning Classifiers
- MonoNeuralFusion: Online Monocular Neural 3D Reconstruction with Geometric Priors
- Embedded System Performance Analysis for Implementing a Portable Drowsiness Detection System for Drivers
- Ensemble Machine Learning Model Trained on a New Synthesized Dataset Generalizes Well for Stress Prediction Using Wearable Devices
- Batch Multivalid Conformal Prediction
- Double Graphs Regularized Multi-view Subspace Clustering
- On Convergence of Average-Reward Off-Policy Control Algorithms in Weakly Communicating MDPs