Papers
Thu 9 Jun 2022
216 papers
- Challenges and Opportunities in Offline Reinforcement Learning from Visual ObservationsOffline RL and imitation learning from data → Offline RL algorithms
- Mildly Conservative Q-Learning for Offline Reinforcement LearningOffline RL and imitation learning from data → Offline RL algorithms
- Predictive Exit: Prediction of Fine-Grained Early Exits for Computation- and Energy-Efficient InferenceEfficient LLM inference and serving → Early exit and edge inference
- Uni-Perceiver-MoE: Learning Sparse Generalist Models with Conditional MoEsMixture-of-experts → MoE theory and gating functions
- PointNeXt: Revisiting PointNet++ with Improved Training and Scaling StrategiesWorld models → World modeling from LiDAR generation
- Knowledge Distillation Decision Tree for Unravelling Black-box Machine Learning ModelsKnowledge distillation → General knowledge distillation methods
- Temporal Logic Imitation: Learning Plan-Satisficing Motion Policies from DemonstrationsOffline RL and imitation learning from data → Robot learning from demonstration
- Pragmatically Learning from Pedagogical Demonstrations in Multi-Goal EnvironmentsOffline RL and imitation learning from data → Robot learning from demonstration
- Unlearning Protected User Attributes in Recommendations with Adversarial TrainingLLM safety and security → Membership inference attacks
- Receding Horizon Inverse Reinforcement LearningOffline RL and imitation learning from data → Inverse reinforcement learning
- Value Memory Graph: A Graph-Structured World Model for Offline Reinforcement LearningWorld models → Latent dynamics models and model-based RL +1
- AutoML-Based Drought Forecast with Meteorological Variables
- Process Knowledge-Infused AI: Towards User-level Explainability, Interpretability, and Safety
- Audio-video fusion strategies for active speaker detection in meetings
- CrowdWorkSheets: Accounting for Individual and Collective Identities Underlying Crowdsourced Dataset Annotation
- Principal Trade-off Analysis
- Does a Technique for Building Multimodal Representation Matter? -- Comparative Analysis
- Towards Target High-Utility Itemsets
- Concept Identification for Complex Engineering Datasets
- Spatial-temporal Concept based Explanation of 3D ConvNets
- SimVP: Simpler yet Better Video Prediction
- On Neural Architecture Inductive Biases for Relational Tasks
- A No-reference Quality Assessment Metric for Point Cloud Based on Captured Video Sequences
- Coswara: A website application enabling COVID-19 screening by analysing respiratory sound samples and health symptoms
- Meta-data Study in Autism Spectrum Disorder Classification Based on Structural MRI
- Temporal Inductive Logic Reasoning over Hypergraphs
- Improved Approximation for Fair Correlation Clustering
- Denoising Generalized Expectation-Consistent Approximation for MR Image Recovery
- A GPU-Accelerated Light-field Super-resolution Framework Based on Mixed Noise Model and Weighted Regularization
- Empirical Bayes approach to Truth Discovery problems
- The Case for a Single Model that can Both Generate Continuations and Fill in the Blank
- Deep learning-enhanced ensemble-based data assimilation for high-dimensional nonlinear dynamical systems
- Adaptive Model Pooling for Online Deep Anomaly Detection from a Complex Evolving Data Stream
- Learn2Augment: Learning to Composite Videos for Data Augmentation in Action Recognition
- Comprehensive Fair Meta-learned Recommender System
- Building Spatio-temporal Transformers for Egocentric 3D Pose Estimation
- On the Bias-Variance Characteristics of LIME and SHAP in High Sparsity Movie Recommendation Explanation Tasks
- ReFace: Real-time Adversarial Attacks on Face Recognition Systems
- Speak Like a Dog: Human to Non-human creature Voice Conversion
- Trimmed Maximum Likelihood Estimation for Robust Learning in Generalized Linear Models
- What should AI see? Using the Public's Opinion to Determine the Perception of an AI
- Joint Entropy Search for Maximally-Informed Bayesian Optimization
- Neural Bregman Divergences for Distance Learning
- Data-Efficient Double-Win Lottery Tickets from Robust Pre-training
- An Empirical Study on Disentanglement of Negative-free Contrastive Learning
- Defending Compositionality in Emergent Languages
- HDTorch: Accelerating Hyperdimensional Computing with GP-GPUs for Design Space Exploration
- Strong Memory Lower Bounds for Learning Natural Models
- Accelerating Asynchronous Federated Learning Convergence via Opportunistic Mobile Relaying
- Quantum Policy Iteration via Amplitude Estimation and Grover Search -- Towards Quantum Advantage for Reinforcement Learning
- XAudit : A Theoretical Look at Auditing with Explanations
- I'm Me, We're Us, and I'm Us: Tri-directional Contrastive Learning on Hypergraphs
- A Novel Partitioned Approach for Reduced Order Model -- Finite Element Model (ROM-FEM) and ROM-ROM Coupling
- Fast Bayesian Inference with Batch Bayesian Quadrature via Kernel Recombination
- AI-MIA: COVID-19 Detection & Severity Analysis through Medical Imaging
- Leveraging Centric Data Federated Learning Using Blockchain For Integrity Assurance
- Towards Target Sequential Rules
- STNDT: Modeling Neural Population Activity with a Spatiotemporal Transformer
- COSTA: Covariance-Preserving Feature Augmentation for Graph Contrastive Learning
- Modular design patterns for neural-symbolic integration: refinement and combination
- On the Unreasonable Effectiveness of Federated Averaging with Heterogeneous Data
- A Resilient Distributed Boosting Algorithm
- AI-based Clinical Assessment of Optic Nerve Head Robustness Superseding Biomechanical Testing
- A New Frontier of AI: On-Device AI Training and Personalization
- Swan: A Neural Engine for Efficient DNN Training on Smartphone SoCs
- Unsupervised Deep Discriminant Analysis Based Clustering
- Structure-consistent Restoration Network for Cataract Fundus Image Enhancement
- Molecular dynamics without molecules: searching the conformational space of proteins with generative neural networks
- Neural Prompt Search
- Overcoming the Spectral Bias of Neural Value Approximation
- Open Challenges in Deep Stereo: the Booster Dataset
- Beyond RGB: Scene-Property Synthesis with Neural Radiance Fields
- GateHUB: Gated History Unit with Background Suppression for Online Action Detection
- Extreme Masking for Learning Instance and Distributed Visual Representations
- AGConv: Adaptive Graph Convolution on 3D Point Clouds
- On Data Scaling in Masked Image Modeling
- Provably efficient variational generative modeling of quantum many-body systems via quantum-probabilistic information geometry
- DiSparse: Disentangled Sparsification for Multitask Model Compression
- Jewelry Shop Conversational Chatbot
- BigVGAN: A Universal Neural Vocoder with Large-Scale Training
- Simple Cues Lead to a Strong Multi-Object Tracker
- Towards Layer-wise Image Vectorization
- VideoINR: Learning Video Implicit Neural Representation for Continuous Space-Time Super-Resolution
- Minimax Optimal Algorithms for Fixed-Budget Best Arm Identification
- Probability flow solution of the Fokker-Planck equation
- Regret Bounds for Information-Directed Reinforcement Learning
- Spatial Entropy as an Inductive Bias for Vision Transformers
- AttX: Attentive Cross-Connections for Fusion of Wearable Signals in Emotion Recognition
- Factuality Enhanced Language Models for Open-Ended Text Generation
- A Critical Review on the Use (and Misuse) of Differential Privacy in Machine Learning
- On the Generalization and Adaption Performance of Causal Models
- Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models
- Explicit Regularization in Overparametrized Models via Noise Injection
- On Margins and Generalisation for Voting Classifiers
- Field Level Neural Network Emulator for Cosmological N-body Simulations
- Privacy Leakage in Text Classification: A Data Extraction Approach
- GASP: Gated Attention For Saliency Prediction
- Optimal SQ Lower Bounds for Robustly Learning Discrete Product Distributions and Ising Models
- Extracting Zero-shot Common Sense from Large Language Models for Robot 3D Scene Understanding
- Efficient and Robust 2D-to-BEV Representation Learning via Geometry-guided Kernel Transformer
All 216
- Clustering with Queries under Semi-Random Noise
- Transformer based Urdu Handwritten Text Optical Character Reader
- Simple lessons from complex learning: what a neural network model learns about cosmic structure formation
- Revisiting End-to-End Speech-to-Text Translation From Scratch
- Benefits of Overparameterized Convolutional Residual Networks: Function Approximation under Smoothness Constraint
- TwiBot-22: Towards Graph-Based Twitter Bot Detection
- Functional Code Building Genetic Programming
- BFS-Net: Weakly Supervised Cell Instance Segmentation from Bright-Field Microscopy Z-Stacks
- SparseFormer: Attention-based Depth Completion Network
- A Fourier representation of kernel Stein discrepancy with application to Goodness-of-Fit tests for measures on infinite dimensional Hilbert spaces
- A Relational Intervention Approach for Unsupervised Dynamics Generalization in Model-Based Reinforcement Learning
- Classification of COVID-19 in Chest X-ray Images Using Fusion of Deep Features and LightGBM
- ECLAD: Extracting Concepts with Local Aggregated Descriptors
- DORA: Exploring Outlier Representations in Deep Neural Networks
- Face-Dubbing++: Lip-Synchronous, Voice Preserving Translation of Videos
- An FPGA-based Solution for Convolution Operation Acceleration
- Accurate Node Feature Estimation with Structured Variational Graph Autoencoder
- SAR Despeckling using a Denoising Diffusion Probabilistic Model
- AAM-Gym: Artificial Intelligence Testbed for Advanced Air Mobility
- Efficient Human Pose Estimation via 3D Event Point Cloud
- SsciBERT: A Pre-trained Language Model for Social Science Texts
- cycle text2face: cycle text-to-face gan via transformers
- What is a Good Metric to Study Generalization of Minimax Learners?
- Mitigating Modality Collapse in Multimodal VAEs via Impartial Optimization
- Redundancy in Deep Linear Neural Networks
- Data-Efficient Brain Connectome Analysis via Multi-Task Meta-Learning
- BSM loss: A superior way in modeling aleatory uncertainty of fine_grained classification
- Individually Fair Learning with One-Sided Feedback
- Early Transferability of Adversarial Examples in Deep Neural Networks
- Towards Understanding Graph Neural Networks: An Algorithm Unrolling Perspective
- Joint Encoder-Decoder Self-Supervised Pre-training for ASR
- Meet You Halfway: Explaining Deep Learning Mysteries
- Open ERP System Data For Occupational Fraud Detection
- SDQ: Stochastic Differentiable Quantization with Mixed Precision
- Choosing Answers in varepsilon-Best-Answer Identification for Linear Bandits
- The Missing Link: Finding label relations across datasets
- Draft-and-Revise: Effective Image Generation with Contextual RQ-Transformer
- Segmentation Enhanced Lameness Detection in Dairy Cows from RGB and Depth Video
- Convolutional Dictionary Learning by End-To-End Training of Iterative Neural Networks
- Dict-NMT: Bilingual Dictionary based NMT for Extremely Low Resource Languages
- A taxonomy of explanations to support Explainability-by-Design
- Towards Safe Reinforcement Learning via Constraining Conditional Value-at-Risk
- Regret Analysis of Certainty Equivalence Policies in Continuous-Time Linear-Quadratic Systems
- Discriminative and Generative Learning for Linear Estimation of Random Signals [Lecture Notes]
- Cross-boosting of WNNM Image Denoising method by Directional Wavelet Packets
- Multiple Instance Learning for Digital Pathology: A Review on the State-of-the-Art, Limitations & Future Potential
- Learning to generalize Dispatching rules on the Job Shop Scheduling
- Neonatal EEG graded for severity of background abnormalities in hypoxic-ischaemic encephalopathy
- Unsupervised Learning of the Total Variation Flow
- Conformal Off-Policy Prediction in Contextual Bandits
- VITA: Video Instance Segmentation via Object Token Association
- Cross-modal Local Shortest Path and Global Enhancement for Visible-Thermal Person Re-Identification
- Depression Recognition using Remote Photoplethysmography from Facial Videos
- Xplique: A Deep Learning Explainability Toolbox
- HideNseek: Federated Lottery Ticket via Server-side Pruning and Sign Supermask
- CLIP-Actor: Text-Driven Recommendation and Stylization for Animating Human Meshes
- STIP: A SpatioTemporal Information-Preserving and Perception-Augmented Model for High-Resolution Video Prediction
- Uncovering bias in the PlantVillage dataset
- Diagnosing Ensemble Few-Shot Classifiers
- Ancestor-to-Creole Transfer is Not a Walk in the Park
- CARLA-GeAR: a Dataset Generator for a Systematic Evaluation of Adversarial Robustness of Vision Models
- Deep Neural Network for Blind Visual Quality Assessment of 4K Content
- Model Degradation Hinders Deep Graph Neural Networks
- A general approximation lower bound in Lp norm, with applications to feed-forward neural networks
- Learning Non-Vacuous Generalization Bounds from Optimization
- A Simple Unified Approach to Testing High-Dimensional Conditional Independences for Categorical and Ordinal Data
- Graph Attention Multi-Layer Perceptron
- Applying separative non-negative matrix factorization to extra-financial data
- Deep radiomic signature with immune cell markers predicts the survival of glioma patients
- How Asynchronous Events Encode Video
- Joint Modeling of Image and Label Statistics for Enhancing Model Generalizability of Medical Image Segmentation
- Learning to generate imaginary tasks for improving generalization in meta-learning
- Corpus Similarity Measures Remain Robust Across Diverse Languages
- Predicting Embedding Reliability in Low-Resource Settings Using Corpus Similarity Measures
- Novel projection schemes for graph-based Light Field coding
- Language Identification for Austronesian Languages
- CFA: Coupled-hypersphere-based Feature Adaptation for Target-Oriented Anomaly Localization
- Negative Shannon Information Hides Networks
- Blind Surveillance Image Quality Assessment via Deep Neural Network Combined with the Visual Saliency
- Topic-Controllable Summarization: Topic-Aware Evaluation and Transformer Methods
- Adversarial Noises Are Linearly Separable for (Nearly) Random Neural Networks
- Multi-class Classification with Fuzzy-feature Observations: Theory and Algorithms
- GSmooth: Certified Robustness against Semantic Transformations via Generalized Randomized Smoothing
- Context-based out-of-vocabulary word recovery for ASR systems in Indian languages
- Unveiling Transformers with LEGO: a synthetic reasoning task
- Reconstruct Face from Features Using GAN Generator as a Distribution Constraint
- FOAM: A Follower-aware Speaker Model For Vision-and-Language Navigation
- OptWedge: Cognitive Optimized Guidance toward Off-screen POIs
- A No-Reference Deep Learning Quality Assessment Method for Super-resolution Images Based on Frequency Maps
- Evaluating Aleatoric Uncertainty via Conditional Generative Models
- A Unification Framework for Euclidean and Hyperbolic Graph Neural Networks
- Sample-Efficient Reinforcement Learning in the Presence of Exogenous Information
- Local Spatiotemporal Representation Learning for Longitudinally-consistent Neuroimage Analysis
- On Hypothesis Transfer Learning of Functional Linear Models
- Robust Matrix Completion with Heavy-tailed Noise
- STEM image analysis based on deep learning: identification of vacancy defects and polymorphs of MoS2
- DeepVerge: Classification of Roadside Verge Biodiversity and Conservation Potential
- A General Framework For Proving The Equivariant Strong Lottery Ticket Hypothesis
- Smart System: Joint Utility and Frequency for Pattern Classification
- There is no Accuracy-Interpretability Tradeoff in Reinforcement Learning for Mazes
- ScatterSample: Diversified Label Sampling for Data Efficient Graph Neural Network Learning
- CLTS+: A New Chinese Long Text Summarization Dataset with Abstractive Summaries
- An Optimization Method-Assisted Ensemble Deep Reinforcement Learning Algorithm to Solve Unit Commitment Problems
- SwinCheX: Multi-label classification on chest X-ray images with transformers
- OOD Augmentation May Be at Odds with Open-Set Recognition
- Enhancement of Healthcare Data Transmission using the Levenberg-Marquardt Algorithm
- Crosslinguistic word order variation reflects evolutionary pressures of dependency and information locality
- Cardiac Adipose Tissue Segmentation via Image-Level Annotations
- Edgeworth Accountant: An Analytical Approach to Differential Privacy Composition
- JNMR: Joint Non-linear Motion Regression for Video Frame Interpolation
- GCVAE: Generalized-Controllable Variational AutoEncoder
- Analyzing Folktales of Different Regions Using Topic Modeling and Clustering
- Neo-GNNs: Neighborhood Overlap-aware Graph Neural Networks for Link Prediction
- It's a super deal -- train recurrent network on noisy data and get smooth prediction free
- Deep Surrogate Assisted Generation of Environments
- Exploring Predictive States via Cantor Embeddings and Wasserstein Distance