Papers
Fri 20 May 2022
192 papers
- Down and Across: Introducing Crossword-Solving as a New NLP BenchmarkLLM reasoning → Reasoning benchmarks and evaluation
- MoESys: A Distributed and Efficient Mixture-of-Experts Training and Inference System for Internet ServicesMixture-of-experts → Efficient MoE training and inference systems
- InDistill: Information flow-preserving knowledge distillation for model compressionKnowledge distillation → General knowledge distillation methods
- A Unified and Biologically-Plausible Relational Graph Representation of Vision Transformers
- Evaluating and Inducing Personality in Pre-trained Language Models
- Am I No Good? Towards Detecting Perceived Burdensomeness and Thwarted Belongingness from Suicide Notes
- Persistent Homology of Coarse Grained State Space Networks
- QADAM: Quantization-Aware DNN Accelerator Modeling for Pareto-Optimality
- Open Arms: Open-Source Arms, Hands & Control
- Action Recognition for American Sign Language
- Neur2SP: Neural Two-Stage Stochastic Programming
- Quantum Kerr Learning
- Adaptive Fairness-Aware Online Meta-Learning for Changing Environments
- Neuro-Symbolic Regex Synthesis Framework via Neural Example Splitting
- A Survey on Physiological Signal Based Emotion Recognition
- Synthesis from Satisficing and Temporal Goals
- Robust Sensible Adversarial Learning of Deep Neural Networks for Image Classification
- PSO-Convolutional Neural Networks with Heterogeneous Learning Rate
- Pre-training Transformer Models with Sentence-Level Objectives for Answer Sentence Selection
- E2FL: Equal and Equitable Federated Learning
- Searching for PETs: Using Distributional and Sentiment-Based Methods to Find Potentially Euphemistic Terms
- Temporally Precise Action Spotting in Soccer Videos Using Dense Detection Anchors
- A Hybrid Model for Forecasting Short-Term Electricity Demand
- Predicting Seriousness of Injury in a Traffic Accident: A New Imbalanced Dataset and Benchmark
- How Useful are Gradients for OOD Detection Really?
- Dynamic Ensemble Selection Using Fuzzy Hyperboxes
- Towards Better Understanding Attribution Methods
- Learning Dense Reward with Temporal Variant Self-Supervision
- Using machine learning on new feature sets extracted from 3D models of broken animal bones to classify fragments according to break agent
- Multiple-criteria Heuristic Rating Estimation
- Learning Geometrically Disentangled Representations of Protein Folding Simulations
- ARLO: A Framework for Automated Reinforcement Learning
- Current Trends and Approaches in Synonyms Extraction: Potential Adaptation to Arabic
- Forecasting COVID-19 Caseloads Using Unsupervised Embedding Clusters of Social Media Posts
- Prototyping three key properties of specific curiosity in computational reinforcement learning
- Combining Contrastive and Supervised Learning for Video Super-Resolution Detection
- Tackling Provably Hard Representative Selection via Graph Neural Networks
- Multi2WOZ: A Robust Multilingual Dataset and Conversational Pretraining for Task-Oriented Dialog
- Multilingual Normalization of Temporal Expressions with Masked Language Models
- Modernizing Open-Set Speech Language Identification
- Assessing visual acuity in visual prostheses through a virtual-reality system
- EGR: Equivariant Graph Refinement and Assessment of 3D Protein Complex Structures
- A Dynamic Weighted Tabular Method for Convolutional Neural Networks
- DELMAR: Deep Linear Matrix Approximately Reconstruction to Extract Hierarchical Functional Connectivity in the Human Brain
- A SSIM Guided cGAN Architecture For Clinically Driven Generative Image Synthesis of Multiplexed Spatial Proteomics Channels
- Diversity vs. Recognizability: Human-like generalization in one-shot generative models
- Energy-efficient Deployment of Deep Learning Applications on Cortex-M based Microcontrollers using Deep Compression
- Automatic Generation of Synthetic Colonoscopy Videos for Domain Randomization
- Latent-space disentanglement with untrained generator networks for the isolation of different motion types in video data
- Fast Change Identification in Multi-Play Bandits and its Applications in Wireless Networks
- A Correlation Information-based Spatiotemporal Network for Traffic Flow Forecasting
- Learning to Reverse DNNs from AI Programs Automatically
- Robust Task-Oriented Dialogue Generation with Contrastive Pre-training and Adversarial Filtering
- FIND:Explainable Framework for Meta-learning
- StyLitGAN: Prompting StyleGAN to Produce New Illumination Conditions
- Lossless Acceleration for Seq2seq Generation with Aggressive Decoding
- Diverse super-resolution with pretrained deep hiererarchical VAEs
- Towards Understanding Grokking: An Effective Theory of Representation Learning
- Self-supervised 3D anatomy segmentation using self-distilled masked image transformer (SMIT)
- Efficient visual object representation using a biologically plausible spike-latency code and winner-take-all inhibition
- UViM: A Unified Modeling Approach for Vision with Learned Guiding Codes
- UCC: Uncertainty guided Cross-head Co-training for Semi-Supervised Semantic Segmentation
- A Review of Safe Reinforcement Learning: Methods, Theory and Applications
- What's the Harm? Sharp Bounds on the Fraction Negatively Affected by Treatment
- Nothing makes sense in deep learning, except in the light of evolution
- Complex behavior from intrinsic motivation to occupy action-state path space
- ClusterEA: Scalable Entity Alignment with Stochastic Training and Normalized Mini-batch Similarities
- Low-cost Relevance Generation and Evaluation Metrics for Entity Resolution in AI
- DELATOR: Money Laundering Detection via Multi-Task Learning on Large Transaction Graphs
- On the SDEs and Scaling Rules for Adaptive Gradient Algorithms
- Heterformer: Transformer-based Deep Node Representation Learning on Heterogeneous Text-Rich Networks
- Pre-Train Your Loss: Easy Bayesian Transfer Learning with Informative Priors
- A theoretical framework for self-supervised MR image reconstruction using sub-sampling via variable density Noisier2Noise
- Salient Skin Lesion Segmentation via Dilated Scale-Wise Feature Fusion Network
- Compression ensembles quantify aesthetic complexity and the evolution of visual art
- B-cos Networks: Alignment is All We Need for Interpretability
- Analysis of Co-Laughter Gesture Relationship on RGB videos in Dyadic Conversation Contex
- DEMAND: Deep Matrix Approximately Nonlinear Decomposition to Identify Meta, Canonical, and Sub-Spatial Pattern of functional Magnetic Resonance Imaging in the Human Brain
- A Demographic Attribute Guided Approach to Age Estimation
- Explanatory machine learning for sequential human teaching
- Sampling Is All You Need on Modeling Long-Term User Behaviors for CTR Prediction
- SADAM: Stochastic Adam, A Stochastic Operator for First-Order Gradient-based Optimizer
- EXODUS: Stable and Efficient Training of Spiking Neural Networks
- Exploring the Trade-off between Plausibility, Change Intensity and Adversarial Power in Counterfactual Explanations using Multi-objective Optimization
- Learning Task-relevant Representations for Generalization via Characteristic Functions of Reward Sequence Distributions
- Memorization and Optimization in Deep Neural Networks with Minimum Over-parameterization
- Test-time Batch Normalization
- Measuring algorithmic interpretability: A human-learning-based framework and the corresponding cognitive complexity score
- Learning to Count Anything: Reference-less Class-agnostic Counting with Weak Supervision
- How to Guide Adaptive Depth Sampling?
- On the Decentralization of Blockchain-enabled Asynchronous Federated Learning
- The Fairness of Credit Scoring Models
- A Novel Underwater Image Enhancement and Improved Underwater Biological Detection Pipeline
- A New Central Limit Theorem for the Augmented IPW Estimator: Variance Inflation, Cross-Fit Covariance and Beyond
- Unsupervised Flow-Aligned Sequence-to-Sequence Learning for Video Restoration
- On the Trade-off between Redundancy and Local Coherence in Summarization
- Progressive Class Semantic Matching for Semi-supervised Text Classification
- A Proximal Algorithm for Sampling from Non-convex Potentials
- Adversarial Body Shape Search for Legged Robots
- Bayesian Active Learning with Fully Bayesian Gaussian Processes
All 192
- E-Scooter Rider Detection and Classification in Dense Urban Environments
- Prototypical Calibration for Few-shot Learning of Language Models
- Towards the Generation of Synthetic Images of Palm Vein Patterns: A Review
- Visually-Augmented Language Modeling
- Task Relabelling for Multi-task Transfer using Successor Features
- FedAdapter: Efficient Federated Learning for Modern NLP
- Swapping Semantic Contents for Mixing Images
- Machine Learning for Combinatorial Optimisation of Partially-Specified Problems: Regret Minimisation as a Unifying Lens
- Revisiting GANs by Best-Response Constraint: Perspective, Methodology, and Application
- The developmental trajectory of object recognition robustness: children are like small adults but unlike big deep neural networks
- Towards efficient feature sharing in MIMO architectures
- Reliability-based Mesh-to-Grid Image Reconstruction
- FedNoiL: A Simple Two-Level Sampling Method for Federated Learning with Noisy Labels
- LeNSE: Learning To Navigate Subgraph Embeddings for Large-Scale Combinatorial Optimisation
- Degradation-Aware Unfolding Half-Shuffle Transformer for Spectral Compressive Imaging
- MSTRIQ: No Reference Image Quality Assessment Based on Swin Transformer with Multi-Stage Fusion
- Adversarial joint attacks on legged robots
- How to keep text private? A systematic review of deep learning methods for privacy-preserving natural language processing
- Visual Concepts Tokenization
- Kernel Normalized Convolutional Networks
- Semi-self-supervised Automated ICD Coding
- People Tracking and Re-Identifying in Distributed Contexts: Extension Study of PoseTReID
- A Unified Experiment Design Approach for Cyclic and Acyclic Causal Models
- On the Calibration of Probabilistic Classifier Sets
- Emergence of Double-slit Interference by Representing Visual Space in Artificial Neural Networks
- Unintended memorisation of unique features in neural networks
- Uzbek affix finite state machine for stemming
- Contrastive Learning with Cross-Modal Knowledge Mining for Multimodal Human Activity Recognition
- On the Prediction Instability of Graph Neural Networks
- Understanding and Mitigating the Uncertainty in Zero-Shot Translation
- Uniform Masking: Enabling MAE Pre-training for Pyramid-based Vision Transformers with Locality
- The Unreasonable Effectiveness of Deep Evidential Regression
- Beyond the Granularity: Multi-Perspective Dialogue Collaborative Selection for Dialogue State Tracking
- Leveraging Relational Information for Learning Weakly Disentangled Representations
- A Case of Exponential Convergence Rates for SVM
- Towards Extremely Fast Bilevel Optimization with Self-governed Convergence Guarantees
- What's Behind the Mask: Understanding Masked Graph Modeling for Graph Autoencoders
- Assessing Demographic Bias Transfer from Dataset to Model: A Case Study in Facial Expression Recognition
- The Sufficiency of Off-Policyness and Soft Clipping: PPO is still Insufficient according to an Off-Policy Measure
- ExMo: Explainable AI Model using Inverse Frequency Decision Rules
- Towards biologically plausible Dreaming and Planning in recurrent spiking networks
- Posterior Refinement Improves Sample Efficiency in Bayesian Neural Networks
- Exploring Extreme Parameter Compression for Pre-trained Language Models
- Survey on Fair Reinforcement Learning: Theory and Practice
- Trend analysis and forecasting air pollution in Rwanda
- Transition-based Semantic Role Labeling with Pointer Networks
- Towards Consistency in Adversarial Classification
- Predicting electrode array impedance after one month from cochlear implantation surgery
- Neural Additive Models for Nowcasting
- Translating Hanja Historical Documents to Contemporary Korean and English
- NMA: Neural Multi-slot Auctions with Externalities for Online Advertising
- Learning Progress Driven Multi-Agent Curriculum
- A Survey of Trustworthy Graph Learning: Reliability, Explainability, and Privacy Protection
- Descartes: Generating Short Descriptions of Wikipedia Articles
- Constructive Interpretability with CoLabel: Corroborative Integration, Complementary Features, and Collaborative Learning
- The price of ignorance: how much does it cost to forget noise structure in low-rank matrix estimation?
- Action parsing using context features
- Self-Supervised Depth Estimation with Isometric-Self-Sample-Based Learning
- RiskLoc: Localization of Multi-dimensional Root Causes by Weighted Risk
- Mask-guided Vision Transformer (MG-ViT) for Few-Shot Learning
- Planning with Diffusion for Flexible Behavior Synthesis
- Set-based Meta-Interpolation for Few-Task Meta-Learning
- SALTED: A Framework for SAlient Long-Tail Translation Error Detection
- SafeNet: The Unreasonable Effectiveness of Ensembles in Private Collaborative Learning
- HeadText: Exploring Hands-free Text Entry using Head Gestures by Motion Sensing on a Smart Earpiece
- FairNorm: Fair and Fast Graph Neural Network Training
- Diagnosis and Prognosis of COVID-19 Disease Using Routine Blood Values and LogNNet Neural Network
- On Tackling Explanation Redundancy in Decision Trees
- A General Framework for quantifying Aleatoric and Epistemic uncertainty in Graph Neural Networks
- A Fully Controllable Agent in the Path Planning using Goal-Conditioned Reinforcement Learning
- Few-Shot Font Generation by Learning Fine-Grained Local Styles
- Sample Complexity of Learning Heuristic Functions for Greedy-Best-First and A* Search
- Advanced Feature Learning on Point Clouds using Multi-resolution Features and Learnable Pooling
- Discrete-Convex-Analysis-Based Framework for Warm-Starting Algorithms with Predictions
- Structured Attention Composition for Temporal Action Localization
- HCFormer: Unified Image Segmentation with Hierarchical Clustering
- PGDP5K: A Diagram Parsing Dataset for Plane Geometry Problems
- Explainable Supervised Domain Adaptation
- Conformal Prediction with Temporal Quantile Adjustments
- Towards Explanation for Unsupervised Graph-Level Representation Learning
- Hyperspectral Unmixing Based on Nonnegative Matrix Factorization: A Comprehensive Review
- BayesPCN: A Continually Learnable Predictive Coding Associative Memory
- Self-Supervised Time Series Representation Learning via Cross Reconstruction Transformer
- CertiFair: A Framework for Certified Global Fairness of Neural Networks
- On Jointly Optimizing Partial Offloading and SFC Mapping: A Cooperative Dual-agent Deep Reinforcement Learning Approach
- Anomaly Detection for Multivariate Time Series on Large-scale Fluid Handling Plant Using Two-stage Autoencoder
- KERPLE: Kernelized Relative Positional Embedding for Length Extrapolation
- Robust Expected Information Gain for Optimal Bayesian Experimental Design Using Ambiguity Sets
- Can Foundation Models Wrangle Your Data?
- Sparse Infinite Random Feature Latent Variable Modeling
- Data Augmentation for Compositional Data: Advancing Predictive Models of the Microbiome
- Deep transfer learning for image classification: a survey