Papers
Tue 14 Jun 2022
200 papers
- Understanding Narratives through Dimensions of AnalogyLLM reasoning → Reasoning benchmarks and evaluation
- Regularizing a Model-based Policy Stationary Distribution to Stabilize Offline Reinforcement LearningOffline RL and imitation learning from data → Offline RL algorithms
- Toward Student-Oriented Teacher Network Training For Knowledge DistillationKnowledge distillation → General knowledge distillation methods
- FreeKD: Free-direction Knowledge Distillation for Graph Neural NetworksKnowledge distillation → Graph neural network distillation
- A Hybrid Model and Learning-Based Adaptive Navigation Filter
- Does Twitter know your political views? POLiTweets dataset and semi-automatic method for political leaning discovery
- ECG beat classification using machine learning and pre-trained convolutional neural networks
- Tackling Data Scarcity with Transfer Learning: A Case Study of Thickness Characterization from Optical Spectra of Perovskite Thin Films
- Label-enhanced Prototypical Network with Contrastive Learning for Multi-label Few-shot Aspect Category Detection
- Can Foundation Models Talk Causality?
- Confidence-Guided Unsupervised Domain Adaptation for Cerebellum Segmentation
- The Metaverse Data Deluge: What Can We Do About It?
- Bayesian neural networks for the probabilistic forecasting of wind direction and speed using ocean data
- A theory of learning with constrained weight-distribution
- Resolution Limits of Non-Adaptive 20 Questions Search for a Moving Target
- Reconstructing vehicles from orthographic drawings using deep neural networks
- Embarrassingly Parallel Independent Training of Multi-Layer Perceptrons with Heterogeneous Architectures
- You Are the Best Reviewer of Your Own Papers: The Isotonic Mechanism
- Atrial Fibrillation Detection Using Weight-Pruned, Log-Quantised Convolutional Neural Networks
- Classification of ECG based on Hybrid Features using CNNs for Wearable Applications
- Explainable expected goal models for performance analysis in football analytics
- Beyond Grounding: Extracting Fine-Grained Event Hierarchies Across Modalities
- Attributions Beyond Neural Networks: The Linear Program Case
- Unbiased Estimation using Underdamped Langevin Dynamics
- Using Machine Learning to Augment Dynamic Time Warping Based Signal Classification
- Benefits of Additive Noise in Composing Classes with Bounded Capacity
- Surgical Phase Recognition in Laparoscopic Cholecystectomy
- Improving Solar Flare Prediction by Time Series Outlier Detection
- Towards a Solution to Bongard Problems: A Causal Approach
- Tearing Apart NOTEARS: Controlling the Graph Prediction via Variance Manipulation
- Machines Explaining Linear Programs
- Codec at SemEval-2022 Task 5: Multi-Modal Multi-Transformer Misogynous Meme Classification Framework
- Defending Observation Attacks in Deep Reinforcement Learning via Detection and Denoising
- To Aggregate or Not? Learning with Separate Noisy Labels
- Proximal Splitting Adversarial Attacks for Semantic Segmentation
- Frequency-centroid features for word recognition of non-native English speakers
- Measuring Representational Harms in Image Captioning
- Segmentation in large-scale cellular electron microscopy with deep learning: A literature survey
- Towards Goal, Feasibility, and Diversity-Oriented Deep Generative Models in Design
- Edge Security: Challenges and Issues
- DeepRecon: Joint 2D Cardiac Segmentation and 3D Volume Reconstruction via A Structure-Specific Generative Method
- Category-Agnostic 6D Pose Estimation with Conditional Neural Processes
- GraphFM: Improving Large-Scale GNN Training via Feature Momentum
- LAVENDER: Unifying Video-Language Understanding as Masked Language Modeling
- Federated Multi-organ Segmentation with Inconsistent Labels
- Self-Supervision on Images and Text Reduces Reliance on Visual Shortcut Features
- An Intelligent Assistant for Converting City Requirements to Formal Specification
- It's Time for Artistic Correspondence in Music and Video
- Efficiently Training Low-Curvature Neural Networks
- MBGDT:Robust Mini-Batch Gradient Descent
- Prioritized Training on Points that are Learnable, Worth Learning, and Not Yet Learnt
- Automatic Clipping: Differentially Private Deep Learning Made Easier and Stronger
- Stability of Image-Reconstruction Algorithms
- Lazy Queries Can Reduce Variance in Zeroth-order Optimization
- Self-Supervised Pretraining for Differentially Private Learning
- Loss Functions for Classification using Structured Entropy
- TriHorn-Net: A Model for Accurate Depth-Based 3D Hand Pose Estimation
- If it Bleeds, it Leads: A Computational Approach to Covering Crime in Los Angeles
- Minorities in networks and algorithms
- NewsEdits: A News Article Revision Dataset and a Document-Level Reasoning Challenge
- Plurality Veto: A Simple Voting Rule Achieving Optimal Metric Distortion
- Combining Counterfactuals With Shapley Values To Explain Image Models
- Understanding the Generalization Benefit of Normalization Layers: Sharpness Reduction
- An Efficient HTN to STRIPS Encoding for Concurrent Plans
- Learning the Structure of Large Networked Systems Obeying Conservation Laws
- Stability and Generalization of Stochastic Optimization with Nonconvex and Nonsmooth Problems
- Applications of Generative Adversarial Networks in Neuroimaging and Clinical Neuroscience
- Measuring Inconsistency in Declarative Process Specifications
- Near-Exact Recovery for Tomographic Inverse Problems via Deep Learning
- RGB-Multispectral Matching: Dataset, Learning Methodology, Evaluation
- ReCo: Retrieve and Co-segment for Zero-shot Transfer
- Text Generation with Text-Editing Models
- Learning Behavior Representations Through Multi-Timescale Bootstrapping
- AnimeSR: Learning Real-World Super-Resolution Models for Animation Videos
- Accurate 3D Body Shape Regression using Metric and Semantic Attributes
- Learning 3D Object Shape and Layout without 3D Supervision
- Computational linguistics and Natural Language Processing
- SBERT studies Meaning Representations: Decomposing Sentence Embeddings into Explainable Semantic Features
- Federated Optimization Algorithms with Random Reshuffling and Gradient Compression
- Turning a Curse into a Blessing: Enabling In-Distribution-Data-Free Backdoor Removal via Stabilized Model Inversion
- Consistent Video Instance Segmentation with Inter-Frame Recurrent Attention
- Two-Timescale Stochastic Approximation for Bilevel Optimisation Problems in Continuous-Time Models
- ProcTHOR: Large-Scale Embodied AI Using Procedural Generation
- An Experimental Investigation of Part-Of-Speech Taggers for Vietnamese
- Exploring Representation of Horn Clauses using GNNs (Extended Technical Report)
- Two-terminal source coding with common sum reconstruction
- Highly Efficient Structural Learning of Sparse Staged Trees
- Deep Reinforcement Learning for Exact Combinatorial Optimization: Learning to Branch
- ABCinML: Anticipatory Bias Correction in Machine Learning Applications
- AuxMix: Semi-Supervised Learning with Unconstrained Unlabeled Data
- Continual-Learning-as-a-Service (CLaaS): On-Demand Efficient Adaptation of Predictive Models
- FETILDA: An Effective Framework For Fin-tuned Embeddings For Long Financial Text Documents
- Monitoring Urban Forests from Auto-Generated Segmentation Maps
- K-Space Transformer for Undersampled MRI Reconstruction
- OSN Dashboard Tool For Sentiment Analysis
- Stand-Alone Inter-Frame Attention in Video Models
- Comprehending and Ordering Semantics for Image Captioning
- Scaling ResNets in the Large-depth Regime
- The Maximum Linear Arrangement Problem for trees under projectivity and planarity
- A Multi-task Framework for Infrared Small Target Detection and Segmentation
All 200
- Object Scene Representation Transformer
- Manifold Alignment-Based Multi-Fidelity Reduced-Order Modeling Applied to Structural Analysis
- Grad-GradaGrad? A Non-Monotone Adaptive Stochastic Gradient Method
- RDU: A Region-based Approach to Form-style Document Understanding
- CERT: Continual Pre-Training on Sketches for Library-Oriented Code Generation
- Neural interval-censored survival regression with feature selection
- An Accurate HDDL Domain Learning Algorithm from Partial and Noisy Observations
- Temporal Multimodal Multivariate Learning
- On Provably Robust Meta-Bayesian Optimization
- How are policy gradient methods affected by the limits of control?
- Evaluating histopathology transfer learning with ChampKit
- On the explainable properties of 1-Lipschitz Neural Networks: An Optimal Transport Perspective
- On the Finite-Time Performance of the Knowledge Gradient Algorithm
- Robust Reinforcement Learning with Distributional Risk-averse formulation
- Architectural patterns for handling runtime uncertainty of data-driven models in safety-critical perception
- "hasSignification()": une nouvelle fonction de distance pour soutenir la d'etection de donn'ees personnelles
- Efficient Decoder-free Object Detection with Transformers
- Variance Reduction for Policy-Gradient Methods via Empirical Variance Minimization
- Tailored max-out networks for learning convex PWQ functions
- DoWhy-GCM: An extension of DoWhy for causal inference in graphical causal models
- Disentangled Federated Learning for Tackling Attributes Skew via Invariant Aggregation and Diversity Transferring
- Residual-based physics-informed transfer learning: A hybrid method for accelerating long-term CFD simulations via deep learning
- Learning towards Synchronous Network Memorizability and Generalizability for Continual Segmentation across Multiple Sites
- Adversarial Audio Synthesis with Complex-valued Polynomial Networks
- Adversarially Robust Multi-Armed Bandit Algorithm with Variance-Dependent Regret Bounds
- The Causal Structure of Semantic Ambiguities
- Asymmetric Dual-Decoder U-Net for Joint Rain and Haze Removal
- Peripheral Vision Transformer
- Open-Ended Learning Strategies for Learning Complex Locomotion Skills
- Riemannian stochastic approximation algorithms
- How to Agree to Disagree: Managing Ontological Perspectives using Standpoint Logic
- Supervised Dictionary Learning with Auxiliary Covariates
- Exploring Adversarial Attacks and Defenses in Vision Transformers trained with DINO
- Universally Expressive Communication in Multi-Agent Reinforcement Learning
- RoSGAS: Adaptive Social Bot Detection with Reinforced Self-Supervised GNN Architecture Search
- Counting Markov Equivalent Directed Acyclic Graphs Consistent with Background Knowledge
- Weakly-Supervised Crack Detection
- Recurrent Transformer Variational Autoencoders for Multi-Action Motion Synthesis
- Adversarial Vulnerability of Randomized Ensembles
- Learning Dense Features for Point Cloud Registration Using a Graph Attention Network
- Automated Precision Localization of Peripherally Inserted Central Catheter Tip through Model-Agnostic Multi-Stage Networks
- Automated SSIM Regression for Detection and Quantification of Motion Artefacts in Brain MR Images
- Specification sketching for Linear Temporal Logic
- Deep Variational Implicit Processes
- Stein Variational Goal Generation for adaptive Exploration in Multi-Goal Reinforcement Learning
- Semi-signed prioritized neural fitting for surface reconstruction from unoriented point clouds
- Interpretable Gait Recognition by Granger Causality
- Visual Radial Basis Q-Network
- Conformal Off-policy Prediction
- Task Transfer and Domain Adaptation for Zero-Shot Question Answering
- CNN-based Classification Framework for Lung Tissues with Auxiliary Information
- Generalizing experimental findings: identification beyond adjustments
- ISLES 2022: A multi-center magnetic resonance imaging stroke lesion segmentation dataset
- COVIDHunter: COVID-19 pandemic wave prediction and mitigation via seasonality-aware modeling
- Bandwidth Enables Generalization in Quantum Kernel Models
- Causal Discovery for Fairness
- Exploring speaker enrolment for few-shot personalisation in emotional vocalisation prediction
- Matching Pursuit Based Scheduling for Over-the-Air Federated Learning
- Severe Damage Recovery in Evolving Soft Robots through Differentiable Programming
- Semi-Autoregressive Energy Flows: Exploring Likelihood-Free Training of Normalizing Flows
- Online Easy Example Mining for Weakly-supervised Gland Segmentation from Histology Images
- Quantitative Imaging Principles Improves Medical Image Learning
- Learning Best Combination for Efficient N:M Sparsity
- The Open Kidney Ultrasound Data Set
- The Kidneys Are Not All Normal: Investigating the Speckle Distributions of Transplanted Kidneys
- SpecNet2: Orthogonalization-free spectral embedding by neural networks
- Confidence Score for Source-Free Unsupervised Domain Adaptation
- RF-Next: Efficient Receptive Field Search for Convolutional Neural Networks
- Explainable AI for High Energy Physics
- Semantic-Discriminative Mixup for Generalizable Sensor-based Cross-domain Activity Recognition
- ULTRA: Uncertainty-aware Label Distribution Learning for Breast Tumor Cellularity Assessment
- Slimmable Domain Adaptation
- TransVG++: End-to-End Visual Grounding with Language Conditioned Vision Transformer
- Solving the capacitated vehicle routing problem with timing windows using rollouts and MAX-SAT
- Transformers are Meta-Reinforcement Learners
- Label Matching Semi-Supervised Object Detection
- Plug-and-Play Pseudo Label Correction Network for Unsupervised Person Re-identification
- Astock: A New Dataset and Automated Stock Trading based on Stock-specific News Analyzing Model
- Deep Isolation Forest for Anomaly Detection
- CorticalFlow++: Boosting Cortical Surface Reconstruction Accuracy, Regularity, and Interoperability
- Permutation Search of Tensor Network Structures via Local Sampling
- On Finite-Sample Identifiability of Contrastive Learning-Based Nonlinear Independent Component Analysis
- Downlink Power Allocation in Massive MIMO via Deep Learning: Adversarial Attacks and Training
- Shopping Queries Dataset: A Large-Scale ESCI Benchmark for Improving Product Search
- Learning Enhanced Representations for Tabular Data via Neighborhood Propagation
- FreeTransfer-X: Safe and Label-Free Cross-Lingual Transfer from Off-the-Shelf Models
- Probabilistic Conformal Prediction Using Conditional Random Samples
- Exploring evolution-aware & -free protein language models as protein function predictors
- CHQ-Summ: A Dataset for Consumer Healthcare Question Summarization
- Physics Informed Neural Fields for Smoke Reconstruction with Sparse Data
- Med-DANet: Dynamic Architecture Network for Efficient Medical Volumetric Segmentation
- LIFT: Language-Interfaced Fine-Tuning for Non-Language Machine Learning Tasks
- Zeroth-Order Topological Insights into Iterative Magnitude Pruning
- Safe Output Feedback Motion Planning from Images via Learned Perception Modules and Contraction Theory
- A Survey of Automated Data Augmentation Algorithms for Deep Learning-based Image Classification Tasks
- Pixel-by-pixel Mean Opinion Score (pMOS) for No-Reference Image Quality Assessment
- 3D scene reconstruction from monocular spherical video with motion parallax
- A Stochastic Proximal Method for Nonsmooth Regularized Finite Sum Optimization
- MACQ: A Holistic View of Model Acquisition Techniques
- Overparametrized linear dimensionality reductions: From projection pursuit to two-layer neural networks