Papers
Wed 25 May 2022
250 papers
- Pretraining is All You Need for Image-to-Image TranslationDiffusion models → Image generation, text-to-image and editing
- VeriFi: Towards Verifiable Federated UnlearningLLM safety and security → Federated unlearning and poisoning
- Eliciting and Understanding Cross-Task Skills with Task-Level Mixture-of-ExpertsMixture-of-experts → Expert routing strategies
- BITE: Textual Backdoor Attacks with Iterative Trigger InjectionLLM safety and security → Backdoor and data poisoning attacks
- ProsocialDialog: A Prosocial Backbone for Conversational AgentsLLM agents and tool use → Social simulation and multi-agent debate
- TaCube: Pre-computing Data Cubes for Answering Numerical-Reasoning Questions over Tabular DataLLM reasoning → Knowledge- and tool-augmented reasoning
- Bitext Mining Using Distilled Sentence Representations for Low-Resource LanguagesKnowledge distillation → Knowledge distillation for LLMs
- Guiding Visual Question Answering with Attention PriorsLLM reasoning → Multimodal reasoning
- RobustLR: Evaluating Robustness to Logical Perturbation in Deductive ReasoningLLM reasoning → Reasoning benchmarks and evaluation
- Accelerating Diffusion Models via Early Stop of the Diffusion ProcessDiffusion models → Diffusion foundations and sampling
- Teaching Broad Reasoning Skills for Multi-Step QA by Generating Hard ContextsLLM reasoning → Reasoning benchmarks and evaluation
- ToKen: Task Decomposition and Knowledge Infusion for Few-Shot Hate Speech DetectionLLM reasoning → Reasoning benchmarks and evaluation
- Region-aware Knowledge Distillation for Efficient Image-to-Image TranslationKnowledge distillation → General knowledge distillation methods
- Do we need Label Regularization to Fine-tune Pre-trained Language Models?Knowledge distillation → General knowledge distillation methods
- Question Personalization in an Intelligent Tutoring System
- Lifelong Learning Natural Language Processing Approach for Multilingual Data Classification
- Obj2Sub: Unsupervised Conversion of Objective to Subjective Questions
- Federated Adaptation of Reservoirs via Intrinsic Plasticity
- Investigating the Benefits of Free-Form Rationales
- Topological Simplification of Signals for Inference and Approximate Reconstruction
- SS-GNN: A Simple-Structured Graph Neural Network for Affinity Prediction
- Predicting Corporate Risk by Jointly Modeling Company Networks and Dialogues in Earnings Conference Calls
- RIS-ADMM: A RIS and ADMM-Based Passive and Sparse Sensing Method With Interference Removal
- On the solvability of weakly linear systems of fuzzy relation equations
- Scalable Multi-Agent Model-Based Reinforcement Learning
- AI-aided multiscale modeling of physiologically-significant blood clots
- Mutual Information Divergence: A Unified Metric for Multimodal Generative Models
- A Rotated Hyperbolic Wrapped Normal Distribution for Hierarchical Representation Learning
- Identifying Patient-Specific Root Causes with the Heteroscedastic Noise Model
- BRIGHT -- Graph Neural Networks in Real-Time Fraud Detection
- Factorized Structured Regression for Large-Scale Varying Coefficient Models
- Learning to Query Internet Text for Informing Reinforcement Learning Agents
- On Bridging the Gap between Mean Field and Finite Width in Deep Random Neural Networks with Batch Normalization
- Exploring Map-based Features for Efficient Attention-based Vehicle Motion Prediction
- Tight Lower Bounds on Worst-Case Guarantees for Zero-Shot Learning with Attributes
- Forecasting Patient Demand at Urgent Care Clinics using Machine Learning
- Semi-supervised Drifted Stream Learning with Short Lookback
- Urban Rhapsody: Large-scale exploration of urban soundscapes
- RENs: Relevance Encoding Networks
- Designing an Efficient End-to-end Machine Learning Pipeline for Real-time Empty-shelf Detection
- Efficient and Near-Optimal Smoothed Online Learning for Generalized Linear Functions
- Scalable and Low-Latency Federated Learning with Cooperative Mobile Edge Networking
- Online Deep Equilibrium Learning for Regularization by Denoising
- Near-Optimal Goal-Oriented Reinforcement Learning in Non-Stationary Environments
- How explainable are adversarially-robust CNNs?
- Improving Subgraph Representation Learning via Multi-View Augmentation
- EvoVGM: a Deep Variational Generative Model for Evolutionary Parameter Estimation
- Concurrent Neural Tree and Data Preprocessing AutoML for Image Classification
- Formalizing Preferences Over Runtime Distributions
- Preference Dynamics Under Personalized Recommendations
- Towards Using Data-Influence Methods to Detect Noisy Samples in Source Code Corpora
- People counting system for retail analytics using edge AI
- BiT: Robustly Binarized Multi-distilled Transformer
- TSEM: Temporally Weighted Spatiotemporal Explainable Neural Network for Multivariate Time Series
- QGNN: Value Function Factorisation with Graph Neural Networks
- Towards Diverse and Natural Scene-aware 3D Human Motion Synthesis
- Transcormer: Transformer for Sentence Scoring with Sliding Language Modeling
- Position: Tensor Networks are a Valuable Asset for Green AI
- Towards Symbolic Time Series Representation Improved by Kernel Density Estimators
- Uniform Generalization Bound on Time and Inverse Temperature for Gradient Descent Algorithm and its Application to Analysis of Simulated Annealing
- Inception Transformer
- Neural 3D Reconstruction in the Wild
- Learning in Mean Field Games: A Survey
- Conformal Prediction Intervals with Temporal Dependence
- Mitigating multiple descents: A model-agnostic framework for risk monotonization
- Amortized Inference for Causal Structure Learning
- Clustering consistency with Dirichlet process mixtures
- Domain Adaptation for Object Detection using SE Adaptors and Center Loss
- DH-GAN: A Physics-driven Untrained Generative Adversarial Network for 3D Microscopic Imaging using Digital Holography
- A Low Memory Footprint Quantized Neural Network for Depth Completion of Very Sparse Time-of-Flight Depth Maps
- New Intent Discovery with Pre-training and Contrastive Learning
- Context-Aware Video Reconstruction for Rolling Shutter Cameras
- SoK: Cross-border Criminal Investigations and Digital Evidence
- NaturalProver: Grounded Mathematical Proof Generation with Language Models
- Analytics of Business Time Series Using Machine Learning and Bayesian Inference
- Analyzing Tree Architectures in Ensembles via Neural Tangent Kernel
- GARDNet: Robust Multi-View Network for Glaucoma Classification in Color Fundus Images
- Pre-trained Perceptual Features Improve Differentially Private Image Generation
- Reasoning over Logically Interacted Conditions for Question Answering
- Robust Reinforcement Learning on Graphs for Logistics optimization
- You Need to Read Again: Multi-granularity Perception Network for Moment Retrieval in Videos
- Trust-based Consensus in Multi-Agent Reinforcement Learning Systems
- Understanding Programmatic Weak Supervision via Source-aware Influence Function
- Open-Domain Sign Language Translation Learned from Online Video
- Image Colorization using U-Net with Skip Connections and Fusion Layer on Landscape Images
- Structure Unbiased Adversarial Model for Medical Image Segmentation
- Stochastic Second-Order Methods Improve Best-Known Sample Complexity of SGD for Gradient-Dominated Function
- Understanding Factual Errors in Summarization: Errors, Summarizers, Datasets, Error Detectors
- Deep Gradient Learning for Efficient Camouflaged Object Detection
- A Universal Error Measure for Input Predictions Applied to Online Graph Problems
- A Comparative Study of Gastric Histopathology Sub-size Image Classification: from Linear Regression to Visual Transformer
- Marginal Post Processing of Bayesian Inference Products with Normalizing Flows and Kernel Density Estimators
- On Building Spoken Language Understanding Systems for Low Resourced Languages
- Automatic question generation based on sentence structure analysis using machine learning approach
- Mirror Descent Maximizes Generalized Margin and Can Be Implemented Efficiently
- Integrated Gradient attribution for Gaussian Processes with non-Gaussian likelihoods
- Non-rigid Point Cloud Registration with Neural Deformation Pyramid
- Impartial Games: A Challenge for Reinforcement Learning
- AO2-DETR: Arbitrary-Oriented Object Detection Transformer
- TrustGNN: Graph Neural Network based Trust Evaluation via Learnable Propagative and Composable Nature
All 250
- Ultra-compact Binary Neural Networks for Human Activity Recognition on RISC-V Processors
- Residual-Concatenate Neural Network with Deep Regularization Layers for Binary Classification
- Does Moral Code Have a Moral Code? Probing Delphi's Moral Philosophy
- An Experimental Comparison Between Temporal Difference and Residual Gradient with Neural Network Approximation
- Would You Ask it that Way? Measuring and Improving Question Naturalness for Knowledge Graph Question Answering
- An Evolutionary Approach to Dynamic Introduction of Tasks in Large-scale Multitask Learning Systems
- An Empirical Study on Distribution Shift Robustness From the Perspective of Pre-Training and Data Augmentation
- NECA: Network-Embedded Deep Representation Learning for Categorical Data
- Fast Stochastic Composite Minimization and an Accelerated Frank-Wolfe Algorithm under Parallelization
- A Human-Centric Assessment Framework for AI
- Machine learning method for return direction forecasting of Exchange Traded Funds using classification and regression models
- SIoU Loss: More Powerful Learning for Bounding Box Regression
- Neuro-Symbolic Learning of Answer Set Programs from Raw Data
- Deep interpretable ensembles
- Service Discovery in Social Internet of Things using Graph Neural Networks
- Maximum Mean Discrepancy on Exponential Windows for Online Change Detection
- COVID-19 Severity Classification on Chest X-ray Images
- Detecting Label Errors by using Pre-Trained Language Models
- Empathic Conversations: A Multi-level Dataset of Contextualized Conversations
- PLOG: Table-to-Logic Pretraining for Logical Table-to-Text Generation
- Revisiting DocRED -- Addressing the False Negative Problem in Relation Extraction
- Surprises in adversarially-trained linear regression
- Train Flat, Then Compress: Sharpness-Aware Minimization Learns More Compressible Models
- Contrastive Learning with Boosted Memorization
- Understanding Natural Language in Context
- Large Language Models are Few-Shot Clinical Information Extractors
- Ground-Truth Labels Matter: A Deeper Look into Input-Label Demonstrations
- Probabilistic model-error assessment of deep learning proxies: an application to real-time inversion of borehole electromagnetic measurements
- Rethinking Fano's Inequality in Ensemble Learning
- Optimizing Test-Time Query Representations for Dense Retrieval
- Self-Guided Noise-Free Data Generation for Efficient Zero-Shot Learning
- Language Anisotropic Cross-Lingual Model Editing
- Evaluating the Diversity, Equity and Inclusion of NLP Technology: A Case Study for Indian Languages
- Training Language Models with Memory Augmentation
- InstructDial: Improving Zero and Few-shot Generalization in Dialogue through Instruction Tuning
- Discovering Language-neutral Sub-networks in Multilingual Language Models
- QAMPARI: An Open-domain Question Answering Benchmark for Questions with Many Answers from Multiple Paragraphs
- DFM: Dialogue Foundation Model for Universal Large-Scale Dialogue-Oriented Task Learning
- MAPLE-X: Latency Prediction with Explicit Microprocessor Prior Knowledge
- Few-shot Reranking for Multi-hop QA via Language Model Prompting
- Investigating Lexical Replacements for Arabic-English Code-Switched Data Augmentation
- Fast Inference and Transfer of Compositional Task Structures for Few-shot Task Generalization
- Overcoming Catastrophic Forgetting in Zero-Shot Cross-Lingual Generation
- UniInst: Unique Representation for End-to-End Instance Segmentation
- LingMess: Linguistically Informed Multi Expert Scorers for Coreference Resolution
- Asking the Right Questions in Low Resource Template Extraction
- On the Interpretability of Regularisation for Neural Networks Through Model Gradient Similarity
- Does Your Model Classify Entities Reasonably? Diagnosing and Mitigating Spurious Correlations in Entity Typing
- TreEnhance: A Tree Search Method For Low-Light Image Enhancement
- A Zipf's Law-based Text Generation Approach for Addressing Imbalance in Entity Extraction
- MoCoViT: Mobile Convolutional Vision Transformer
- Real-Time Video Deblurring via Lightweight Motion Compensation
- NTIRE 2022 Challenge on High Dynamic Range Imaging: Methods and Results
- Multimodal Knowledge Alignment with Reinforcement Learning
- Are Large Pre-Trained Language Models Leaking Your Personal Information?
- Primitive3D: 3D Object Dataset Synthesis from Randomly Assembled Primitives
- Unbiased and Efficient Sampling of Dependency Trees
- Location-free Human Pose Estimation
- DisinfoMeme: A Multimodal Dataset for Detecting Meme Intentionally Spreading Out Disinformation
- Autoformalization with Large Language Models
- Deep Aesthetic Assessment and Retrieval of Breast Cancer Treatment Outcomes
- Generating Information-Seeking Conversations from Unlabeled Documents
- ReSmooth: Detecting and Utilizing OOD Samples when Training with Data Augmentation
- Leveraging QA Datasets to Improve Generative Data Augmentation
- VTP: Volumetric Transformer for Multi-view Multi-person 3D Pose Estimation
- Learning Distributions by Generative Adversarial Networks: Approximation and Generalization
- ORCA: Interpreting Prompted Language Models via Locating Supporting Data Evidence in the Ocean of Pretraining Data
- Heterogeneous Reservoir Computing Models for Persian Speech Recognition
- Less Learn Shortcut: Analyzing and Mitigating Learning of Spurious Feature-Label Correlation
- RSTGen: Imbuing Fine-Grained Interpretable Control into Long-FormText Generators
- Deniable Steganography
- Perturbation Augmentation for Fairer NLP
- TAGPRIME: A Unified Framework for Relational Structure Extraction
- MUG: Multi-human Graph Network for 3D Mesh Reconstruction from 2D Pose
- From Pedestrian Detection to Crosswalk Estimation: An EM Algorithm and Analysis on Diverse Datasets
- EDIN: An End-to-end Benchmark and Pipeline for Unknown Entity Discovery and Indexing
- Towards a Fair Comparison and Realistic Evaluation Framework of Android Malware Detectors based on Static Analysis and Machine Learning
- Spotlights: Probing Shapes from Spherical Viewpoints
- Gradient-Based Constrained Sampling from Language Models
- Are Akpans Trick or Treat: Unveiling Helpful Biases in Assistant Systems
- Masked Jigsaw Puzzle: A Versatile Position Embedding for Vision Transformers
- Recognition Models to Learn Dynamics from Partial Observations with Neural ODEs
- Learning from time-dependent streaming data with online stochastic algorithms
- RLPrompt: Optimizing Discrete Text Prompts with Reinforcement Learning
- Some equivalence relation between persistent homology and morphological dynamics
- Deep Dense Local Feature Matching and Vehicle Removal for Indoor Visual Localization
- Misleading Deep-Fake Detection with GAN Fingerprints
- ER-Test: Evaluating Explanation Regularization Methods for Language Models
- Apport des ontologies pour le calcul de la similarit'e s'emantique au sein d'un syst`eme de recommandation
- Is a Question Decomposition Unit All We Need?
- Structured Uncertainty in the Observation Space of Variational Autoencoders
- Skill Machines: Temporal Logic Skill Composition in Reinforcement Learning
- LOPS: Learning Order Inspired Pseudo-Label Selection for Weakly Supervised Text Classification
- Segmenting Numerical Substitution Ciphers
- TranSpeech: Speech-to-Speech Translation With Bilateral Perturbation
- Crossmodal-3600: A Massively Multilingual Multimodal Evaluation Dataset
- Structure Aware and Class Balanced 3D Object Detection on nuScenes Dataset
- Toward Discovering Options that Achieve Faster Planning
- Machine Translation Robustness to Natural Asemantic Variation
- Text-to-Face Generation with StyleGAN2
- Exact Phase Transitions in Deep Learning
- Re-Examining Calibration: The Case of Question Answering
- Memorization in NLP Fine-tuning Methods
- GENEVA: Benchmarking Generalizability for Event Argument Extraction with Hundreds of Event Types and Argument Roles
- Deadlock-Free Method for Multi-Agent Pickup and Delivery Problem Using Priority Inheritance with Temporary Priority
- The Dialog Must Go On: Improving Visual Dialog via Generative Self-Training
- Federated Self-supervised Learning for Heterogeneous Clients
- Fine-grained Contrastive Learning for Relation Extraction
- Improve Event Extraction via Self-Training with Gradient Guidance
- End-to-End Multimodal Fact-Checking and Explanation Generation: A Challenging Dataset and Models
- Factorizing Content and Budget Decisions in Abstractive Summarization of Long Documents
- Conditional set generation using Seq2seq models
- GisPy: A Tool for Measuring Gist Inference Score in Text
- A Convergence Theory for Over-parameterized Variational Quantum Eigensolvers
- Leveraging Locality in Abstractive Text Summarization
- Low Resource Style Transfer via Domain Adaptive Meta Learning
- Learning a Better Initialization for Soft Prompts via Meta-Learning
- Logical Satisfiability of Counterfactuals for Faithful Explanations in NLI
- Multiview Textured Mesh Recovery by Differentiable Rendering
- R2D2: Robust Data-to-Text with Replacement Detection
- Eye-gaze-guided Vision Transformer for Rectifying Shortcut Learning
- FBNETGEN: Task-aware GNN-based fMRI Analysis via Functional Brain Network Generation
- sat2pc: Estimating Point Cloud of Building Roofs from 2D Satellite Images
- Improving CTC-based ASR Models with Gated Interlayer Collaboration
- Augmentation-induced Consistency Regularization for Classification
- Linear Algorithms for Robust and Scalable Nonparametric Multiclass Probability Estimation
- A CNN with Noise Inclined Module and Denoise Framework for Hyperspectral Image Classification
- A Lightweight NMS-free Framework for Real-time Visual Fault Detection System of Freight Trains
- Investigating Information Inconsistency in Multilingual Open-Domain Question Answering
- Recipe for a General, Powerful, Scalable Graph Transformer
- Know Where You're Going: Meta-Learning for Parameter-Efficient Fine-Tuning
- Sparse*BERT: Sparse Models Generalize To New tasks and Domains
- Cross-Domain Style Mixing for Face Cartoonization
- MAVIPER: Learning Decision Tree Policies for Interpretable Multi-Agent Reinforcement Learning
- Transportation-Inequalities, Lyapunov Stability and Sampling for Dynamical Systems on Continuous State Space
- FLEURS: Few-shot Learning Evaluation of Universal Representations of Speech
- Over-the-Air Design of GAN Training for mmWave MIMO Channel Estimation
- Generating Natural Language Proofs with Verifier-Guided Search
- Lyapunov function approach for approximation algorithm design and analysis: with applications in submodular maximization
- Skin Cancer Diagnostics with an All-Inclusive Smartphone Application
- Additive Logistic Mechanism for Privacy-Preserving Self-Supervised Learning
- Interaction of a priori Anatomic Knowledge with Self-Supervised Contrastive Learning in Cardiac Magnetic Resonance Imaging
- Non-stationary Bandits with Knapsacks
- VulBERTa: Simplified Source Code Pre-Training for Vulnerability Detection
- Deletion and Insertion Tests in Regression Models
- Non-Programmers Can Label Programs Indirectly via Active Examples: A Case Study with Text-to-SQL
- Learning Action Conditions from Instructional Manuals for Instruction Understanding
- Physics Guided Machine Learning for Variational Multiscale Reduced Order Modeling
- Tiered Reinforcement Learning: Pessimism in the Face of Uncertainty and Constant Regret
- Counterfactual Data Augmentation improves Factuality of Abstractive Summarization