Papers
Mon 23 May 2022
235 papers
- On the Paradox of Learning to Reason from DataLLM reasoning → Reasoning benchmarks and evaluation
- Flexible Diffusion Modeling of Long VideosDiffusion models → Video generation
- Photorealistic Text-to-Image Diffusion Models with Deep Language UnderstandingDiffusion models → Image generation, text-to-image and editing
- Data augmentation for efficient learning from parametric expertsOffline RL and imitation learning from data → Imitation learning methods
- Logical Reasoning with Span-Level Predictions for Interpretable and Robust NLI ModelsLLM reasoning → Reasoning benchmarks and evaluation
- PEVL: Position-enhanced Pre-training and Prompt Tuning for Vision-language ModelsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
- IDEAL: Query-Efficient Data-Free Learning from Black-box ModelsKnowledge distillation → General knowledge distillation methods
- Supporting Vision-Language Model Inference with Confounder-pruning Knowledge PromptMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
- PointDistiller: Structured Knowledge Distillation Towards Efficient and Compact 3D DetectionKnowledge distillation → Detection and dense prediction distillation
- When Data Geometry Meets Deep Function: Generalizing Offline Reinforcement LearningOffline RL and imitation learning from data → Offline RL algorithms
- Efficient Reinforcement Learning from Demonstration Using Local Ensemble and Reparameterization with Split and Merge of Expert PoliciesOffline RL and imitation learning from data → Inverse reinforcement learning
- Boosting Multi-Label Image Classification with Complementary Parallel Self-DistillationKnowledge distillation → General knowledge distillation methods
- Neural Copula: A unified framework for estimating generic high-dimensional Copula functions
- Interpretable Feature Engineering for Time Series Predictors using Attention Networks
- KQGC: Knowledge Graph Embedding with Smoothing Effects of Graph Convolutions for Recommendation
- Training Efficient CNNS: Tweaking the Nuts and Bolts of Neural Networks for Lighter, Faster and Robust Models
- Theoretical Analysis of Primal-Dual Algorithm for Non-Convex Stochastic Decentralized Optimization
- PCA-Boosted Autoencoders for Nonlinear Dimensionality Reduction in Low Data Regimes
- Why does Throwing Away Data Improve Worst-Group Error?
- Algorithm Development for Controlling Movement of a Robotic Platform by Digital Image Processing
- Towards Model Generalization for Monocular 3D Object Detection
- Penguins Don't Fly: Reasoning about Generics through Instantiations and Exceptions
- FlexiBERT: Are Current Transformer Architectures too Homogeneous and Rigid?
- A Natural Language Processing Pipeline for Detecting Informal Data References in Academic Literature
- Deep Representations for Time-varying Brain Datasets
- Machine Learning for Electricity Market Clearing
- Generalization Gap in Amortized Inference
- DOGE-Train: Discrete Optimization on GPU with End-to-end Training
- Forecasting of Non-Stationary Sales Time Series Using Deep Learning
- TransforMatcher: Match-to-Match Attention for Semantic Correspondence
- Towards Opening the Black Box of Neural Machine Translation: Source and Target Interpretations of the Transformer
- Identifying Patient-Specific Root Causes of Disease
- Effective Integration of Weighted Cost-to-go and Conflict Heuristic within Suboptimal CBS
- Utilizing Language-Image Pretraining for Efficient and Robust Bilingual Word Alignment
- uGLAD: Sparse graph recovery by optimizing deep unrolled networks
- Discriminative Feature Learning through Feature Distance Loss
- On Measuring Social Biases in Prompt-Based Multi-Task Learning
- Representation Projection Invariance Mitigates Representation Collapse
- Seeded Hierarchical Clustering for Expert-Crafted Taxonomies
- Challenges in Measuring Bias via Open-Ended Language Generation
- Forecasting Argumentation Frameworks
- Explaining Causal Models with Argumentation: the Case of Bi-variate Reinforcement
- Simple Recurrence Improves Masked Language Models
- PrivFairFL: Privacy-Preserving Group Fairness in Federated Learning
- BolT: Fused Window Transformers for fMRI Time Series Analysis
- Quasi Black-Box Variational Inference with Natural Gradients for Bayesian Learning
- VPAIR -- Aerial Visual Place Recognition and Localization in Large-scale Outdoor Environments
- Accelerating the creation of instance segmentation training sets through bounding box annotation
- Using Natural Language and Program Abstractions to Instill Human Inductive Biases in Machines
- Learning to Ignore Adversarial Attacks
- Identifying magnetic antiskyrmions while they form with convolutional neural networks
- From Hours to Seconds: Towards 100x Faster Quantitative Phase Imaging via Differentiable Microscopy
- FedSA: Accelerating Intrusion Detection in Collaborative Environments with Federated Simulated Annealing
- LIA: Privacy-Preserving Data Quality Evaluation in Federated Learning Using a Lazy Influence Approximation
- Cardiomegaly Detection using Deep Convolutional Neural Network with U-Net
- Information Propagation by Composited Labels in Natural Language Processing
- Contrastive and Non-Contrastive Self-Supervised Learning Recover Global and Local Spectral Embedding Methods
- Computationally Efficient Horizon-Free Reinforcement Learning for Linear Mixture MDPs
- Orchestra: Unsupervised Federated Learning via Globally Consistent Clustering
- What Makes Data-to-Text Generation Hard for Pretrained Language Models?
- Prompt-and-Rerank: A Method for Zero-Shot and Few-Shot Arbitrary Textual Style Transfer with Small Language Models
- VQA-GNN: Reasoning with Multimodal Knowledge via Graph Neural Networks for Visual Question Answering
- Injecting Domain Adaptation with Learning-to-hash for Effective and Efficient Zero-shot Dense Retrieval
- HyperTree Proof Search for Neural Theorem Proving
- Local Byte Fusion for Neural Machine Translation
- Robust and Agnostic Learning of Conditional Distributional Treatment Effects
- Conditional Supervised Contrastive Learning for Fair Text Classification
- Towards Automated Document Revision: Grammatical Error Correction, Fluency Edits, and Beyond
- Learning differential equations from data
- Towards Tracing Factual Knowledge in Language Models Back to the Training Data
- Novel Light Field Imaging Device with Enhanced Light Collection for Cold Atom Clouds
- Exposing Outlier Exposure: What Can Be Learned From Few, One, and Zero Outlier Images
- Rethinking Streaming Machine Learning Evaluation
- Diversity Over Size: On the Effect of Sample and Topic Sizes for Topic-Dependent Argument Mining Datasets
- Exploiting the Curvature of Feasible Sets for Faster Projection-Free Online Learning
- Advanced Transient Diagnostic with Ensemble Digital Twin Modeling
- A Question-Answer Driven Approach to Reveal Affirmative Interpretations from Verbal Negations
- SQuALITY: Building a Long-Document Summarization Dataset the Hard Way
- Context Limitations Make Neural Language Models More Human-Like
- Graph-theoretical approach to robust 3D normal extraction of LiDAR data
- CELEST: Federated Learning for Globally Coordinated Threat Detection
- Multilingual Extraction and Categorization of Lexical Collocations with Graph-aware Transformers
- What is Your Metric Telling You? Evaluating Classifier Calibration under Context-Specific Definitions of Reliability
- Overfitting in quantum machine learning and entangling dropout
- Unsupervised Tokenization Learning
- Federated Distillation based Indoor Localization for IoT Networks
- Probabilistic forecasting of German electricity imbalance prices
- Contrastive Representation Learning for Cross-Document Coreference Resolution of Events and Entities
- SiSPRNet: End-to-End Learning for Single-Shot Phase Retrieval
- Informed Pre-Training on Prior Knowledge
- Spreading Factor assisted LoRa Localization with Deep Reinforcement Learning
- Decoder Denoising Pretraining for Semantic Segmentation
- LILA-BOTI : Leveraging Isolated Letter Accumulations By Ordering Teacher Insights for Bangla Handwriting Recognition
- Enhanced Prototypical Learning for Unsupervised Domain Adaptation in LiDAR Semantic Segmentation
- The Importance of Being Parameters: An Intra-Distillation Method for Serious Gains
- QASem Parsing: Text-to-text Modeling of QA-based Semantics
- Instance-Based Uncertainty Estimation for Gradient-Boosted Regression Trees
- Many-Class Text Classification with Matching
- Deep-learning-based prediction of nanoparticle phase transitions during in situ transmission electron microscopy
- Variable-Input Deep Operator Networks
All 235
- Causal Machine Learning for Healthcare and Precision Medicine
- Fine-Grained Counting with Crowd-Sourced Supervision
- Super Vision Transformer
- Multi-Temporal Spatial-Spectral Comparison Network for Hyperspectral Anomalous Change Detection
- Detection of Fights in Videos: A Comparison Study of Anomaly Detection and Action Recognition
- Generic bounds on the approximation error for physics-informed (and) operator learning
- StreamingQA: A Benchmark for Adaptation to New Knowledge over Time in Question Answering Models
- Outliers Dimensions that Disrupt Transformers Are Driven by Frequency
- Markedness in Visual Semantic AI
- Learned Digital Back-Propagation for Dual-Polarization Dispersion Managed Systems
- Exploring the limits of multifunctionality across different reservoir computers
- Looking for a Handsome Carpenter! Debiasing GPT-3 Job Advertisements
- User Clustering for Rate Splitting using Machine Learning
- Use of Transformer-Based Models for Word-Level Transliteration of the Book of the Dean of Lismore
- Rethinking Task-Incremental Learning Baselines
- Statistical inference as Green's functions
- Graph-Based Methods for Discrete Choice
- Chaotic Regularization and Heavy-Tailed Limits for Deterministic Gradient Descent
- Towards Size-Independent Generalization Bounds for Deep Operator Nets
- POLTER: Policy Trajectory Ensemble Regularization for Unsupervised Reinforcement Learning
- Spatial Attention-based Implicit Neural Representation for Arbitrary Reduction of MRI Slice Spacing
- Heterogeneous Graph Neural Network for Personalized Session-Based Recommendation with User-Session Constraints
- The Diminishing Returns of Masked Language Models to Science
- Towards Deeper Understanding of Camouflaged Object Detection
- ImGCL: Revisiting Graph Contrastive Learning on Imbalanced Node Classification
- Towards automatic detection of wildlife trade using machine vision models
- Revisiting the role of heterophily in graph representation learning: An edge classification perspective
- Active Learning Through a Covering Lens
- Continual Barlow Twins: continual self-supervised learning for remote sensing semantic segmentation
- KOLD: Korean Offensive Language Dataset
- Symptom Identification for Interpretable Detection of Multiple Mental Disorders
- Sample Efficient Approaches for Idiomaticity Detection
- Cooperative Reinforcement Learning on Traffic Signal Control
- SelfReformer: Self-Refined Network with Transformer for Salient Object Detection
- Tyger: Task-Type-Generic Active Learning for Molecular Property Prediction
- When does Parameter-Efficient Transfer Learning Work for Machine Translation?
- Memory-enriched computation and learning in spiking neural networks through Hebbian plasticity
- RL with KL penalties is better viewed as Bayesian inference
- GR-GAN: Gradual Refinement Text-to-image Generation
- Dynamic Split Computing for Efficient Deep Edge Intelligence
- Fed-DART and FACT: A solution for Federated Learning in a production environment
- What You See is What You Classify: Black Box Attributions
- A Template-based Method for Constrained Neural Machine Translation
- Scalable Kernel-Based Minimum Mean Square Error Estimator for Accelerated Image Error Concealment
- Document Intelligence Metrics for Visually Rich Document Evaluation
- Non-Parametric Domain Adaptation for End-to-End Speech Translation
- Stop Filtering: Multi-View Attribute-Enhanced Dialogue Learning
- Denoising-based image reconstruction from pixels located at non-integer positions
- BBTv2: Towards a Gradient-Free Future with Large Language Models
- Feature-Distribution Perturbation and Calibration for Generalized Person ReID
- Deep Image Retrieval is not Robust to Label Noise
- UnifieR: A Unified Retriever for Large-Scale Retrieval
- Active Domain Adaptation with Multi-level Contrastive Units for Semantic Segmentation
- NPU-BOLT: A Dataset for Bolt Object Detection in Natural Scene Images
- An Evaluation Study of Intrinsic Motivation Techniques applied to Reinforcement Learning over Hard Exploration Environments
- Online Hybrid Lightweight Representations Learning: Its Application to Visual Tracking
- Consistency of UML class, object and statechart diagrams using ontology reasoners
- Multi-objective Optimization of Clustering-based Scheduling for Multi-workflow On Clouds Considering Fairness
- How Powerful are Spectral Graph Neural Networks
- Logarithmic regret bounds for continuous-time average-reward Markov decision processes
- Prompt Tuning for Discriminative Pre-trained Language Models
- Time-series Transformer Generative Adversarial Networks
- Learning to Advise and Learning from Advice in Cooperative Multi-Agent Reinforcement Learning
- A Self-Paced Mixed Distillation Method for Non-Autoregressive Generation
- RuNNE-2022 Shared Task: Recognizing Nested Named Entities
- Squeeze Training for Adversarial Robustness
- Decoupling multivariate functions using a nonparametric filtered tensor decomposition
- Cross-lingual Lifelong Learning
- Split personalities in Bayesian Neural Networks: the case for full marginalisation
- A Coupling Enhancement Algorithm for ZrO2 Ceramic Bearing Ball Surface Defect Detection Based on Cartoon-texture Decomposition Model and Multi-Scale Filtering Method
- Stability of the scattering transform for deformations with minimal regularity
- OPQ: Compressing Deep Neural Networks with One-shot Pruning-Quantization
- Human-in-the-loop: Provably Efficient Preference-based Reinforcement Learning with General Function Approximation
- GraphAD: A Graph Neural Network for Entity-Wise Multivariate Time-Series Anomaly Detection
- Please, Don't Forget the Difference and the Confidence Interval when Seeking for the State-of-the-Art Status
- Heterogeneous Semantic Transfer for Multi-label Recognition with Partial Labels
- Fairness in Recommender Systems: Research Landscape and Future Directions
- KRNet: Towards Efficient Knowledge Replay
- ConvPoseCNN2: Prediction and Refinement of Dense 6D Object Poses
- PyRelationAL: a python library for active learning research and development
- Summarize and Generate to Back-translate: Unsupervised Translation of Programming Languages
- DTU-Net: Learning Topological Similarity for Curvilinear Structure Segmentation
- What Drives the Use of Metaphorical Language? Negative Insights from Abstractness, Affect, Discourse Coherence and Contextualized Word Representations
- DistilCamemBERT: a distillation of the French model CamemBERT
- Meta-Learning Regrasping Strategies for Physical-Agnostic Objects
- Illuminating Salient Contributions in Neuron Activation with Attribution Equilibrium
- Paddy Doctor: A Visual Image Dataset for Automated Paddy Disease Classification and Benchmarking
- Learning to branch with Tree MDPs
- An improved neural network model for treatment effect estimation
- Generalization, Mayhems and Limits in Recurrent Proximal Policy Optimization
- Proceedings Seventeenth International Workshop on the ACL2 Theorem Prover and its Applications
- FL Games: A federated learning framework for distribution shifts
- B'ezier Flow: a Surface-wise Gradient Descent Method for Multi-objective Optimization
- A Fine-grained Interpretability Evaluation Benchmark for Neural NLP
- FedNorm: Modality-Based Normalization in Federated Learning for Multi-Modal Liver Segmentation
- FaceMAE: Privacy-Preserving Face Recognition via Masked Autoencoders
- Deep Digging into the Generalization of Self-Supervised Monocular Depth Estimation
- YouTube Ad View Sentiment Analysis using Deep Learning and Machine Learning
- BanglaNLG and BanglaT5: Benchmarks and Resources for Evaluating Low-Resource Natural Language Generation in Bangla
- Beyond EM Algorithm on Over-specified Two-Component Location-Scale Gaussian Mixtures
- Self-distilled Knowledge Delegator for Exemplar-free Class Incremental Learning
- WOGAN at the SBST 2022 CPS Tool Competition
- Saliency-Driven Active Contour Model for Image Segmentation
- Vegetation Mapping by UAV Visible Imagery and Machine Learning
- Wasserstein Generative Adversarial Networks for Online Test Generation for Cyber Physical Systems
- Falsification of Multiple Requirements for Cyber-Physical Systems Using Online Generative Adversarial Networks and Multi-Armed Bandits
- TempLM: Distilling Language Models into Template-Based Generators
- Flow-based Recurrent Belief State Learning for POMDPs
- GBA: A Tuning-free Approach to Switch between Synchronous and Asynchronous Training for Recommendation Model
- Keypoint-Based Category-Level Object Pose Tracking from an RGB Sequence with Uncertainty Estimation
- Personalized Federated Learning with Server-Side Information
- FLEX: Feature-Logic Embedding Framework for CompleX Knowledge Graph Reasoning
- Augmented Newton Method for Optimization: Global Linear Rate and Momentum Interpretation
- Body Composition Estimation Based on Multimodal Multi-task Deep Neural Network
- HessianFR: An Efficient Hessian-based Follow-the-Ridge Algorithm for Minimax Optimization
- META-GUI: Towards Multi-modal Conversational Agents on Mobile GUI
- RCP: Recurrent Closest Point for Scene Flow Estimation on 3D Point Clouds
- Flexible and Hierarchical Prior for Bayesian Nonnegative Matrix Factorization
- Vector-Quantized Input-Contextualized Soft Prompts for Natural Language Understanding
- AdaptivePaste: Code Adaptation through Learning Semantics-aware Variable Usage Representations
- Artificial intelligence for topic modelling in Hindu philosophy: mapping themes between the Upanishads and the Bhagavad Gita
- A Comprehensive Handwritten Paragraph Text Recognition System: LexiconNet
- MolMiner: You only look once for chemical structure recognition
- Calibrate and Refine! A Novel and Agile Framework for ASR-error Robust Intent Detection
- Nonparametric learning of kernels in nonlocal operators
- Parameter-Efficient Sparsity for Large Language Models Fine-Tuning
- Semi-Decentralized Federated Learning with Collaborative Relaying
- Data-Efficient Modeling for Precise Power Consumption Estimation of Quadrotor Operations Using Ensemble Learning
- From Width-Based Model Checking to Width-Based Automated Theorem Proving
- Multiple Domain Cyberspace Attack and Defense Game Based on Reward Randomization Reinforcement Learning
- Improving Short Text Classification With Augmented Data Using GPT-3
- What should I Ask: A Knowledge-driven Approach for Follow-up Questions Generation in Conversational Surveys
- Global Extreme Heat Forecasting Using Neural Weather Models
- Neural Subgraph Explorer: Reducing Noisy Information via Target-Oriented Syntax Graph Pruning
- Computational Storytelling and Emotions: A Survey