Papers
Thu 13 Oct 2022
296 papers
- Bootstrapping Multilingual Semantic Parsers using Large Language ModelsSynthetic data and self-improvement for LLMs → LLM synthetic data generation
- Joint Reasoning on Hybrid-knowledge sources for Task-Oriented DialogLLM reasoning → Reasoning benchmarks and evaluation
- SODAPOP: Open-Ended Discovery of Social Biases in Social Commonsense Reasoning ModelsLLM reasoning → Reasoning benchmarks and evaluation
- Unified Vision and Language Prompt LearningMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
- Visual Classification via Description from Large Language ModelsMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
- Counterfactual Multihop QA: A Cause-Effect Approach for Reducing Disconnected ReasoningLLM reasoning → Causal reasoning in LLMs
- Language Models of Code are Few-Shot Commonsense LearnersLLM reasoning → Reasoning benchmarks and evaluation
- CORL: Research-oriented Deep Offline Reinforcement Learning LibraryOffline RL and imitation learning from data → Offline RL algorithms
- Augmentation for Learning From Demonstration with Environmental ConstraintsOffline RL and imitation learning from data → Robot learning from demonstration
- DE-FAKE: Detection and Attribution of Fake Images Generated by Text-to-Image Generation ModelsDiffusion models → Image generation, text-to-image and editing
- Dim-Krum: Backdoor-Resistant Federated Learning for NLP with Dimension-wise Krum-Based AggregationLLM safety and security → Federated unlearning and poisoning
- Policy Gradient With Serial Markov Chain ReasoningLLM reasoning → Reinforcement learning for reasoning
- Exploring Contextual Representation and Multi-Modality for End-to-End Autonomous DrivingEnd-to-end autonomous driving → End-to-end system architecture
- Explanations from Large Language Models Make Small Reasoners BetterLLM reasoning → Reasoning benchmarks and evaluation
- Large Language Models are few(1)-shot Table ReasonersLLM reasoning → Knowledge- and tool-augmented reasoning
- Model-Based Offline Reinforcement Learning with Pessimism-Modulated Dynamics BeliefOffline RL and imitation learning from data → Offline RL algorithms
- A Brief Survey on Representation Learning based Graph Dimensionality Reduction Techniques
- Post trade allocation: how much are bunched orders costing your performance?
- Deep reinforcement learning for automatic run-time adaptation of UWB PHY radio settings
- LSG Attention: Extrapolation of pretrained Transformers to long sequences
- ProSky: NEAT Meets NOMA-mmWave in the Sky of 6G
- Multi-Modal Recommendation System with Auxiliary Information
- Virtual-Reality based Vestibular Ocular Motor Screening for Concussion Detection using Machine-Learning
- Vision Transformers provably learn spatial structure
- A Systematic Review of Machine Learning Techniques for Cattle Identification: Datasets, Methods and Future Directions
- On the Identifiability and Estimation of Causal Location-Scale Noise Models
- Cross-domain Variational Capsules for Information Extraction
- Real-Time Automated Answer Scoring
- QuAnt: Quantum Annealing with Learnt Couplings
- Trajectory Prediction for Vehicle Conflict Identification at Intersections Using Sequence-to-Sequence Recurrent Neural Networks
- Inductive Logical Query Answering in Knowledge Graphs
- Knowledge acquisition via interactive Distributed Cognitive skill Modules
- Codes, Patterns and Shapes of Contemporary Online Antisemitism and Conspiracy Narratives -- an Annotation Guide and Labeled German-Language Dataset in the Context of COVID-19
- A Consistent and Differentiable Lp Canonical Calibration Error Estimator
- Meta-Query-Net: Resolving Purity-Informativeness Dilemma in Open-set Active Learning
- Object-Category Aware Reinforcement Learning
- Autoregressive Uncertainty Modeling for 3D Bounding Box Prediction
- Task Grouping for Multilingual Text Recognition
- Learning to Efficiently Plan Robust Frictional Multi-Object Grasps
- GLACIAL: Granger and Learning-based Causality Analysis for Longitudinal Imaging Studies
- Noise Audits Improve Moral Foundation Classification
- Invariance-adapted decomposition and Lasso-type contrastive learning
- TractoSCR: A Novel Supervised Contrastive Regression Framework for Prediction of Neurocognitive Measures Using Multi-Site Harmonized Diffusion MRI Tractography
- Identification of quantum entanglement with Siamese convolutional neural networks and semi-supervised learning
- Anomaly detection in dynamic networks
- Early Discovery of Disappearing Entities in Microblogs
- Estimation of the Sample Frechet Mean: A Convolutional Neural Network Approach
- Real-time Action Recognition for Fine-Grained Actions and The Hand Wash Dataset
- A Concise Introduction to Reinforcement Learning in Robotics
- Caption supervision enables robust learners
- Efficiently Computing Local Lipschitz Constants of Neural Networks via Bound Propagation
- Amortized Inference for Heterogeneous Reconstruction in Cryo-EM
- Behavior Cloned Transformers are Neurosymbolic Reasoners
- Frustratingly Easy Sentiment Analysis of Text Streams: Generating High-Quality Emotion Arcs Using Emotion Lexicons
- Marginalized particle Gibbs for multiple state-space models coupled through shared parameters
- ScionFL: Efficient and Robust Secure Quantized Aggregation
- A Relational Macrostate Theory Guides Artificial Intelligence to Learn Macro and Design Micro
- Mind the Labels: Describing Relations in Knowledge Graphs With Pretrained Models
- SWFormer: Sparse Window Transformer for 3D Object Detection in Point Clouds
- M2D2: A Massively Multi-domain Language Modeling Dataset
- Is It Worth the (Environmental) Cost? Limited Evidence for Temporal Adaptation via Continuous Training
- Can Demographic Factors Improve Text Classification? Revisiting Demographic Adaptation in the Age of Transformers
- Consistency and Accuracy of CelebA Attribute Values
- Finding Islands of Predictability in Action Forecasting
- JOIST: A Joint Speech and Text Streaming Model For ASR
- Predicting Fine-Tuning Performance with Probing
- Disentanglement of Correlated Factors via Hausdorff Factorized Support
- An Embarrassingly Simple Backdoor Attack on Self-supervised Learning
- Scientific Impact of Graph-Based Approaches in Deep Learning Studies -- A Bibliometric Comparison
- LEAVES: Learning Views for Time-Series Biobehavioral Data in Contrastive Learning
- Reinforcement Learning with Unbiased Policy Evaluation and Linear Function Approximation
- FOON Creation and Traversal for Recipe Generation
- Secure Multiparty Computation for Synthetic Data Generation from Distributed Data
- Sample Efficient Dynamics Learning for Symmetrical Legged Robots:Leveraging Physics Invariance and Geometric Symmetries
- Machine Learning vs. Deep Learning in 5G Networks -- A Comparison of Scientific Impact
- Experiments on Turkish ASR with Self-Supervised Speech Representation Learning
- Machine Generated Text: A Comprehensive Survey of Threat Models and Detection Methods
- A Large-Scale Annotated Multivariate Time Series Aviation Maintenance Dataset from the NGAFID
- MTEB: Massive Text Embedding Benchmark
- Bootstrap Advantage Estimation for Policy Optimization in Reinforcement Learning
- SHINE: SubHypergraph Inductive Neural nEtwork
- Deep Reinforcement Learning-based Rebalancing Policies for Profit Maximization of Relay Nodes in Payment Channel Networks
- 3D GAN Inversion with Pose Optimization
- AMP: Automatically Finding Model Parallel Strategies with Heterogeneity Awareness
- Joint control variate for faster black-box variational inference
- Improving Deep Learning Models for Pediatric Low-Grade Glioma Tumors Molecular Subtype Identification Using 3D Probability Distributions of Tumor Location
- Harfang3D Dog-Fight Sandbox: A Reinforcement Learning Research Platform for the Customized Control Tasks of Fighter Aircrafts
- Meta-Uncertainty in Bayesian Model Comparison
- The Hidden Uniform Cluster Prior in Self-Supervised Learning
- BLOX: Macro Neural Architecture Search Benchmark and Algorithms
- Multi-Task Learning for Joint Semantic Role and Proto-Role Labeling
- Topics in Deep Learning and Optimization Algorithms for IoT Applications in Smart Transportation
- OpenOOD: Benchmarking Generalized Out-of-Distribution Detection
- Visual Reinforcement Learning with Self-Supervised 3D Representations
- How to Train Vision Transformer on Small-scale Datasets?
- Composite Learning for Robust and Effective Dense Predictions
- Forces are not Enough: Benchmark and Critical Evaluation for Machine Learning Force Fields with Molecular Simulations
- Improved Bounds on Neural Complexity for Representing Piecewise Linear Functions
- The Complexity of NISQ
- Shape Preserving Facial Landmarks with Graph Attention Networks
All 296
- Mass-Editing Memory in a Transformer
- Language Model Decoding as Likelihood-Utility Alignment
- Exploring Long-Sequence Masked Autoencoders
- Saliency Map Verbalization: Comparing Feature Importance Representations from Model-free and Instruction-based Methods
- Condition-number-independent convergence rate of Riemannian Hamiltonian Monte Carlo with numerical integrators
- FARE: Provably Fair Representation Learning with Practical Certificates
- Computer-Aided Multi-Objective Optimization in Small Molecule Discovery
- Attribution-aware Weight Transfer: A Warm-Start Initialization for Class-Incremental Semantic Segmentation
- Best Practices in the Creation and Use of Emotion Lexicons
- Searching for Better Database Queries in the Outputs of Semantic Parsers
- Self-Supervised Geometric Correspondence for Category-Level 6D Object Pose Estimation in the Wild
- Towards Trustworthy Automatic Diagnosis Systems by Emulating Doctors' Reasoning with Deep Reinforcement Learning
- Towards a Unified Multi-Dimensional Evaluator for Text Generation
- On Compressing Sequences for Self-Supervised Speech Models
- ezCoref: Towards Unifying Annotation Guidelines for Coreference Resolution
- On the Utility of Self-supervised Models for Prosody-related Tasks
- Towards Multi-Agent Reinforcement Learning driven Over-The-Counter Market Simulations
- PDEBENCH: An Extensive Benchmark for Scientific Machine Learning
- MonoNeRF: Learning Generalizable NeRFs from Monocular Videos without Camera Pose
- MAPL: Parameter-Efficient Adaptation of Unimodal Pre-Trained Models for Vision-Language Few-Shot Prompting
- SQuAT: Sharpness- and Quantization-Aware Training for BERT
- Forecast Hedging and Calibration
- HSurf-Net: Normal Estimation for 3D Point Clouds by Learning Hyper Surfaces
- Fast Estimation of Bayesian State Space Models Using Amortized Simulation-Based Inference
- Smooth Calibration, Leaky Forecasts, Finite Recall, and Nash Dynamics
- Global Explainability of GNNs via Logic Combination of Learned Concepts
- Scalable Multi-robot Motion Planning for Congested Environments With Topological Guidance
- U-HRNet: Delving into Improving Semantic Representation of High Resolution Network for Dense Prediction
- You Can Have Your Data and Balance It Too: Towards Balanced and Efficient Multilingual Models
- Learning Multivariate CDFs and Copulas using Tensor Factorization
- Challenges in Explanation Quality Evaluation
- RTFormer: Efficient Design for Real-Time Semantic Segmentation with Transformer
- Deep Idempotent Network for Efficient Single Image Blind Deblurring
- Graph-based Neural Modules to Inspect Attention-based Architectures: A Position Paper
- Precision QCD corrections to gluon-initiated diphoton-plus-jet production at the LHC
- Towards End-to-End Open Conversational Machine Reading
- A Multi-dimensional Evaluation of Tokenizer-free Multilingual Pretrained Models
- Dungeons and Dragons as a Dialog Challenge for Artificial Intelligence
- Corneal endothelium assessment in specular microscopy images with Fuchs' dystrophy via deep regression of signed distance maps
- Dissipative residual layers for unsupervised implicit parameterization of data manifolds
- Meta-learning Based Short-Term Passenger Flow Prediction for Newly-Operated Urban Rail Transit Stations
- Incorporating Context into Subword Vocabularies
- Query Expansion Using Contextual Clue Sampling with Language Models
- Implicit Bias in Leaky ReLU Networks Trained on High-Dimensional Data
- Few-Shot Visual Question Generation: A Novel Task and Benchmark Datasets
- CLASP: Few-Shot Cross-Lingual Data Augmentation for Semantic Parsing
- ConvTransSeg: A Multi-resolution Convolution-Transformer Network for Medical Image Segmentation
- The Open-World Lottery Ticket Hypothesis for OOD Intent Classification
- Deep Clustering With Consensus Representations
- Sparse in Space and Time: Audio-visual Synchronisation with Trainable Selectors
- Scaling Back-Translation with Domain Text Generation for Sign Language Gloss Translation
- Dimensionality of datasets in object detection networks
- Spontaneous Emerging Preference in Two-tower Language Model
- Threshold Treewidth and Hypertree Width
- Self-Supervised Learning of Linear Precoders under Non-Linear PA Distortion for Energy-Efficient Massive MIMO Systems
- Prompt-based Connective Prediction Method for Fine-grained Implicit Discourse Relation Recognition
- Rebalanced Zero-shot Learning
- Self-explaining deep models with logic rule reasoning
- CROP: Zero-shot Cross-lingual Named Entity Recognition with Multilingual Labeled Sequence Translation
- ComSearch: Equation Searching with Combinatorial Strategy for Solving Math Word Problems with Weak Supervision
- Learning with Style: Continual Semantic Segmentation Across Tasks and Domains
- Transfer Deep Reinforcement Learning-based Large-scale V2G Continuous Charging Coordination with Renewable Energy Sources
- Over-the-Air Computation Based on Balanced Number Systems for Federated Edge Learning
- Variational Graph Generator for Multi-View Graph Clustering
- Sustainable Online Reinforcement Learning for Auto-bidding
- Anonymizing Speech with Generative Adversarial Networks to Preserve Speaker Privacy
- Two approaches to inpainting microstructure with deep convolutional generative adversarial networks
- DICTDIS: Dictionary Constrained Disambiguation for Improved NMT
- Multi-Task Meta Learning: learn how to adapt to unseen tasks
- Tone prediction and orthographic conversion for Basaa
- Probabilistic Integration of Object Level Annotations in Chest X-ray Classification
- Shot-frugal and Robust quantum kernel classifiers
- Differential Bias: On the Perceptibility of Stance Imbalance in Argumentation
- Behavioral graph fraud detection in E-commerce
- CUF: Continuous Upsampling Filters
- Causality-driven Hierarchical Structure Discovery for Reinforcement Learning
- Feature-Adaptive Interactive Thresholding of Large 3D Volumes
- A Survey on Explainable Anomaly Detection
- Darwinian Model Upgrades: Model Evolving with Selective Compatibility
- SageMix: Saliency-Guided Mixup for Point Clouds
- Multilingual Zero Resource Speech Recognition Base on Self-Supervise Pre-Trained Acoustic Models
- On the potential benefits of entropic regularization for smoothing Wasserstein estimators
- NoMorelization: Building Normalizer-Free Models from a Sample's Perspective
- On the Explainability of Natural Language Processing Deep Models
- Sentence Ambiguity, Grammaticality and Complexity Probes
- Delta-Closure Structure for Studying Data Distribution
- Scene Text Image Super-Resolution via Content Perceptual Loss and Criss-Cross Transformer Blocks
- Wider and Higher: Intensive Integration and Global Foreground Perception for Image Matting
- Automotive Multilingual Fault Diagnosis
- A Direct Approximation of AIXI Using Logical State Abstractions
- On the Evaluation of the Plausibility and Faithfulness of Sentiment Analysis Explanations
- Adapting Behaviour Based On Trust In Human-Agent Ad Hoc Teamwork
- CNTN: Cyclic Noise-tolerant Network for Gait Recognition
- HoechstGAN: Virtual Lymphocyte Staining Using Generative Adversarial Networks
- Feature-Proxy Transformer for Few-Shot Segmentation
- Hierarchical and Progressive Image Matting
- Entropy Approximation by Machine Learning Regression: Application for Irregularity Evaluation of Images in Remote Sensing
- GA-SAM: Gradient-Strength based Adaptive Sharpness-Aware Minimization for Improved Generalization
- Experimental Design for Multi-Channel Imaging via Task-Driven Feature Selection
- AccelAT: A Framework for Accelerating the Adversarial Training of Deep Neural Networks through Accuracy Gradient
- ROS-PyBullet Interface: A Framework for Reliable Contact Simulation and Human-Robot Interaction
- ImaginaryNet: Learning Object Detectors without Real Images and Annotations
- Geometric Active Learning for Segmentation of Large 3D Volumes
- Algorithms for Weighted Pushdown Automata
- RaP: Redundancy-aware Video-language Pre-training for Text-Video Retrieval
- CS-Insights: A System for Analyzing Computer Science Research
- Pre-Avatar: An Automatic Presentation Generation Framework Leveraging Talking Avatar
- Learning Physical Dynamics with Subequivariant Graph Neural Networks
- Data augmentation on-the-fly and active learning in data stream classification
- Dirichlet process mixture models for non-stationary data streams
- Adv-Attribute: Inconspicuous and Transferable Adversarial Attack on Face Recognition
- NeuralRoom: Geometry-Constrained Neural Implicit Surfaces for Indoor Scene Reconstruction
- Overview of BioASQ 2022: The tenth BioASQ challenge on Large-Scale Biomedical Semantic Indexing and Question Answering
- Sample-Then-Optimize Batch Neural Thompson Sampling
- Retrospectives on the Embodied AI Workshop
- An α-regret analysis of Adversarial Bilateral Trade
- Multi-agent Dynamic Algorithm Configuration
- Exploiting Mixed Unlabeled Data for Detecting Samples of Seen and Unseen Out-of-Distribution Classes
- Multi-Target XGBoostLSS Regression
- Ensemble Creation via Anchored Regularization for Unsupervised Aspect Extraction
- Rethinking Annotation: Can Language Learners Contribute?
- Fast Optimization of Weighted Sparse Decision Trees for use in Optimal Treatment Regimes and Optimal Policy Design
- An Empirical Study on Finding Spans
- Scalable Neural Video Representations with Learnable Positional Features
- Personalized Federated Hypernetworks for Privacy Preservation in Multi-Task Reinforcement Learning
- Mean-field analysis for heavy ball methods: Dropout-stability, connectivity, and global convergence
- ALIFE: Adaptive Logit Regularizer and Feature Replay for Incremental Semantic Segmentation
- CROWDLAB: Supervised learning to infer consensus labels and quality scores for data with multiple annotators
- On the calibration of underrepresented classes in LiDAR-based semantic segmentation
- Improving Out-of-Distribution Generalization by Adversarial Training with Structured Priors
- OOOE: Only-One-Object-Exists Assumption to Find Very Small Objects in Chest Radiographs
- Benchmarking Long-tail Generalization with Likelihood Splits
- Subspace-Contrastive Multi-View Clustering
- SDW-ASL: A Dynamic System to Generate Large Scale Dataset for Continuous American Sign Language
- Large-Scale Open-Set Classification Protocols for ImageNet
- TiDAL: Learning Training Dynamics for Active Learning
- Observed Adversaries in Deep Reinforcement Learning
- Evaluating the Label Efficiency of Contrastive Self-Supervised Learning for Multi-Resolution Satellite Imagery
- An efficient combination strategy for hybird quantum ensemble classifier
- Efficient circuit implementation for coined quantum walks on binary trees and application to reinforcement learning
- Closed-book Question Generation via Contrastive Learning
- Intermediate Prototype Mining Transformer for Few-Shot Semantic Segmentation
- Generalized Inter-class Loss for Gait Recognition
- X-Align: Cross-Modal Cross-View Alignment for Bird's-Eye-View Segmentation
- Improving the Reliability for Confidence Estimation
- Re3: Generating Longer Stories With Recursive Reprompting and Revision
- An Additive Autoencoder for Dimension Estimation
- Mitigating Unintended Memorization in Language Models via Alternating Teaching
- Feature Reconstruction Attacks and Countermeasures of DNN training in Vertical Federated Learning
- Outlier-Robust Group Inference via Gradient Space Clustering
- Decoding Visual Neural Representations by Multimodal Learning of Brain-Visual-Linguistic Features
- Reducing Annotation Effort by Identifying and Labeling Contextually Diverse Classes for Semantic Segmentation Under Domain Shift
- Shortcomings of Question Answering Based Factuality Frameworks for Error Localization
- DCANet: Differential Convolution Attention Network for RGB-D Semantic Segmentation
- H2RBox: Horizontal Box Annotation is All You Need for Oriented Object Detection
- Why self-attention is Natural for Sequence-to-Sequence Problems? A Perspective from Symmetries
- Equal Improvability: A New Fairness Notion Considering the Long-term Impact
- A Stream Learning Approach for Real-Time Identification of False Data Injection Attacks in Cyber-Physical Power Systems
- On the Efficient Implementation of High Accuracy Optimality of Profile Maximum Likelihood
- Assessing Out-of-Domain Language Model Performance from Few Examples
- Stochastic noise can be helpful for variational quantum algorithms
- Few-shot Relational Reasoning via Connection Subgraph Pretraining
- LIME: Weakly-Supervised Text Classification Without Seeds
- Reward Imputation with Sketching for Contextual Batched Bandits
- Hybrid RL: Using Both Offline and Online Data Can Make RL Efficient
- Low-resource Neural Machine Translation with Cross-modal Alignment
- Weighted Distillation with Unlabeled Examples
- Categorizing Semantic Representations for Neural Machine Translation
- Q-ViT: Accurate and Fully Quantized Low-bit Vision Transformer
- Jointly Reinforced User Simulator and Task-oriented Dialog System with Simplified Generative Architecture
- From Gradient Flow on Population Loss to Learning with Stochastic Gradient Descent
- COLLIDER: A Robust Training Framework for Backdoor Data
- A Mixture of Surprises for Unsupervised Reinforcement Learning
- Empirical Evaluation of Data Augmentations for Biobehavioral Time Series Data with Deep Learning
- Parameter-Efficient Masking Networks
- SubeventWriter: Iterative Sub-event Sequence Generation with Coherence Controller
- Overlooked Video Classification in Weakly Supervised Video Anomaly Detection
- Real Spike: Learning Real-valued Spikes for Spiking Neural Networks
- Augmenting Flight Training with AI to Efficiently Train Pilots
- Application-Driven AI Paradigm for Hand-Held Action Detection
- Brain Network Transformer
- Walk a Mile in Their Shoes: a New Fairness Criterion for Machine Learning
- Variance-Aware Estimation of Kernel Mean Embedding
- Wasserstein Barycenter-based Model Fusion and Linear Mode Connectivity of Neural Networks
- Understanding the Effect of Smartphone Cameras on Estimating Munsell Soil Colors from Imagery
- Are Macula or Optic Nerve Head Structures better at Diagnosing Glaucoma? An Answer using AI and Wide-Field Optical Coherence Tomography
- Action Matching: Learning Stochastic Dynamics from Samples
- Structural Pruning via Latency-Saliency Knapsack
- Knowledge-grounded Dialog State Tracking
- Interpreting Neural Policies with Disentangled Tree Representations
- Neuro-symbolic Explainable Artificial Intelligence Twin for Zero-touch IoE in Wireless Network
- The COVID That Wasn't: Counterfactual Journalism Using GPT
- What's in a Decade? Transforming Faces Through Time
- Compute-Efficient Deep Learning: Algorithmic Trends and Opportunities
- A Bayesian Optimization Framework for Finding Local Optima in Expensive Multi-Modal Functions
- Equi-Tuning: Group Equivariant Fine-Tuning of Pretrained Models