Papers
Tue 15 Mar 2022
221 papers
- Multi-View Dreaming: Multi-View World Model with Contrastive LearningWorld models → Latent dynamics models and model-based RL
- ReACC: A Retrieval-Augmented Code Completion FrameworkRetrieval-augmented generation → RAG for code
- Evaluating the Text-to-SQL Capabilities of Large Language Models
- Blocks Assemble! Learning to Assemble with Large-Scale Structured Reinforcement Learning
- Vision-Based Manipulators Need to Also See from Their Hands
- MMES: Mixture Model based Evolution Strategy for Large-Scale Optimization
- Reducing overestimating and underestimating volatility via the augmented blending-ARCH model
- Model Comparison in Approximate Bayesian Computation
- Seamless lightning nowcasting with recurrent-convolutional deep learning
- Learning to Optimize Resource Assignment for Task Offloading in Mobile Edge Computing
- Training a Tokenizer for Free with Private Federated Learning
- Privacy-Preserving Speech Representation Learning using Vector Quantization
- CaRTS: Causality-driven Robot Tool Segmentation from Vision and Kinematics Data
- Self-Normalized Density Map (SNDM) for Counting Microbiological Objects
- QUBOs for Sorting Lists and Building Trees
- Semi-FedSER: Semi-supervised Learning for Speech Emotion Recognition On Federated Learning using Multiview Pseudo-Labeling
- Neural-Network-Directed Genetic Programmer for Discovery of Governing Equations
- Disparities in Dermatology AI Performance on a Diverse, Curated Clinical Image Set
- New directions for surrogate models and differentiable programming for High Energy Physics detector simulation
- Physics-Informed Neural Networks with Adaptive Localized Artificial Viscosity
- ADATIME: A Benchmarking Suite for Domain Adaptation on Time Series Data
- TAKDE: Temporal Adaptive Kernel Density Estimator for Real-Time Dynamic Density Estimation
- An explainability framework for cortical surface-based deep learning
- Multilingual Generative Language Models for Zero-Shot Cross-Lingual Event Argument Extraction
- Improving Word Translation via Two-Stage Contrastive Learning
- Hyperdecoders: Instance-specific decoders for multi-task NLP
- FastKASSIM: A Fast Tree Kernel-Based Syntactic Similarity Metric
- Self-Distribution Distillation: Efficient Uncertainty Estimation
- Driving Anomaly Detection Using Conditional Generative Adversarial Network
- Bi-Manual Manipulation and Attachment via Sim-to-Real Reinforcement Learning
- Non-neural Models Matter: A Re-evaluation of Neural Referring Expression Generation Systems
- Active Exploration for Neural Global Illumination of Variable Scenes
- 2-speed network ensemble for efficient classification of incremental land-use/land-cover satellite image chips
- Neural RF SLAM for unsupervised positioning and mapping with channel state information
- Better Quality Estimation for Low Resource Corpus Mining
- Differentiable Multi-Agent Actor-Critic for Multi-Step Radiology Report Summarization
- Non-Linear Reinforcement Learning in Large Action Spaces: Structural Conditions and Sample-efficiency of Posterior Sampling
- Reconstructing Missing EHRs Using Time-Aware Within- and Cross-Visit Information for Septic Shock Early Prediction
- Toward Improving Attentive Neural Networks in Legal Text Processing
- Unified Visual Transformer Compression
- Data Contamination: From Memorization to Exploitation
- A Deep Dive into Dataset Imbalance and Bias in Face Identification
- Sex Trouble: Common pitfalls in incorporating sex/gender in medical machine learning and how to avoid them
- Zipfian environments for Reinforcement Learning
- CrowdMLP: Weakly-Supervised Crowd Counting via Multi-Granularity MLP
- Interactive Portrait Harmonization
- Auto-Gait: Automatic Ataxia Risk Assessment with Computer Vision on Gait Task Videos
- HUMUS-Net: Hybrid unrolled multi-scale network architecture for accelerated MRI reconstruction
- AUTOMATA: Gradient Based Data Subset Selection for Compute-Efficient Hyper-parameter Tuning
- A Differentiable Approach to Combinatorial Optimization using Dataless Neural Networks
- SocialVAE: Human Trajectory Prediction using Timewise Latents
- Learning Deep Implicit Fourier Neural Operators (IFNOs) with Applications to Heterogeneous Material Modeling
- DeepFusion: Lidar-Camera Deep Fusion for Multi-Modal 3D Object Detection
- UNet Architectures in Multiplanar Volumetric Segmentation -- Validated on Three Knee MRI Cohorts
- Fiber Bundle Morphisms as a Framework for Modeling Many-to-Many Maps
- SemiPFL: Personalized Semi-Supervised Federated Learning Framework for Edge Intelligence
- Towards understanding deep learning with the natural clustering prior
- Sensitivity Estimation for Dark Matter Subhalos in Synthetic Gaia DR2 using Deep Learning
- A physics and data co-driven surrogate modeling approach for temperature field prediction on irregular geometric domain
- MoReL: Multi-omics Relational Learning
- Object Manipulation via Visual Target Localization
- Learning Spatio-Temporal Downsampling for Effective Video Upscaling
- CryoAI: Amortized Inference of Poses for Ab Initio Reconstruction of 3D Molecular Volumes from Real Cryo-EM Images
- Privacy-Aware Compression for Federated Data Analysis
- Animatable Implicit Neural Representations for Creating Realistic Avatars from Videos
- One Network Doesn't Rule Them All: Moving Beyond Handcrafted Architectures in Self-Supervised Learning
- Can Neural Nets Learn the Same Model Twice? Investigating Reproducibility and Double Descent from the Decision Boundary Perspective
- From 2D to 3D: Re-thinking Benchmarking of Monocular Depth Prediction
- Deep Learning without Shortcuts: Shaping the Kernel with Tailored Rectifiers
- Representation Learning for Resource-Constrained Keyphrase Generation
- Does Corpus Quality Really Matter for Low-Resource Languages?
- ARTEMIS: Attention-based Retrieval with Text-Explicit Matching and Implicit Similarity
- On Suspicious Coincidences and Pointwise Mutual Information
- Measuring the Impact of (Psycho-)Linguistic and Readability Features and Their Spill Over Effects on the Prediction of Eye Movement Patterns
- Regenerative Particle Thompson Sampling
- Implicit Feature Decoupling with Depthwise Quantization
- Things not Written in Text: Exploring Spatial Commonsense from Visual Signals
- Practical data monitoring in the internet-services domain
- Surrogate Gap Minimization Improves Sharpness-Aware Training
- MotionCLIP: Exposing Human Motion Generation to CLIP Space
- A novel sampler for Gauss-Hermite determinantal point processes with application to Monte Carlo integration
- Seeking Commonness and Inconsistencies: A Jointly Smoothed Approach to Multi-view Subspace Clustering
- Graph filtering over expanding graphs
- POETREE: Interpretable Policy Learning with Adaptive Decision Trees
- Machine Learning and Cosmology
- Modular and Parameter-Efficient Multimodal Fusion with Prompting
- On Hyperbolic Embeddings in 2D Object Detection
- A multi-organ point cloud registration algorithm for abdominal CT registration
- Simultaneous Localisation and Mapping with Quadric Surfaces
- Deep learning for radar data exploitation of autonomous vehicle
- A Noise-level-aware Framework for PET Image Denoising
- Data-Efficient Graph Grammar Learning for Molecular Generation
- Natural Hierarchical Cluster Analysis by Nearest Neighbors with Near-Linear Time Complexity
- End-to-End Modeling via Information Tree for One-Shot Natural Language Spatial Video Grounding
- Approximate Decision Trees For Machine Learning Classification on Tiny Printed Circuits
- Beyond Explaining: Opportunities and Challenges of XAI-Based Model Improvement
- Data Smells in Public Datasets
- InvPT: Inverted Pyramid Multi-task Transformer for Dense Scene Understanding
- RotateQVS: Representing Temporal Information as Rotations in Quaternion Vector Space for Temporal Knowledge Graph Completion
- Approximability and Generalisation
All 221
- Smoothing Matters: Momentum Transformer for Domain Adaptive Semantic Segmentation
- Linear-Time Verification of Data-Aware Dynamic Systems with Arithmetic
- Object Detection as Probabilistic Set Prediction
- OcclusionFusion: Occlusion-aware Motion Estimation for Real-time Dynamic 3D Reconstruction
- On the Pitfalls of Batch Normalization for End-to-End Video Learning: A Study on Surgical Workflow Analysis
- Categorical Representation Learning and RG flow operators for algorithmic classifiers
- MOBDrone: a Drone Video Dataset for Man OverBoard Rescue
- PDNS-Net: A Large Heterogeneous Graph Benchmark Dataset of Network Resolutions for Graph Learning
- Intrinsic Neural Fields: Learning Functions on Manifolds
- Learning Expanding Graphs for Signal Interpolation
- Variational inference of fractional Brownian motion with linear computational complexity
- Generating Privacy-Preserving Process Data with Deep Generative Models
- NINNs: Nudging Induced Neural Networks
- Reachability In Simple Neural Networks
- Threat Detection for General Social Engineering Attack Using Machine Learning Techniques
- Style Transformer for Image Inversion and Editing
- DialogueNeRF: Towards Realistic Avatar Face-to-Face Conversation Video Generation
- Relative Pose from SIFT Features
- Unsupervised Extractive Opinion Summarization Using Sparse Coding
- GPV-Pose: Category-level Object Pose Estimation via Geometry-guided Point-wise Voting
- Scalable Bigraphical Lasso: Two-way Sparse Network Inference for Count Data
- Signal in Noise: Exploring Meaning Encoded in Random Character Sequences with Character-Aware Language Models
- Panoptic SwiftNet: Pyramidal Fusion for Real-time Panoptic Segmentation
- Gold Doesn't Always Glitter: Spectral Removal of Linear and Nonlinear Guarded Attribute Information
- K-VQG: Knowledge-aware Visual Question Generation for Common-sense Acquisition
- Comparing Two Samples Through Stochastic Dominance: A Graphical Approach
- LiP-Flow: Learning Inference-time Priors for Codec Avatars via Normalizing Flows in Latent Space
- Regret Bounds for Expected Improvement Algorithms in Gaussian Process Bandit Optimization
- Imputing Out-of-Vocabulary Embeddings with LOVE Makes Language Models Robust with Little Cost
- Improved Multi-label Classification under Temporal Concept Drift: Rethinking Group-Robust Algorithms in a Label-Wise Setting
- SCD: Self-Contrastive Decorrelation for Sentence Embeddings
- Bamboo: Building Mega-Scale Vision Dataset Continually with Human-Machine Synergy
- What is the best RNN-cell structure to forecast each time series behavior?
- Pose-MUM : Reinforcing Key Points Relationship for Semi-Supervised Human Pose Estimation
- Graph Pre-training for AMR Parsing and Generation
- Better Uncertainty Calibration via Proper Scores for Classification and Beyond
- Learning to Infer Belief Embedded Communication
- Graph Convolutional Neural Networks Sensitivity under Probabilistic Error Model
- Do BERTs Learn to Use Browser User Interface? Exploring Multi-Step Tasks with Unified Vision-and-Language BERTs
- SPA-VAE: Similar-Parts-Assignment for Unsupervised 3D Point Cloud Generation
- SISL:Self-Supervised Image Signature Learning for Splicing Detection and Localization
- Adversarial Counterfactual Augmentation: Application in Alzheimer's Disease Classification
- Image Quality Assessment for Magnetic Resonance Imaging
- Interspace Pruning: Using Adaptive Filter Representations to Improve Training of Sparse CNNs
- End-to-end P300 BCI using Bayesian accumulation of Riemannian probabilities
- On the focusing of thermal images
- A Framework for Verifiable and Auditable Federated Anomaly Detection
- Igeood: An Information Geometry Approach to Out-of-Distribution Detection
- Multi-Unit Diffusion Auctions with Intermediaries
- Parking Analytics Framework using Deep Learning
- Scalable Penalized Regression for Noise Detection in Learning with Noisy Labels
- The Ghost in the Machine has an American accent: value conflict in GPT-3
- Complex Evolutional Pattern Learning for Temporal Knowledge Graph Reasoning
- UniSAr: A Unified Structure-Aware Autoregressive Language Model for Text-to-SQL
- Social Choice Around the Block: On the Computational Social Choice of Blockchain
- Fast Autofocusing using Tiny Transformer Networks for Digital Holographic Microscopy
- Reactive Motion Generation on Learned Riemannian Manifolds
- Multi-Curve Translator for High-Resolution Photorealistic Image Translation
- Generative models and Bayesian inversion using Laplace approximation
- Real-time Neural-MPC: Deep Learning Model Predictive Control for Quadrotors and Agile Robotic Platforms
- ViWOZ: A Multi-Domain Task-Oriented Dialogue Systems Dataset For Low-resource Language
- Exact Feature Distribution Matching for Arbitrary Style Transfer and Domain Generalization
- GCT: Graph Co-Training for Semi-Supervised Few-Shot Learning
- An Annotation-free Restoration Network for Cataractous Fundus Images
- Augmenting Document Representations for Dense Retrieval with Interpolation and Perturbation
- S2F2: Self-Supervised High Fidelity Face Reconstruction from Monocular Image
- Evaluating BERT-based Pre-training Language Models for Detecting Misinformation
- Securing the Classification of COVID-19 in Chest X-ray Images: A Privacy-Preserving Deep Learning Approach
- Meta Ordinal Regression Forest for Medical Image Classification with Ordinal Labels
- CODA: A Real-World Road Corner Case Dataset for Object Detection in Autonomous Driving
- Revitalize Region Feature for Democratizing Video-Language Pre-training of Retrieval
- LDP: Learnable Dynamic Precision for Efficient Deep Neural Network Training and Inference
- Magnification Prior: A Self-Supervised Method for Learning Representations on Breast Cancer Histopathological Images
- ActFormer: A GAN-based Transformer towards General Action-Conditioned 3D Human Motion Generation
- APRNet: Attention-based Pixel-wise Rendering Network for Photo-Realistic Text Image Generation
- Distribution-Aware Single-Stage Models for Multi-Person 3D Pose Estimation
- Implicit field supervision for robust non-rigid shape matching
- Supervised Contrastive Learning with Structure Inference for Graph Classification
- InsCon:Instance Consistency Feature Representation via Self-Supervised Learning
- Compressing Sentence Representation for Semantic Retrieval via Homomorphic Projective Distillation
- Enriched CNN-Transformer Feature Aggregation Networks for Super-Resolution
- DEPTS: Deep Expansion Learning for Periodic Time Series Forecasting
- Energy-efficient Dense DNN Acceleration with Signed Bit-slice Architecture
- Incorporating Heterophily into Graph Neural Networks for Graph Classification
- Unpaired Deep Image Dehazing Using Contrastive Disentanglement Learning
- An Introduction to Multi-Agent Reinforcement Learning and Review of its Application to Autonomous Mobility
- Distributed-Memory Sparse Kernels for Machine Learning
- Safe Neurosymbolic Learning with Differentiable Symbolic Execution
- Progressive End-to-End Object Detection in Crowded Scenes
- SATS: Self-Attention Transfer for Continual Semantic Segmentation
- One Agent To Rule Them All: Towards Multi-agent Conversational AI
- Can you even tell left from right? Presenting a new challenge for VQA
- What's in the Black Box? The False Negative Mechanisms Inside Object Detectors
- Breast Cancer Molecular Subtypes Prediction on Pathological Images with Discriminative Patch Selecting and Multi-Instance Learning
- Neural Radiance Projection
- Seamlessly Integrating Factual Information and Social Content with Persuasive Dialogue
- Wave-SAN: Wavelet based Style Augmentation Network for Cross-Domain Few-Shot Learning
- Generalized but not Robust? Comparing the Effects of Data Modification Methods on Out-of-Domain Generalization and Adversarial Robustness
- Contrastive Learning of Sociopragmatic Meaning in Social Media
- Efficient Long Sequence Encoding via Synchronization
- Can Synthetic Translations Improve Bitext Quality?
- Unsupervised Keyphrase Extraction via Interpretable Neural Networks
- Lifelong Matrix Completion with Sparsity-Number
- Improving Event Representation via Simultaneous Weakly Supervised Contrastive Learning and Clustering
- Graph Representation Learning for Popularity Prediction Problem: A Survey
- P-STMO: Pre-Trained Spatial Temporal Many-to-One Model for 3D Human Pose Estimation
- Multilingual Mix: Example Interpolation Improves Multilingual Neural Machine Translation
- Innovations in trigger and data acquisition systems for next-generation physics facilities
- Do Language Models Plagiarize?
- Learning What Not to Segment: A New Perspective on Few-Shot Segmentation
- CARETS: A Consistency And Robustness Evaluative Test Suite for VQA
- Online Task Assignment Problems with Reusable Resources
- Procedural Text Understanding via Scene-Wise Evolution
- Quantum Finite Automata and Quiver Algebras
- Task-Agnostic Robust Representation Learning
- Distraction is All You Need for Fairness
- Long Document Summarization with Top-down and Bottom-up Inference
- Accelerating Stochastic Probabilistic Inference
- TSM: Measuring the Enticement of Honeyfiles with Natural Language Processing
- Efficient and Optimal Fixed-Time Regret with Two Experts
- Time-series image denoising of pressure-sensitive paint data by projected multivariate singular spectrum analysis