Papers
Mon 21 Mar 2022
192 papers
- Relevant CommonSense Subgraphs for "What if..." Procedural ReasoningLLM reasoning → Knowledge- and tool-augmented reasoning
- Self-Consistency Improves Chain of Thought Reasoning in Language ModelsLLM reasoning → Prompting and chain-of-thought reasoning
- Flow-matching -- efficient coarse-graining of molecular dynamics without forcesDiffusion models → Flow matching, time series and science
- PACS: A Dataset for Physical Audiovisual CommonSense ReasoningLLM reasoning → Audio-language model reasoning
- Optimizing Trajectories for Highway Driving with Offline Reinforcement LearningEnd-to-end autonomous driving → Reinforcement learning for driving +1
- Self-Imitation Learning from DemonstrationsOffline RL and imitation learning from data → Imitation learning methods
- Document-Level Relation Extraction with Adaptive Focal Loss and Knowledge DistillationKnowledge distillation → Knowledge distillation for LLMs
- Hate Speech Classification Using SVM and Naive BAYES
- LQoCo: Learning to Optimize Cache Capacity Overloading in Storage Systems
- Semantic Similarity Computing for Scientific Academic Conferences fused with domain features
- Web Page Content Extraction Based on Multi-feature Fusion
- ImageNet Challenging Classification with the Raspberry Pi: An Incremental Local Stochastic Gradient Descent Algorithm
- AI-enabled Assessment of Cardiac Systolic and Diastolic Function from Echocardiography
- BEFANA: A Tool for Biodiversity-Ecosystem Functioning Assessment by Network Analysis
- Survival Analysis for Idiopathic Pulmonary Fibrosis using CT Images and Incomplete Clinical Data
- Optimizing Binary Decision Diagrams with MaxSAT for classification
- DIANES: A DEI Audit Toolkit for News Sources
- Preference Exploration for Efficient Bayesian Optimization with Multiple Outcomes
- A Bayesian Deep Learning Technique for Multi-Step Ahead Solar Generation Forecasting
- HyperShot: Few-Shot Learning by Kernel HyperNetworks
- Sequential algorithmic modification with test data reuse
- Two methods for Jamming Identification in UAVs Networks using New Synthetic Dataset
- Language modeling via stochastic processes
- Temporal Abstractions-Augmented Temporally Contrastive Learning: An Alternative to the Laplacian in RL
- Audio visual character profiles for detecting background characters in entertainment media
- Towards a Change Taxonomy for Machine Learning Systems
- An Information-theoretic Approach to Prompt Engineering Without Ground Truth Labels
- PI-VAE: Physics-Informed Variational Auto-Encoder for stochastic differential equations
- Segmenting Medical Instruments in Minimally Invasive Surgeries using AttentionMask
- Origami in N dimensions: How feed-forward networks manufacture linear separability
- Global Matching with Overlapping Attention for Optical Flow Estimation
- On The Robustness of Offensive Language Classifiers
- Enhancing Speech Recognition Decoding via Layer Aggregation
- Learning robot motor skills with mixed reality
- Training Quantised Neural Networks with STE Variants: the Additive Noise Annealing Algorithm
- Alarm-Based Root Cause Analysis in Industrial Processes Using Deep Learning
- The Change that Matters in Discourse Parsing: Estimating the Impact of Domain Shift on Parser Error
- Generative Adversarial Network for Future Hand Segmentation from Egocentric Video
- Benchmarking Test-Time Unsupervised Deep Neural Network Adaptation on Edge Devices
- PCA-RF: An Efficient Parkinson's Disease Prediction Model based on Random Forest Classification
- A Contrastive Objective for Learning Disentangled Representations
- NeRFusion: Fusing Radiance Fields for Large-Scale Scene Reconstruction
- Healthy Twitter discussions? Time will tell
- Efficient Classification of Long Documents Using Transformers
- A survey on GANs for computer vision: Recent research, analysis and taxonomy
- DQ-BART: Efficient Sequence-to-Sequence Model via Joint Distillation and Quantization
- The Conceptual VAE
- ME-Net: Multi-Encoder Net Framework for Brain Tumor Segmentation
- ReCCoVER: Detecting Causal Confusion for Explainable Reinforcement Learning
- Disentangling Patterns and Transformations from One Sequence of Images with Shape-invariant Lie Group Transformer
- On the Effect of Pre-Processing and Model Complexity for Plastic Analysis Using Short-Wave-Infrared Hyper-Spectral Imaging
- An efficient heuristic approach combining maximal itemsets and area measure for compressing voluminous table constraints
- Test-time Adaptation with Slot-Centric Models
- Transforming Model Prediction for Tracking
- Robust Visual Tracking by Segmentation
- Masked Discrimination for Self-Supervised Learning on Point Clouds
- Physics-driven Synthetic Data Learning for Biomedical Magnetic Resonance
- One After Another: Learning Incremental Skills for a Changing World
- DiffPoseNet: Direct Differentiable Camera Pose Estimation
- Interpreting Class Conditional GANs with Channel Awareness
- Drive&Segment: Unsupervised Semantic Segmentation of Urban Scenes via Cross-modal Distillation
- Operator Sketching for Deep Unrolling Networks
- Teaching language models to support answers with verified quotes
- Multispectral Satellite Data Classification using Soft Computing Approach
- Can we integrate spatial verification methods into neural-network loss functions for atmospheric science?
- Not All Points Are Equal: Learning Highly Efficient Point-based Detectors for 3D LiDAR Point Clouds
- Review of Disentanglement Approaches for Medical Applications -- Towards Solving the Gordian Knot of Generative Models in Healthcare
- Towards Explainable Evaluation Metrics for Natural Language Generation
- No Pain, Big Gain: Classify Dynamic Point Cloud Sequences with Static Models by Fitting Feature-level Space-time Surfaces
- Facial Expression Analysis Using Decomposed Multiscale Spatiotemporal Networks
- FGAN: Federated Generative Adversarial Networks for Anomaly Detection in Network Traffic
- High-fidelity GAN Inversion with Padding Space
- Diverse Counterfactual Explanations for Anomaly Detection in Time Series
- CLIP meets GamePhysics: Towards bug identification in gameplay videos using zero-shot transfer learning
- Automated Clinical Coding: What, Why, and Where We Are?
- PersFormer: 3D Lane Detection via Perspective Transformer and the OpenLane Benchmark
- Ovid: A Machine Learning Approach for Automated Vandalism Detection in OpenStreetMap
- Overcoming Oscillations in Quantization-Aware Training
- Telling Stories from Computational Notebooks: AI-Assisted Presentation Slides Creation for Presenting Data Science Work
- MixFormer: End-to-End Tracking with Iterative Mixed Attention
- Image Classification on Accelerated Neural Networks
- MTBF-33: A multi-temporal building footprint dataset for 33 counties in the United States (1900-2015)
- Collaborative Learning for Cyberattack Detection in Blockchain Networks
- Dense Siamese Network for Dense Unsupervised Learning
- From Concept Drift to Model Degradation: An Overview on Performance-Aware Drift Detectors
- Learning Enriched Illuminants for Cross and Single Sensor Color Constancy
- Optimizing Revenue Maximization and Demand Learning in Airline Revenue Management
- Targeted Extraction of Temporal Facts from Textual Resources for Improved Temporal Question Answering over Knowledge Bases
- AutoTTS: End-to-End Text-to-Speech Synthesis through Differentiable Duration Modeling
- How Do We Answer Complex Questions: Discourse Structure of Long-form Answers
- A new perspective on probabilistic image modeling
- Voltage-Dependent Synaptic Plasticity (VDSP): Unsupervised probabilistic Hebbian plasticity rule based on neurons membrane potential
- Stereo Neural Vernier Caliper
- Continual Spatio-Temporal Graph Convolutional Networks
- Transformer-based HTR for Historical Documents
- Computational ergonomics for task delegation in Human-Robot Collaboration: spatiotemporal adaptation of the robot to the human through contactless gesture recognition
- Underwater Light Field Retention : Neural Rendering for Underwater Imaging
- Self-Supervised Road Layout Parsing with Graph Auto-Encoding
- Word Order Does Matter (And Shuffled Language Models Know It)
- Spoofing-Aware Speaker Verification with Unsupervised Domain Adaptation
All 192
- Minimum Variance Unbiased N:M Sparsity for the Neural Gradients
- Hierarchical autoregressive neural networks for statistical systems
- BNS-GCN: Efficient Full-Graph Training of Graph Convolutional Networks with Partition-Parallelism and Random Boundary Node Sampling
- MonoDTR: Monocular 3D Object Detection with Depth-Aware Transformer
- Improving anatomical plausibility in medical image segmentation via hybrid graph neural networks: applications to chest x-ray analysis
- GCF: Generalized Causal Forest for Heterogeneous Treatment Effect Estimation in Online Marketplace
- Towards Self-Supervised Gaze Estimation
- A Local Convergence Theory for the Stochastic Gradient Descent Method in Non-Convex Optimization With Non-isolated Local Minima
- AraBART: a Pretrained Arabic Sequence-to-Sequence Model for Abstractive Summarization
- Quality Controlled Paraphrase Generation
- General and Domain Adaptive Chinese Spelling Check with Error Consistent Pretraining
- 3D Multi-Object Tracking Using Graph Neural Networks with Cross-Edge Modality Attention
- Learning Occlusion-Aware Coarse-to-Fine Depth Map for Self-supervised Monocular Depth Estimation
- TinyMLOps: Operational Challenges for Widespread Edge AI Adoption
- Depth Completion using Geometry-Aware Embedding
- x-enVENT: A Corpus of Event Descriptions with Experiencer-specific Emotion and Appraisal Annotations
- PublicCheck: Public Integrity Verification for Services of Run-time Deep Models
- Unified Multivariate Gaussian Mixture for Efficient Neural Image Compression
- Revisiting Domain Generalized Stereo Matching Networks from a Feature Consistency Perspective
- ELIC: Efficient Learned Image Compression with Unevenly Grouped Space-Channel Contextual Adaptive Coding
- Zoom Out and Observe: News Environment Perception for Fake News Detection
- Efficient Algorithms for Extreme Bandits
- Efficient Remote Photoplethysmography with Temporal Derivative Modules and Time-Shift Invariant Loss
- Unsupervised Network Embedding Beyond Homophily
- Multi-class Label Noise Learning via Loss Decomposition and Centroid Estimation
- RGB-Depth Fusion GAN for Indoor Depth Completion
- Paraphrasing Techniques for Maritime QA system
- Boost Test-Time Performance with Closed-Loop Inference
- Multi-modal learning for predicting the genotype of glioma
- Neural Token Segmentation for High Token-Internal Complexity
- Multitask Neuroevolution for Reinforcement Learning with Long and Short Episodes
- TCM-SD: A Benchmark for Probing Syndrome Differentiation via Natural Language Processing
- Multi-class versus One-class classifier in spontaneous speech analysis oriented to Alzheimer Disease diagnosis
- Hyperbolic Vision Transformers: Combining Improvements in Metric Learning
- Perceptual Features as Markers of Parkinson's Disease: The Issue of Clinical Interpretability
- Long Short-Term Memory for Spatial Encoding in Multi-Agent Path Planning
- Sem2NeRF: Converting Single-View Semantic Masks to Neural Radiance Fields
- Hierarchical Path-planning from Speech Instructions with Spatial Concept-based Topometric Semantic Mapping
- ARM: Any-Time Super-Resolution Method
- AnoViT: Unsupervised Anomaly Detection and Localization with Vision Transformer-based Encoder-Decoder
- ViM: Out-Of-Distribution with Virtual-logit Matching
- Longitudinal Self-Supervision for COVID-19 Pathology Quantification
- Graph Neural Networks for Wireless Communications: From Theory to Practice
- Effective Token Graph Modeling using a Novel Labeling Strategy for Structured Sentiment Analysis
- Human-Centric Artificial Intelligence Architecture for Industry 5.0 Applications
- Phase-Aware Spoof Speech Detection Based on Res2Net with Phase Network
- ScalableViT: Rethinking the Context-oriented Generalization of Vision Transformer
- Domain Generalization by Mutual-Information Regularization with Pre-trained Models
- Classifications of Skull Fractures using CT Scan Images via CNN with Lazy Learning Approach
- GroupTransNet: Group Transformer Network for RGB-D Salient Object Detection
- Adaptive and Cascaded Compressive Sensing
- Delving into the Estimation Shift of Batch Normalization in a Network
- K-space and Image Domain Collaborative Energy based Model for Parallel MRI Reconstruction
- Fictitious Play with Maximin Initialization
- Slice Imputation: Intermediate Slice Interpolation for Anisotropic 3D Medical Image Segmentation
- ASE: Anomaly Scoring Based Ensemble Learning for Imbalanced Datasets
- Upsampling Autoencoder for Self-Supervised Point Cloud Learning
- Harnessing Hard Mixed Samples with Decoupled Regularizer
- A Slot Is Not Built in One Utterance: Spoken Language Dialogs with Sub-Slots
- Strong posterior contraction rates via Wasserstein dynamics
- Match the Script, Adapt if Multilingual: Analyzing the Effect of Multilingual Pretraining on Cross-lingual Transferability
- XTREME-S: Evaluating Cross-lingual Speech Representations
- WeSinger: Data-augmented Singing Voice Synthesis with Auxiliary Losses
- STCGAT: A Spatio-temporal Causal Graph Attention Network for traffic flow prediction in Intelligent Transportation Systems
- EAutoDet: Efficient Architecture Search for Object Detection
- Programming Language Agnostic Mining of Code and Language Pairs with Sequence Labeling Based Question Answering
- Academic Resource Text Level Multi-label Classification based on Attention
- HIBRIDS: Attention with Hierarchical Biases for Structure-aware Long Document Summarization
- Tree Energy Loss: Towards Sparsely Annotated Semantic Segmentation
- The activity-weight duality in feed forward neural networks: The geometric determinants of generalization
- Research Scholar Interest Mining Method based on Load Centrality
- Semantic Segmentation with Active Semi-Supervised Learning
- DSRRTracker: Dynamic Search Region Refinement for Attention-based Siamese Multi-Object Tracking
- TransFusion: Multi-view Divergent Fusion for Medical Image Segmentation with Transformers
- An Intermediate-level Attack Framework on The Basis of Linear Regression
- LocATe: End-to-end Localization of Actions in 3D with Transformers
- Prediction Algorithm for Heat Demand of Science and Technology Topics Based on Time Convolution Network
- An Intellectual Property Entity Recognition Method Based on Transformer and Technological Word Information
- Forecast Evaluation for Data Scientists: Common Pitfalls and Best Practices
- A Prompting-based Approach for Adversarial Example Generation and Robustness Enhancement
- Disentangling Architecture and Training for Optical Flow
- Monocular Vision-based Prediction of Cut-in Maneuvers with LSTM Networks
- Compression of Generative Pre-trained Language Models via Quantization
- HP-Capsule: Unsupervised Face Part Discovery by Hierarchical Parsing Capsule Network
- A Policy Driven AI-Assisted PoW Framework
- FAR: Fourier Aerial Video Recognition
- Leveraging Expert Guided Adversarial Augmentation For Improving Generalization in Named Entity Recognition
- Better Language Model with Hypernym Class Prediction
- CNN Attention Guidance for Improved Orthopedics Radiographic Fracture Classification
- Online Continual Learning for Embedded Devices
- Learning latent causal relationships in multiple time series
- FaceMap: Towards Unsupervised Face Clustering via Map Equation