Papers
Mon 12 Dec 2022
166 papers
- Decentralized cooperative perception for autonomous vehicles: Learning to value the unknownEnd-to-end autonomous driving → Cooperative and V2X driving
- Evaluation of Synthetic Datasets for Conversational Recommender SystemsSynthetic data and self-improvement for LLMs → LLM synthetic data generation
- Rodin: A Generative Model for Sculpting 3D Digital Avatars Using DiffusionDiffusion models → 3D, point cloud and scene generation
- Security of Deep Reinforcement Learning for Autonomous Driving: A SurveyEnd-to-end autonomous driving → Adversarial scenarios and safety testing
- The Stable Artist: Steering Semantics in Diffusion Latent SpaceDiffusion models → Image generation, text-to-image and editing
- Continuation KD: Improved Knowledge Distillation through the Lens of Continuation OptimizationKnowledge distillation → Knowledge distillation for LLMs
- RGBD2: Generative Scene Synthesis via Incremental View Inpainting using RGBD Diffusion ModelsDiffusion models → 3D, point cloud and scene generation
- Towards Practical Plug-and-Play Diffusion ModelsDiffusion models → Diffusion foundations and sampling
- Improving Generalization of Pre-trained Language Models via Stochastic Weight AveragingKnowledge distillation → Knowledge distillation for LLMs
- Diff-Font: Diffusion Model for Robust One-Shot Font GenerationDiffusion models → Image generation, text-to-image and editing
- CACTI: A Framework for Scalable Multi-Task Multi-Scene Visual Imitation LearningOffline RL and imitation learning from data → Robot manipulation imitation learning
- The use of Octree in point cloud analysis with application to cultural heritage
- MaNLP@SMM4H22: BERT for Classification of Twitter Posts
- Learning Optimal Phase-Shifts of Holographic Metasurface Transceivers
- TriNet: stabilizing self-supervised learning from complete or slow collapse on ASR
- Machine Learning for Detecting Malware in PE Files
- Page Layout Analysis of Text-heavy Historical Documents: a Comparison of Textual and Visual Approaches
- Siamese Sleep Transformer For Robust Sleep Stage Scoring With Self-knowledge Distillation and Selective Batch Sampling
- Tool flank wear prediction using high-frequency machine data from industrial edge device
- Mind the Retrosynthesis Gap: Bridging the divide between Single-step and Multi-step Retrosynthesis Prediction
- Nervus: A Comprehensive Deep Learning Classification, Regression, and Prognostication Tool for both Medical Image and Clinical Data Analysis
- Distributed Unconstrained Optimization with Time-varying Cost Functions
- Robust and Explainable Identification of Logical Fallacies in Natural Language Arguments
- Earthquake Impact Analysis Based on Text Mining and Social Media Analytics
- AI Model Utilization Measurements For Finding Class Encoding Patterns
- Forecasting Soil Moisture Using Domain Inspired Temporal Graph Convolution Neural Networks To Guide Sustainable Crop Management
- Agnostic Learning for Packing Machine Stoppage Prediction in Smart Factories
- Variance-Reduced Conservative Policy Iteration
- Decentralized Stochastic Multi-Player Multi-Armed Walking Bandits
- Efficient Bayesian Uncertainty Estimation for nnU-Net
- Mortality Prediction Models with Clinical Notes Using Sparse Attention at the Word and Sentence Levels
- An Ensemble Method to Automatically Grade Diabetic Retinopathy with Optical Coherence Tomography Angiography Images
- Data Leakage via Access Patterns of Sparse Features in Deep Learning-based Recommendation Systems
- You Only Need a Good Embeddings Extractor to Fix Spurious Correlations
- Learning Disturbances Online for Risk-Aware Control: Risk-Aware Flight with Less Than One Minute of Data
- Autoregressive Bandits
- ScanEnts3D: Exploiting Phrase-to-3D-Object Correspondences for Improved Visio-Linguistic Models in 3D Scenes
- Jointly Learning Visual and Auditory Speech Representations from Raw Data
- PathFusion: Path-consistent Lidar-Camera Deep Feature Fusion
- Test-time Adaptation vs. Training-time Generalization: A Case Study in Human Instance Segmentation using Keypoints Estimation
- Synthetic Image Data for Deep Learning
- Reinforced Approximate Exploratory Data Analysis
- Comparison Of Deep Object Detectors On A New Vulnerable Pedestrian Dataset
- Quantum Phase Recognition using Quantum Tensor Networks
- Contextual Explainable Video Representation: Human Perception-based Understanding
- Doubly Right Object Recognition: A Why Prompt for Visual Rationales
- Breaking the "Object" in Video Object Segmentation
- ROAD: Learning an Implicit Recursive Octree Auto-Decoder to Efficiently Encode 3D Shapes
- Zero-Shot Motor Health Monitoring by Blind Domain Transition
- An adaptive human-in-the-loop approach to emission detection of Additive Manufacturing processes and active learning with computer vision
- Accelerating Dataset Distillation via Model Augmentation
- Utilizing Mutations to Evaluate Interpretability of Neural Networks on Genomic Data
- CLIP Itself is a Strong Fine-tuner: Achieving 85.7% and 88.0% Top-1 Accuracy with ViT-B and ViT-L on ImageNet
- NMS Strikes Back
- Nearly Minimax Optimal Reinforcement Learning for Linear Markov Decision Processes
- Siamese Neural Networks for Skin Cancer Classification and New Class Detection using Clinical and Dermoscopic Image Datasets
- Neural Assets: Volumetric Object Capture and Rendering for Interactive Environments
- In Defense of Cross-Encoders for Zero-Shot Retrieval
- Where To Start? Transferring Simple Skills to Complex Environments
- Resolving Semantic Confusions for Improved Zero-Shot Detection
- Implicit Convolutional Kernels for Steerable CNNs
- Prompting Is Programming: A Query Language for Large Language Models
- Hand-breathe: Non-Contact Monitoring of Breathing Abnormalities from Hand Palm
- Hardware-efficient learning of quantum many-body states
- Fast Learning of Multidimensional Hawkes Processes via Frank-Wolfe
- Robust Perception through Equivariance
- Regression with Label Differential Privacy
- VOQL: Towards Optimal Regret in Model-free RL with Nonlinear Function Approximation
- Solving the Wide-band Inverse Scattering Problem via Equivariant Neural Networks
- HACA3: A Unified Approach for Multi-site MR Image Harmonization
- PERFEX: Classifier Performance Explanations for Trustworthy AI Systems
- Opponent Modeling in Multiplayer Imperfect-Information Games
- Video Prediction by Efficient Transformers
- Reconstructing Humpty Dumpty: Multi-feature Graph Autoencoder for Open Set Action Recognition
- A novel feature-scrambling approach reveals the capacity of convolutional neural networks to learn spatial relations
- A Neural ODE Interpretation of Transformer Layers
- An Approach for Improving Automatic Mouth Emotion Recognition
- Who Evaluates the Evaluators? On Automatic Metrics for Assessing AI-based Offensive Code Generators
- Effective Seed-Guided Topic Discovery by Integrating Multiple Types of Contexts
- Reinforcement Learning and Tree Search Methods for the Unit Commitment Problem
- Dirichlet-Survival Process: Scalable Inference of Topic-Dependent Diffusion Networks
- Multivariate Powered Dirichlet Hawkes Process
- Graph algorithms for predicting subcellular localization at the pathway level
- On Computing Probabilistic Abductive Explanations
- MegaCRN: Meta-Graph Convolutional Recurrent Network for Spatio-Temporal Modeling
- Selective classification using a robust meta-learning approach
- Real-World Compositional Generalization with Disentangled Sequence-to-Sequence Learning
- DexBERT: Effective, Task-Agnostic and Fine-grained Representation Learning of Android Bytecode
- Federated Few-Shot Learning for Mobile NLP
- RPN: A Word Vector Level Data Augmentation Algorithm in Deep Learning for Language Understanding
- Corruption-Robust Algorithms with Uncertainty Weighting for Nonlinear Contextual Bandits and Markov Decision Processes
- Evaluation and Improvement of Interpretability for Self-Explainable Part-Prototype Networks
- SRoUDA: Meta Self-training for Robust Unsupervised Domain Adaptation
- NFResNet: Multi-scale and U-shaped Networks for Deblurring
- Instance-Conditional Timescales of Decay for Non-Stationary Learning
- Parameter-Efficient Finetuning of Transformers for Source Code
- Deep learning-based Subtyping of Atypical and Normal Mitoses using a Hierarchical Anchor-Free Object Detector
- MultiAct: Long-Term 3D Human Motion Generation from Multiple Action Labels
- Text Mining-Based Patent Analysis for Automated Rule Checking in AEC
- ALSO: Automotive Lidar Self-supervision by Occupancy estimation
All 166
- Measuring the Driving Forces of Predictive Performance: Application to Credit Scoring
- Joint Counting, Detection and Re-Identification for Multi-Object Tracking
- Automated ICD Coding using Extreme Multi-label Long Text Transformer-based Models
- "I think this is the most disruptive technology": Exploring Sentiments of ChatGPT Early Adopters using Twitter Data
- BeautyREC: Robust, Efficient, and Content-preserving Makeup Transfer
- DeepCut: Unsupervised Segmentation using Graph Neural Networks Clustering
- CbwLoss: Constrained Bidirectional Weighted Loss for Self-supervised Learning of Depth and Pose
- Optimizing ship detection efficiency in SAR images
- Acceptance Rates of Invertible Neural Networks on Electron Spectra from Near-Critical Laser-Plasmas: A Comparison
- P-Transformer: Towards Better Document-to-Document Neural Machine Translation
- Carpet-bombing patch: attacking a deep network without usual requirements
- Lower Bounds for the Total Variation Distance Given Means and Variances of Distributions
- GWRBoost:A geographically weighted gradient boosting method for explainable quantification of spatially-varying relationships
- KonX: Cross-Resolution Image Quality Assessment
- Transfer Learning using Spectral Convolutional Autoencoders on Semi-Regular Surface Meshes
- Z-SSMNet: Zonal-aware Self-supervised Mesh Network for Prostate Cancer Detection and Diagnosis with Bi-parametric MRI
- Direct Speech-to-speech Translation without Textual Annotation using Bottleneck Features
- BigText-QA: Question Answering over a Large-Scale Hybrid Knowledge Graph
- Generalizing DP-SGD with Shuffling and Batch Clipping
- CTT-Net: A Multi-view Cross-token Transformer for Cataract Postoperative Visual Acuity Prediction
- Collaborating Heterogeneous Natural Language Processing Tasks via Federated Learning
- Markerless Body Motion Capturing for 3D Character Animation based on Multi-view Cameras
- Multi-scale Feature Imitation for Unsupervised Anomaly Localization
- GT-CausIn: a novel causal-based insight for traffic prediction
- Robust Recurrent Neural Network to Identify Ship Motion in Open Water with Performance Guarantees -- Technical Report
- Instrumental Variables in Causal Inference and Machine Learning: A Survey
- A Survey on Natural Language Processing for Programming
- Multi-Dimensional Self Attention based Approach for Remaining Useful Life Estimation
- A Survey of Knowledge Graph Reasoning on Graph Types: Static, Dynamic, and Multimodal
- Interactive introduction to self-calibrating interfaces
- Information-Theoretic Text Hallucination Reduction for Video-grounded Dialogue
- Domain Adaptation of Transformer-Based Models using Unlabeled Data for Relevance and Polarity Classification of German Customer Feedback
- Momentum Contrastive Pre-training for Question Answering
- BEV-MAE: Bird's Eye View Masked Autoencoders for Point Cloud Pre-training in Autonomous Driving Scenarios
- Scale-Semantic Joint Decoupling Network for Image-text Retrieval in Remote Sensing
- On Pre-Training for Visuo-Motor Control: Revisiting a Learning-from-Scratch Baseline
- Where to go: Agent Guidance with Deep Reinforcement Learning in A City-Scale Online Ride-Hailing Service
- Searching for Effective Multilingual Fine-Tuning Methods: A Case Study in Summarization
- Adaptive Low-Precision Training for Embeddings in Click-Through Rate Prediction
- ROIFormer: Semantic-Aware Region of Interest Transformer for Efficient Self-Supervised Monocular Depth Estimation
- Evaluating Model-free Reinforcement Learning toward Safety-critical Tasks
- T5Score: Discriminative Fine-tuning of Generative Evaluation Metrics
- HDNet: A Hierarchically Decoupled Network for Crowd Counting
- Tensor-based Sequential Learning via Hankel Matrix Representation for Next Item Recommendations
- Tensor Factorization via Transformed Tensor-Tensor Product for Image Alignment
- Feature Calibration Network for Occluded Pedestrian Detection
- On Generalization and Regularization via Wasserstein Distributionally Robust Optimization
- A Roadmap to Domain Knowledge Integration in Machine Learning
- HOTCOLD Block: Fooling Thermal Infrared Detectors with a Novel Wearable Design
- Human Mobility Modeling During the COVID-19 Pandemic via Deep Graph Diffusion Infomax
- Detection Selection Algorithm: A Likelihood based Optimization Method to Perform Post Processing for Object Detection
- Implementing Deep Learning-Based Approaches for Article Summarization in Indian Languages
- Revisiting the acceleration phenomenon via high-resolution differential equations
- MoDem: Accelerating Visual Model-Based Reinforcement Learning with Demonstrations
- Ensembling Transformers for Cross-domain Automatic Term Extraction
- CircleNet: Reciprocating Feature Adaptation for Robust Pedestrian Detection
- REAP: A Large-Scale Realistic Adversarial Patch Benchmark
- Evolutionary Multitasking with Solution Space Cutting for Point Cloud Registration
- Masked autoencoders are effective solution to transformer data-hungry
- Hybrid Censored Quantile Regression Forest to Assess the Heterogeneous Effects
- Development of Personalized Sleep Induction System based on Mental States
- Fighting Malicious Media Data: A Survey on Tampering Detection and Deepfake Detection
- On an Interpretation of ResNets via Solution Constructions
- Optimal Planning of Hybrid Energy Storage Systems using Curtailed Renewable Energy through Deep Reinforcement Learning
- Spatial-temporal traffic modeling with a fusion graph reconstructed by tensor decomposition
- Cross-Modal Learning with 3D Deformable Attention for Action Recognition