Papers
Tue 21 Jun 2022
192 papers
- (Certified!!) Adversarial Robustness for Free!Diffusion models → Robustness, privacy and adversarial aspects
- PlanBench: An Extensible Benchmark for Evaluating Large Language Models on Planning and Reasoning about ChangeLLM reasoning → Reasoning for agents, planning and code
- Robust Task Representations for Offline Meta-Reinforcement Learning via Contrastive LearningOffline RL and imitation learning from data → Decision transformers and sequence modeling
- Imitation Learning for Nonprehensile Manipulation through Self-Supervised Learning Considering Motion SpeedOffline RL and imitation learning from data → Robot manipulation imitation learning
- Incorporating Voice Instructions in Model-Based Reinforcement Learning for Self-Driving CarsEnd-to-end autonomous driving → Reinforcement learning for driving
- Model-Based Imitation Learning Using Entropy Regularization of Model and PolicyOffline RL and imitation learning from data → Imitation learning methods
- Tell Me the Evidence? Dual Visual-Linguistic Interaction for Answer Grounding
- On the Intrinsic Structures of Spiking Neural Networks
- Online Trajectory Prediction for Metropolitan Scale Mobility Digital Twin
- Transferable Graph Backdoor Attack
- Using cognitive psychology to understand GPT-3
- Why Robust Natural Language Understanding is a Challenge
- Knowledge Graph Fusion for Language Model Fine-tuning
- An Efficient Industrial Federated Learning Framework for AIoT: A Face Recognition Application
- Generative Modelling With Inverse Heat Dissipation
- A Simple Approach for Visual Rearrangement: 3D Mapping and Semantic Search
- On the Limitations of Elo: Real-World Games, are Transitive, not Additive
- f-divergences and their applications in lossy compression and bounding generalization error
- Deep Reinforcement Learning for Turbulence Modeling in Large Eddy Simulations
- World of Bugs: A Platform for Automated Bug Detection in 3D Video Games
- On the Statistical Efficiency of Reward-Free Exploration in Non-Linear RL
- A method for ethical AI in Defence: A case study on developing trustworthy autonomous systems
- Floor Map Reconstruction Through Radio Sensing and Learning By a Large Intelligent Surface
- BiometricBlender: Ultra-high dimensional, multi-class synthetic data generator to imitate biometric feature space
- Derivative-Informed Neural Operator: An Efficient Framework for High-Dimensional Parametric Derivative Learning
- Don't Forget About Pronouns: Removing Gender Bias in Language Models Without Losing Factual Gender Information
- Quantum-Enhanced Selection Operators for Evolutionary Algorithms
- Deep Metric Color Embeddings for Splicing Localization in Severely Degraded Images
- Imitate then Transcend: Multi-Agent Optimal Execution with Dual-Window Denoise PPO
- Sharp Constants in Uniformity Testing via the Huber Statistic
- Predicting Team Performance with Spatial Temporal Graph Convolutional Networks
- Physics-informed machine learning with differentiable programming for heterogeneous underground reservoir pressure management
- Meta Reinforcement Learning with Finite Training Tasks -- a Density Estimation Approach
- Beyond Uniform Lipschitz Condition in Differentially Private Optimization
- Panoramic Panoptic Segmentation: Insights Into Surrounding Parsing for Mobile Agents via Unsupervised Contrastive Learning
- TraSE: Towards Tackling Authorial Style from a Cognitive Science Perspective
- Multi-Omic Data Integration and Feature Selection for Survival-based Patient Stratification via Supervised Concrete Autoencoders
- TiCo: Transformation Invariance and Covariance Contrast for Self-Supervised Visual Representation Learning
- Performance Prediction Under Dataset Shift
- Epicasting: An Ensemble Wavelet Neural Network (EWNet) for Forecasting Epidemics
- Making the case for audience design in conversational AI: Rapport expectations and language ideologies in a task-oriented chatbot
- A consistent and flexible framework for deep matrix factorizations
- Multi-level Domain Adaptation for Lane Detection
- Towards OOD Detection in Graph Classification from Uncertainty Estimation Perspective
- Learning Continuous Rotation Canonicalization with Radial Beam Sampling
- Differentially Private Maximal Information Coefficients
- Learning Neuro-Symbolic Skills for Bilevel Planning
- ConTraNet: A single end-to-end hybrid network for EEG-based and EMG-based human machine interfaces
- Natural Backdoor Datasets
- SCIM: Simultaneous Clustering, Inference, and Mapping for Open-World Semantic Scene Understanding
- BenchCLAMP: A Benchmark for Evaluating Language Models on Syntactic and Semantic Parsing
- BOSS: A Benchmark for Human Belief Prediction in Object-context Scenarios
- Questions Are All You Need to Train a Dense Passage Retriever
- On the Maximum Hessian Eigenvalue and Generalization
- Sparse Kernel Gaussian Processes through Iterative Charted Refinement (ICR)
- CoCoPIE XGen: A Full-Stack AI-Oriented Optimizing Framework
- Asymmetric Learned Image Compression with Multi-Scale Residual Block, Importance Map, and Post-Quantization Filtering
- Temporally Consistent Semantic Video Editing
- EdgeNeXt: Efficiently Amalgamated CNN-Transformer Architecture for Mobile Vision Applications
- Robust SDE-Based Variational Formulations for Solving Linear PDEs via Deep Learning
- Guiding Visual Attention in Deep Convolutional Neural Networks Based on Human Eye Movements
- D-CIPHER: Discovery of Closed-form Partial Differential Equations
- Nimble GNN Embedding with Tensor-Train Decomposition
- Gradient-Enhanced Physics-Informed Neural Networks for Power Systems Operational Support
- Solving Constrained Variational Inequalities via a First-order Interior Point-based Method
- H&E-based Computational Biomarker Enables Universal EGFR Screening for Lung Adenocarcinoma
- Toward Unpaired Multi-modal Medical Image Segmentation via Learning Structured Semantic Consistency
- Controllability of Coarsely Measured Networked Linear Dynamical Systems (Extended Version)
- Ensembling over Classifiers: a Bias-Variance Perspective
- sqSGD: Locally Private and Communication Efficient Federated Learning
- Semantics-Depth-Symbiosis: Deeply Coupled Semi-Supervised Learning of Semantics and Depth
- Low Resource Pipeline for Spoken Language Understanding via Weak Supervision
- EnvPool: A Highly Parallel Reinforcement Learning Environment Execution Engine
- LargeKernel3D: Scaling up Kernels in 3D Sparse CNNs
- Uncertainty Quantification for Competency Assessment of Autonomous Agents
- Vicinity Vision Transformer
- On the effectiveness of persistent homology
- FedHiSyn: A Hierarchical Synchronous Federated Learning Framework for Resource and Data Heterogeneity
- Multi-UAV Planning for Cooperative Wildfire Coverage and Tracking with Quality-of-Service Guarantees
- Faster Diffusion Cardiac MRI with Deep Learning-based breath hold reduction
- Rethinking Symbolic Regression Datasets and Benchmarks for Scientific Discovery
- HealNet -- Self-Supervised Acute Wound Heal-Stage Classification
- EpiGRAF: Rethinking training of 3D GANs
- Neural Transformers for Intraductal Papillary Mucosal Neoplasms (IPMN) Classification in MRI images
- QuantFace: Towards Lightweight Face Recognition by Synthetic Data Low-bit Quantization
- Lyapunov Density Models: Constraining Distribution Shift in Learning-Based Control
- SFace: Privacy-friendly and Accurate Face Recognition using Synthetic Data
- Bi-Calibration Networks for Weakly-Supervised Video Representation Learning
- Learning to Estimate and Refine Fluid Motion with Physical Dynamics
- Policy Learning with Asymmetric Counterfactual Utilities
- Survival Kernets: Scalable and Interpretable Deep Kernel Survival Analysis with an Accuracy Guarantee
- Twitter conversations predict the daily confirmed COVID-19 cases
- The Privacy Onion Effect: Memorization is Relative
- An Overview of Privacy-enhancing Technologies in Biometric Recognition
- The Digital Twin Landscape at the Crossroads of Predictive Maintenance, Machine Learning and Physics Based Modeling
- An Automatic and Efficient BERT Pruning for Edge AI Systems
- Domain Adaptive 3D Pose Augmentation for In-the-wild Human Mesh Recovery
- Shifted Compression Framework: Generalizations and Improvements
- Winning the Lottery Ahead of Time: Efficient Early Network Pruning
- Transformer-Based Multi-modal Proposal and Re-Rank for Wikipedia Image-Caption Matching
All 192
- Graphical Join: A New Physical Join Algorithm for RDBMSs
- Model Joins: Enabling Analytics Over Joins of Absent Big Tables
- Plug and Play Counterfactual Text Generation for Model Robustness
- Rethinking Audio-visual Synchronization for Active Speaker Detection
- Route to Time and Time to Route: Travel Time Estimation from Sparse Trajectories
- A Single-Timescale Analysis For Stochastic Approximation With Multiple Coupled Sequences
- WrapperFL: A Model Agnostic Plug-in for Industrial Federated Learning
- Using EBGAN for Anomaly Intrusion Detection
- Neural Moving Horizon Estimation for Robust Flight Control
- TabText: Language-Based Representations of Tabular Health Data for Predictive Modelling
- An Energy and Carbon Footprint Analysis of Distributed and Federated Learning
- MEStereo-Du2CNN: A Novel Dual Channel CNN for Learning Robust Depth Estimates from Multi-exposure Stereo Images for HDR 3D Applications
- Enhancing Multi-view Stereo with Contrastive Matching and Weighted Focal Loss
- Supervised learning of random quantum circuits via scalable neural networks
- Building an Endangered Language Resource in the Classroom: Universal Dependencies for Kakataibo
- Machine Learning Prescriptive Canvas for Optimizing Business Outcomes
- SVG Vector Font Generation for Chinese Characters with Transformer
- Online progressive instance-balanced sampling for weakly supervised object detection
- What Makes Forest-Based Heterogeneous Treatment Effect Estimators Work?
- Marginal Tail-Adaptive Normalizing Flows
- Dynamic Reserve Price Design with Distributed Solving Algorithm
- Using the Polar Transform for Efficient Deep Learning-Based Aorta Segmentation in CTA Images
- Algorithmic Gaussianization through Sketching: Converting Data into Sub-gaussian Random Designs
- Position-prior Clustering-based Self-attention Module for Knee Cartilage Segmentation
- muBoost: An Effective Method for Solving Indic Multilingual Text Classification Problem
- Attention-driven Next-best-view Planning for Efficient Reconstruction of Plants and Targeted Plant Parts
- KnowDA: All-in-One Knowledge Mixture Model for Data Augmentation in Low-Resource NLP
- Object Structural Points Representation for Graph-based Semantic Monocular Localization and Mapping
- Interpretable Deep Causal Learning for Moderation Effects
- R2-AD2: Detecting Anomalies by Analysing the Raw Gradient
- GNN-PMB: A Simple but Effective Online 3D Multi-Object Tracker without Bells and Whistles
- Towards Optimizing OCR for Accessibility
- Document Navigability: A Need for Print-Impaired
- Experimental Evaluation of Pose Initialization Methods for Relative Navigation Between Non-Cooperative Satellites
- Deep Active Latent Surfaces for Medical Geometries
- Riemannian data-dependent randomized smoothing for neural networks certification
- TAPHSIR: Towards AnaPHoric Ambiguity Detection and ReSolution In Requirements
- Broken News: Making Newspapers Accessible to Print-Impaired
- Rethinking Unsupervised Neural Superpixel Segmentation
- The Integration of Machine Learning into Automated Test Generation: A Systematic Mapping Study
- SemMAE: Semantic-Guided Masking for Learning Masked Autoencoders
- Personalized Subgraph Federated Learning
- Enabling Capsule Networks at the Edge through Approximate Softmax and Squash Operations
- LDD: A Dataset for Grape Diseases Object Detection and Instance Segmentation
- A General Theory for Federated Optimization with Asynchronous and Heterogeneous Clients Updates
- Analysis of Self-Supervised Learning and Dimensionality Reduction Methods in Clustering-Based Active Learning for Speech Emotion Recognition
- Improving Localization for Semi-Supervised Object Detection
- Federated Stochastic Approximation under Markov Noise and Heterogeneity: Applications in Reinforcement Learning
- covEcho Resource constrained lung ultrasound image analysis tool for faster triaging and active learning
- Large region targets observation scheduling by multiple satellites using resampling particle swarm optimization
- TCJA-SNN: Temporal-Channel Joint Attention for Spiking Neural Networks
- Efficient Inference of Spatially-varying Gaussian Markov Random Fields with Applications in Gene Regulatory Networks
- Predicting Parking Lot Availability by Graph-to-Sequence Model: A Case Study with SmartSantander
- Certifiably Robust Policy Learning against Adversarial Communication in Multi-agent Systems
- Probing Visual-Audio Representation for Video Highlight Detection via Hard-Pairs Guided Contrastive Learning
- Review Neural Networks about Image Transformation Based on IGC Learning Framework with Annotated Information
- Diffractive Interconnects: All-Optical Permutation Operation Using Diffractive Networks
- KE-RCNN: Unifying Knowledge based Reasoning into Part-level Attribute Parsing
- Deep Learning Eliminates Massive Dust Storms from Images of Tianwen-1
- Open-Source Framework for Encrypted Internet and Malicious Traffic Classification
- Noise-contrastive Online Change Point Detection
- Propagation with Adaptive Mask then Training for Node Classification on Attributed Networks
- Comprehensive Analysis of Negative Sampling in Knowledge Graph Representation Learning
- Insights into Pre-training via Simpler Synthetic Tasks
- Few-Max: Few-Shot Domain Adaptation for Unsupervised Contrastive Representation Learning
- An Integrated Representation & Compression Scheme Based on Convolutional Autoencoders with 4D DCT Perceptual Encoding for High Dynamic Range Light Fields
- Automatic Concept Extraction for Concept Bottleneck-based Video Classification
- Bridging the Gap Between Indexing and Retrieval for Differentiable Search Index with Query Generation
- Supervision-Guided Codebooks for Masked Prediction in Speech Pre-training
- Safe and Psychologically Pleasant Traffic Signal Control with Reinforcement Learning using Action Masking
- Finite Expression Method for Solving High-Dimensional Partial Differential Equations
- HOPE: Hierarchical Spatial-temporal Network for Occupancy Flow Prediction
- General Framework for Reversible Data Hiding in Texts Based on Masked Language Modeling
- Sensitivity of Average Precision to Bounding Box Perturbations
- Automatic Controllable Product Copywriting for E-Commerce
- Reconstruct from BEV: A 3D Lane Detection Approach based on Geometry Structure Prior
- Transformers Improve Breast Cancer Diagnosis from Unregistered Multi-View Mammograms
- Pyramid Region-based Slot Attention Network for Temporal Action Proposal Generation
- DeePKS+ABACUS as a Bridge between Expensive Quantum Mechanical Models and Machine Learning Potentials
- BEVDepth: Acquisition of Reliable Depth for Multi-view 3D Object Detection
- KTN: Knowledge Transfer Network for Learning Multi-person 2D-3D Correspondences
- Renormalized Sparse Neural Network Pruning
- Optimally Controllable Perceptual Lossy Compression
- One-stage Action Detection Transformer
- The Manifold Scattering Transform for High-Dimensional Point Cloud Data
- Counting Varying Density Crowds Through Density Guided Adaptive Selection CNN and Transformer Estimation
- Finding Optimal Policy for Queueing Models: New Parameterization
- BOND: Benchmarking Unsupervised Outlier Node Detection on Static Attributed Graphs
- RendNet: Unified 2D/3D Recognizer With Latent Space Rendering
- Early Recall, Late Precision: Multi-Robot Semantic Object Mapping under Operational Constraints in Perceptually-Degraded Environments
- Bypass Network for Semantics Driven Image Paragraph Captioning
- Robust Deep Reinforcement Learning through Bootstrapped Opportunistic Curriculum