Papers
Thu 26 May 2022
212 papers
- Protein Structure and Sequence Generation with Equivariant Denoising Diffusion Probabilistic ModelsDiffusion models → Flow matching, time series and science
- Membership Inference Attack Using Self Influence FunctionsLLM safety and security → Membership inference attacks
- Quark: Controllable Text Generation with Reinforced UnlearningLLM safety and security → Machine unlearning
- BagFlip: A Certified Defense against Data PoisoningLLM safety and security → Backdoor and data poisoning attacks
- Pessimism in the Face of Confounders: Provably Efficient Offline Reinforcement Learning in Partially Observable Markov Decision ProcessesOffline RL and imitation learning from data → Offline RL algorithms
- Revisiting Generative Commonsense Reasoning: A Pre-Ordering ApproachLLM reasoning → Reasoning benchmarks and evaluation
- On Collective Robustness of Bagging Against Data PoisoningLLM safety and security → Backdoor and data poisoning attacks
- Roadmap to Autonomous Surgery -- A Framework to Surgical Autonomy
- Flexible Group Fairness Metrics for Survival Analysis
- The impact of spatio-temporal travel distance on epidemics using an interpretable attention-based sequence-to-sequence model
- Efficient textual explanations for complex road and traffic scenarios based on semantic segmentation
- Sequential Nature of Recommender Systems Disrupts the Evaluation Process
- SeedGNN: Graph Neural Networks for Supervised Seeded Graph Matching
- Forward variable selection enables fast and accurate dynamic system identification with Karhunen-Lo`eve decomposed Gaussian processes
- Reinforcement Learning Approach for Mapping Applications to Dataflow-Based Coarse-Grained Reconfigurable Array
- Global Normalization for Streaming Speech Recognition in a Modular Framework
- Transformer for Partial Differential Equations' Operator Learning
- Explaining Preferences with Shapley Values
- Contextual Adapters for Personalized Speech Recognition in Neural Transducers
- Mixed Federated Learning: Joint Decentralized and Centralized Learning
- A Unified Analysis of Federated Learning with Arbitrary Client Participation
- Learning to Reason with Neural Networks: Generalization, Unseen Data and Boolean Measures
- Machine and Deep Learning Applications to Mouse Dynamics for Continuous User Authentication
- Spatio-temporally separable non-linear latent factor learning: an application to somatomotor cortex fMRI data
- A Model Predictive Control Functional Continuous Time Bayesian Network for Self-Management of Multiple Chronic Conditions
- RIGID: Robust Linear Regression with Missing Data
- Deep Sensor Fusion with Pyramid Fusion Networks for 3D Semantic Segmentation
- Experimental Design for Linear Functionals in Reproducing Kernel Hilbert Spaces
- Faster Optimization on Sparse Graphs via Neural Reparametrization
- Hybrid Neural Autoencoders for Stimulus Encoding in Visual and Other Sensory Neuroprostheses
- Differentially Private Decoding in Large Language Models
- Fairness in Recommendation: Foundations, Methods and Applications
- Phantom Sponges: Exploiting Non-Maximum Suppression to Attack Deep Object Detectors
- Does DQN Learn?
- Towards A Proactive ML Approach for Detecting Backdoor Poison Samples
- Emergent organization of receptive fields in networks of excitatory and inhibitory neurons
- Circumventing Backdoor Defenses That Are Based on Latent Separability
- Topological Hidden Markov Models
- Self-supervised Pretraining and Transfer Learning Enable Flu and COVID-19 Predictions in Small Mobile Sensing Datasets
- Tensor Program Optimization with Probabilistic Programs
- Consistent and fast inference in compartmental models of epidemics using Poisson Approximate Likelihoods
- MyoSuite -- A contact-rich simulation suite for musculoskeletal motor control
- VectorAdam for Rotation Equivariant Geometry Optimization
- DRLComplex: Reconstruction of protein quaternary structures using deep reinforcement learning
- Evolution of beliefs in social networks
- Comparing the Digital Annealer with Classical Evolutionary Algorithm
- Learning in Feedback-driven Recurrent Spiking Neural Networks using full-FORCE Training
- Harnessing Artificial Intelligence to Infer Novel Spatial Biomarkers for the Diagnosis of Eosinophilic Esophagitis
- CA-UDA: Class-Aware Unsupervised Domain Adaptation with Optimal Assignment and Pseudo-Label Refinement
- Dynamic Network Reconfiguration for Entropy Maximization using Deep Reinforcement Learning
- Understanding new tasks through the lens of training data via exponential tilting
- Predictor-corrector algorithms for stochastic optimization under gradual distribution shift
- Pruning has a disparate impact on model accuracy
- Efficient Approximation of Gromov-Wasserstein Distance Using Importance Sparsification
- Clinical Dialogue Transcription Error Correction using Seq2Seq Models
- Low-rank lottery tickets: finding efficient low-rank neural networks via matrix differential equations
- Learning Dialogue Representations from Consecutive Utterances
- Exploration, Exploitation, and Engagement in Multi-Armed Bandits with Abandonment
- Unequal Covariance Awareness for Fisher Discriminant Analysis and Its Variants in Classification
- Physics-Guided Hierarchical Reward Mechanism for Learning-Based Robotic Grasping
- Training and Inference on Any-Order Autoregressive Models the Right Way
- Learning black- and gray-box chemotactic PDEs/closures from agent based Monte Carlo simulation data
- Revealing the Dark Secrets of Masked Image Modeling
- BEVFusion: Multi-Task Multi-Sensor Fusion with Unified Bird's-Eye View Representation
- Mitigating barren plateaus of variational quantum eigensolvers
- Verifying Learning-Based Robotic Navigation Systems
- AdaptFormer: Adapting Vision Transformers for Scalable Visual Recognition
- Selective Prediction via Training Dynamics
- Learning ReLU networks to high uniform accuracy is intractable
- Semantic Parsing of Interpage Relations
- SFP: State-free Priors for Exploration in Off-Policy Reinforcement Learning
- Subspace clustering in high-dimensions: Phase transitions & Statistical-to-Computational gap
- On the Inconsistency of Kernel Ridgeless Regression in Fixed Dimensions
- PREF: Phasorial Embedding Fields for Compact Neural Representations
- Discovering Policies with DOMiNO: Diversity Optimization Maintaining Near Optimality
- Transfer learning driven design optimization for inertial confinement fusion
- Green Hierarchical Vision Transformer for Masked Image Modeling
- Pick up the PACE: Fast and Simple Domain Adaptation via Ensemble Pseudo-Labeling
- A Framework for Overparameterized Learning
- Are Transformers Effective for Time Series Forecasting?
- An Analytic Framework for Robust Training of Artificial Neural Networks
- Factor selection in screening experiments by aggregation over random models
- Censored Quantile Regression Neural Networks for Distribution-Free Survival Analysis
- Mesoscopic modeling of hidden spiking neurons
- Sparse Graph Learning from Spatiotemporal Time Series
- SemAffiNet: Semantic-Affine Transformation for Point Cloud Segmentation
- Measuring Perceptual Color Differences of Smartphone Photographs
- DeepJoint: Robust Survival Modelling Under Clinical Presence Shift
- Learning to Reconstruct Missing Data from Spatiotemporal Graphs with Sparse Observations
- Embed to Control Partially Observed Systems: Representation Learning with Provable Sample Efficiency
- 2D versus 3D Convolutional Spiking Neural Networks Trained with Unsupervised STDP for Human Action Recognition
- Characterising Research Areas in the field of AI
- FedBR: Improving Federated Learning on Heterogeneous Data via Local Learning Bias Reduction
- SigMaNet: One Laplacian to Rule Them All
- AutoTSG: Learning and Synthesis for Incident Troubleshooting
- Continual evaluation for lifelong learning: Identifying the stability gap
- Follow-the-Perturbed-Leader for Adversarial Markov Decision Processes with Bandit Feedback
- Variance-Aware Sparse Linear Bandits
- Multi-Phase Multi-Objective Dexterous Manipulation with Adaptive Hierarchical Curriculum
- Jointly Learning Span Extraction and Sequence Labeling for Information Extraction from Business Documents
All 212
- Do we really need temporal convolutions in action segmentation?
- Opinion Spam Detection: A New Approach Using Machine Learning and Network-Based Algorithms
- Bias in Machine Learning Models Can Be Significantly Mitigated by Careful Training: Evidence from Neuroimaging Studies
- Avoiding Barren Plateaus with Classical Deep Neural Networks
- A Fair Federated Learning Framework With Reinforcement Learning
- Physical-World Optical Adversarial Attacks on 3D Face Recognition
- Your Transformer May Not be as Powerful as You Expect
- Multi-objective QUBO Solver: Bi-objective Quadratic Assignment
- Looking for Out-of-Distribution Environments in Multi-center Critical Care Data
- Continual Learning for Visual Search with Backward Consistent Feature Embedding
- BppAttack: Stealthy and Efficient Trojan Attacks against Deep Neural Networks via Image Quantization and Contrastive Adversarial Learning
- Classification ensembles for multivariate functional data with application to mouse movements in web surveys
- Prismal view of ethics
- One-Shot Face Reenactment on Megapixels
- Multi-fidelity power flow solver
- Feature Forgetting in Continual Representation Learning
- Transfer and Share: Semi-Supervised Learning from Long-Tailed Data
- The Document Vectors Using Cosine Similarity Revisited
- Learning What and Where: Disentangling Location and Identity Tracking Without Supervision
- Keywords and Instances: A Hierarchical Contrastive Learning Framework Unifying Hybrid Granularities for Text Generation
- Leveraging Causal Inference for Explainable Automatic Program Repair
- QUIC-FL: Quick Unbiased Compression for Federated Learning
- Deep Active Learning with Noise Stability
- Target-aware Abstractive Related Work Generation with Contrastive Learning
- TransBoost: Improving the Best ImageNet Performance using Deep Transduction
- How Powerful are K-hop Message Passing Graph Neural Networks
- SHREC 2022: pothole and crack detection in the road pavement using images and RGB-D data
- Learning the spatio-temporal relationship between wind and significant wave height using deep learning
- The Effect of Task Ordering in Continual Learning
- Towards Learning Universal Hyperparameter Optimizers with Transformers
- Fair Representation Learning through Implicit Path Alignment
- Cross-Architecture Self-supervised Video Representation Learning
- SARS-CoV-2 Result Interpretation based on Image Analysis of Lateral Flow Devices
- Gaussian Universality of Perceptrons with Random Labels
- Federated Non-negative Matrix Factorization for Short Texts Topic Modeling with Mutual Information
- Federated Split BERT for Heterogeneous Text Classification
- DeepTechnome: Mitigating Unknown Bias in Deep Learning Based Assessment of CT Images
- Social Interpretable Tree for Pedestrian Trajectory Prediction
- Analytical Interpretation of Latent Codes in InfoGAN with SAR Images
- Embedding Principle in Depth for the Loss Landscape Analysis of Deep Neural Networks
- On the Eigenvalues of Global Covariance Pooling for Fine-grained Visual Recognition
- Surround-view Fisheye Camera Perception for Automated Driving: Overview, Survey and Challenges
- Objects Matter: Learning Object Relation Graph for Robust Camera Relocalization
- Triangular Contrastive Learning on Molecular Graphs
- Semantic Segmentation for Thermal Images: A Comparative Survey
- VIDI: A Video Dataset of Incidents
- Evaluating Multimodal Interactive Agents
- Acute Lymphoblastic Leukemia Detection Using Hypercomplex-Valued Convolutional Neural Networks
- FCN-Pose: A Pruned and Quantized CNN for Robot Pose Estimation for Constrained Devices
- Unsupervised Multi-object Segmentation Using Attention and Soft-argmax
- MemeTector: Enforcing deep focus for meme detection
- Task-Customized Self-Supervised Pre-training with Scalable Dynamic Routing
- Privacy-Preserving Wavelet Neural Network with Fully Homomorphic Encryption
- Active Labeling: Streaming Stochastic Gradients
- MALICE: Manipulation Attacks on Learned Image ComprEssion
- DT-SV: A Transformer-based Time-domain Approach for Speaker Verification
- Constrained Reinforcement Learning for Short Video Recommendation
- DT+GNN: A Fully Explainable Graph Neural Network using Decision Trees
- Symbiotic Child Emotional Support with Social Robots and Temporal Knowledge Graphs
- Censor-aware Semi-supervised Learning for Survival Time Prediction from Medical Images
- DevFormer: A Symmetric Transformer for Context-Aware Device Placement
- Combating Client Dropout in Federated Learning via Friend Model Substitution
- QSpeech: Low-Qubit Quantum Speech Application Toolkit
- DGSVis: Visual Analysis of Hierarchical Snapshots in Dynamic Graph
- Penalizing Proposals using Classifiers for Semi-Supervised Object Detection
- A Model or 603 Exemplars: Towards Memory-Efficient Class-Incremental Learning
- Encoded Gradients Aggregation against Gradient Leakage in Federated Learning
- SymNMF-Net for The Symmetric NMF Problem
- Fast Vision Transformers with HiLo Attention
- Sym-NCO: Leveraging Symmetricity for Neural Combinatorial Optimization
- O(N2) Universal Antisymmetry in Fermionic Neural Networks
- More Recent Advances in (Hyper)Graph Partitioning
- Decoupled Pyramid Correlation Network for Liver Tumor Segmentation from CT images
- Tree Reconstruction using Topology Optimisation
- Orthogonal Stochastic Configuration Networks with Adaptive Construction Parameter for Data Analytics
- Other Roles Matter! Enhancing Role-Oriented Dialogue Summarization via Role Interactions
- AI for Porosity and Permeability Prediction from Geologic Core X-Ray Micro-Tomography
- Analyzing the Latent Space of GAN through Local Dimension Estimation
- Distributed Contextual Linear Bandits with Minimax Optimal Communication Cost
- On Learning Mixture of Linear Regressions in the Non-Realizable Setting
- Light Field Raindrop Removal via 4D Re-sampling
- Leveraging Dependency Grammar for Fine-Grained Offensive Language Detection using Graph Convolutional Networks
- Cost-efficient Gaussian Tensor Network Embeddings for Tensor-structured Inputs
- HIRL: A General Framework for Hierarchical Image Representation Learning
- SwinVRNN: A Data-Driven Ensemble Forecasting Model via Learned Distribution Perturbation
- Transferable Adversarial Attack based on Integrated Gradients
- Grammar Detection for Sentiment Analysis through Improved Viterbi Algorithm
- Matryoshka Representation Learning
- Unsupervised Reinforcement Adaptation for Class-Imbalanced Text Classification
- MixMAE: Mixed and Masked Autoencoder for Efficient Pretraining of Hierarchical Vision Transformers
- Symbolic Physics Learner: Discovering governing equations via Monte Carlo tree search
- On the Evolution of A.I. and Machine Learning: Towards a Meta-level Measuring and Understanding Impact, Influence, and Leadership at Premier A.I. Conferences
- RACE: A Reinforcement Learning Framework for Improved Adaptive Control of NoC Channel Buffers
- Wireless Deep Video Semantic Transmission
- Prompt-based Learning for Unpaired Image Captioning
- PixelGame: Infrared small target segmentation as a Nash equilibrium
- To image, or not to image: Class-specific diffractive cameras with all-optical erasure of undesired objects
- Cali3F: Calibrated Fast Fair Federated Recommendation System
- Perceptual Learned Source-Channel Coding for High-Fidelity Image Semantic Transmission
- Understanding Metrics for Paraphrasing
- Learn to Cluster Faces via Pairwise Classification
- GraphPMU: Event Clustering via Graph Representation Learning Using Locationally-Scarce Distribution-Level Fundamental and Harmonic PMU Measurements
- Fine-grained Image Captioning with CLIP Reward
- Contextual Pandora's Box
- Learning to segment with limited annotations: Self-supervised pretraining with regression and contrastive loss in MRI
- Unsupervised Abstractive Dialogue Summarization with Word Graphs and POV Conversion
- Trainable Weight Averaging: Accelerating Training and Improving Generalization
- Deep-XFCT: Deep learning 3D-mineral liberation analysis with micro X-ray fluorescence and computed tomography
- Optimal Neural Network Approximation of Wasserstein Gradient Direction via Convex Optimization
- VizInspect Pro -- Automated Optical Inspection (AOI) solution
- Undersampling is a Minimax Optimal Robustness Intervention in Nonparametric Classification
- Dual-Perspective Semantic-Aware Representation Blending for Multi-Label Image Recognition with Partial Labels