Papers
Fri 11 Feb 2022
147 papers
- Learning Fast Samplers for Diffusion Models by Differentiating Through Sample QualityDiffusion models → Diffusion foundations and sampling
- End-to-end Algorithm Synthesis with Recurrent Networks: Logical Extrapolation Without OverthinkingLLM reasoning → Test-time compute and efficient thinking
- Constrained Optimization with Dynamic Bound-scaling for Effective NLPBackdoor DefenseLLM safety and security → Backdoor and data poisoning attacks
- Tiny Object Tracking: A Large-scale Dataset and A BaselineKnowledge distillation → Detection and dense prediction distillation
- Online Decision TransformerOffline RL and imitation learning from data → Decision transformers and sequence modeling
- Multi-Modal Fusion for Sensorimotor Coordination in Steering Angle PredictionOffline RL and imitation learning from data → Robot manipulation imitation learning
- Privacy-preserving Generative Framework Against Membership Inference AttacksLLM safety and security → Membership inference attacks
- Landscape Analysis for Surrogate Models in the Evolutionary Black-Box Context
- A Minimal Deductive System for RDFS with Negative Statements
- Early Disease Stage Characterization in Parkinson's Disease from Resting-state fMRI Data Using a Long Short-term Memory Network
- Deep Learning to advance the Eigenspace Perturbation Method for Turbulence Model Uncertainty Quantification
- Robots Learn Increasingly Complex Tasks with Intrinsic Motivation and Automatic Curriculum Learning
- Tracking environmental policy changes in the Brazilian Federal Official Gazette
- Paraphrasing Magritte's Observation
- On the Complementarity of Images and Text for the Expression of Emotions in Social Media
- Algebraic function based Banach space valued ordinary and fractional neural network approximations
- Explainable COVID-19 Infections Identification and Delineation Using Calibrated Pseudo Labels
- Adversarial Attacks and Defense Methods for Power Quality Recognition
- A Unified Perspective on Value Backup and Exploration in Monte-Carlo Tree Search
- Motif-topology and Reward-learning improved Spiking Neural Network for Efficient Multi-sensory Integration
- Learning from distinctive candidates to optimize reduced-precision convolution program on tensor cores
- A Graph-based U-Net Model for Predicting Traffic in unseen Cities
- Pseudo Polynomial-Time Top-k Algorithms for d-DNNF Circuits
- Metadata-Induced Contrastive Learning for Zero-Shot Multi-Label Text Classification
- Detecting out-of-context objects using contextual cues
- Improving Image-recognition Edge Caches with a Generative Adversarial Network
- Benign Overfitting without Linearity: Neural Network Classifiers Trained by Gradient Descent for Noisy Linear Data
- Compute Trends Across Three Eras of Machine Learning
- Deep Signatures -- Learning Invariants of Planar Curves
- Boosting Barely Robust Learners: A New Perspective on Adversarial Robustness
- Multi-level Latent Space Structuring for Generative Control
- Identification of Flux Rope Orientation via Neural Networks
- Statistical Limits for Testing Correlation of Hypergraphs
- Motion Correction and Volumetric Reconstruction for Fetal Functional Magnetic Resonance Imaging Data
- Uncertainty Aware System Identification with Universal Policies
- Fast Model-based Policy Search for Universal Policy Networks
- Predicting Out-of-Distribution Error with the Projection Norm
- Active Privacy-Utility Trade-off Against Inference in Time-Series Data Sharing
- SafePicking: Learning Safe Object Extraction via Object-Level Mapping
- Automated Architecture Search for Brain-inspired Hyperdimensional Computing
- CLIPasso: Semantically-Aware Object Sketching
- PEg TRAnsfer Workflow recognition challenge report: Does multi-modal data improve recognition?
- The HaMSE Ontology: Using Semantic Technologies to support Music Representation Interoperability and Musicological Analysis
- Distributed saddle point problems for strongly concave-convex functions
- Investigating Power laws in Deep Representation Learning
- Evaluating MT Systems: A Theoretical Framework
- SHED: A Newton-type algorithm for federated learning based on incremental Hessian eigenvector sharing
- Rate-matching the regret lower-bound in the linear quadratic regulator with unknown dynamics
- The Dual Form of Neural Networks Revisited: Connecting Test Time Predictions to Training Patterns via Spotlights of Attention
- Distributionally Robust Data Join
- Meta-learning with GANs for anomaly detection, with deployment in high-speed rail inspection system
- Answer Set Planning: A Survey
- The Power of Adaptivity in SGD: Self-Tuning Step Sizes with Unbounded Gradients and Affine Variance
- Multi-Modal Knowledge Graph Construction and Application: A Survey
- A Modern Self-Referential Weight Matrix That Learns to Modify Itself
- White-Box Attacks on Hate-speech BERT Classifiers in German with Explicit and Implicit Character Level Defense
- Inference of Multiscale Gaussian Graphical Model
- Visualising Multiplayer Game Spaces
- A PDE-Based Analysis of the Symmetric Two-Armed Bernoulli Bandit
- Learning via nonlinear conjugate gradients and depth-varying neural ODEs
- Assessing Privacy Risks from Feature Vector Reconstruction Attacks
- Using Random Perturbations to Mitigate Adversarial Attacks on Sentiment Analysis Models
- A Novel Speech Intelligibility Enhancement Model based on CanonicalCorrelation and Deep Learning
- Bounded nonlinear forecasts of partially observed geophysical systems with physics-constrained deep learning
- Borrowing from yourself: Faster future video segmentation with partial channel update
- Patch-NetVLAD+: Learned patch descriptor and weighted matching strategy for place recognition
- Improving Generalization via Uncertainty Driven Perturbations
- SleepPPG-Net: a deep learning algorithm for robust sleep staging from continuous photoplethysmography
- Deep soccer captioning with transformer: dataset, semantics-related losses, and multi-level evaluation
- On the Detection of Adaptive Adversarial Attacks in Speaker Verification Systems
- The Schr"odinger Bridge between Gaussian Measures has a Closed Form
- Audio Defect Detection in Music with Deep Networks
- Choices, Risks, and Reward Reports: Charting Public Policy for Reinforcement Learning Systems
- Modeling Reservoir Release Using Pseudo-Prospective Learning and Physical Simulations to Predict Water Temperature
- Cross Domain Few-Shot Learning via Meta Adversarial Training
- Positive-Unlabeled Domain Adaptation
- Continual Learning with Invertible Generative Models
- HaT5: Hate Language Identification using Text-to-Text Transfer Transformer
- Conservative Extensions for Existential Rules
- D4: Detection of Adversarial Diffusion Deepfakes Using Disjoint Ensembles
- Graphon-aided Joint Estimation of Multiple Graphs
- SuperCon: Supervised Contrastive Learning for Imbalanced Skin Lesion Classification
- GenderedNews: Une approche computationnelle des 'ecarts de repr'esentation des genres dans la presse franccaise
- Predictive modeling of microbiological seawater quality classification in karst region using cascade model
- Evaluation of post-hoc interpretability methods in time-series classification
- Bernstein Flows for Flexible Posteriors in Variational Bayes
- Efficient Kernel UCB for Contextual Bandits
- Vehicle and License Plate Recognition with Novel Dataset for Toll Collection
- Scale-free Unconstrained Online Learning for Curved Losses
- Artemis: Articulated Neural Pets with Appearance and Motion synthesis
- A Wasserstein GAN for Joint Learning of Inpainting and Spatial Optimisation
- Nonlinear MCMC for Bayesian Machine Learning
- Measuring dissimilarity with diffeomorphism invariance
- CMW-Net: Learning a Class-Aware Sample Weighting Mapping for Robust Deep Learning
- High-dimensional Inference and FDR Control for Simulated Markov Random Fields
- ClidSum: A Benchmark Dataset for Cross-Lingual Dialogue Summarization
- The Shapley Value in Machine Learning
- Video-driven Neural Physically-based Facial Asset for Production
- Predicting Fuel Consumption in Power Generation Plants using Machine Learning and Neural Networks
- Similarity learning for wells based on logging data
All 147
- Change of measure through the Legendre transform
- Shuffle Private Linear Contextual Bandits
- Controlling Multiple Errors Simultaneously with a PAC-Bayes Bound
- Hybridization of Capsule and LSTM Networks for unsupervised anomaly detection on multivariate data
- A Lightweight, Efficient and Explainable-by-Design Convolutional Neural Network for Internet Traffic Classification
- Cyclical Curriculum Learning
- MusIAC: An extensible generative framework for Music Infilling Applications with multi-level Control
- From Unsupervised to Few-shot Graph Anomaly Detection: A Multi-scale Contrastive Learning Approach
- Unsupervised HDR Imaging: What Can Be Learned from a Single 8-bit Video?
- What Does it Mean for a Language Model to Preserve Privacy?
- Electricity Consumption Forecasting for Out-of-distribution Time-of-Use Tariffs
- Dilated convolutional neural network-based deep reference picture generation for video compression
- Inference with System W Satisfies Syntax Splitting
- Support Vectors and Gradient Dynamics of Single-Neuron ReLU Networks
- Towards Weakly-Supervised Text Spotting using a Multi-Task Transformer
- On the preferred extensions of argumentation frameworks: bijections with naive sets
- Fast and Robust Sparsity Learning over Networks: A Decentralized Surrogate Median Regression Approach
- Entroformer: A Transformer-based Entropy Model for Learned Image Compression
- Exemplar-free Online Continual Learning
- Fast Adversarial Training with Noise Augmentation: A Unified Perspective on RandStart and GradAlign
- Fitting Sparse Markov Models to Categorical Time Series Using Convex Clustering
- Concurrent Training of a Control Policy and a State Estimator for Dynamic and Robust Legged Locomotion
- Bench-Marking And Improving Arabic Automatic Image Captioning Through The Use Of Multi-Task Learning Paradigm
- Jigsaw Puzzle: Selective Backdoor Attack to Subvert Malware Classifiers
- WAD-CMSN: Wasserstein Distance based Cross-Modal Semantic Network for Zero-Shot Sketch-Based Image Retrieval
- Reduced order modeling for flow and transport problems with Barlow Twins self-supervised learning
- Conditional Contrastive Learning with Kernel
- Hindi/Bengali Sentiment Analysis Using Transfer Learning and Joint Dual Input Learning with Self Attention
- Robust estimation algorithms don't need to know the corruption level
- ACORT: A Compact Object Relation Transformer for Parameter Efficient Image Captioning
- Fast Rates in Pool-Based Batch Active Learning
- Computational-Statistical Gaps in Reinforcement Learning
- Learning Causally Invariant Representations for Out-of-Distribution Generalization on Graphs
- Minimax Regret Optimization for Robust Machine Learning under Distribution Shift
- Dual Task Framework for Improving Persona-grounded Dialogue Dataset
- A Survey on Programmatic Weak Supervision
- Understanding Curriculum Learning in Policy Optimization for Online Combinatorial Optimization
- Posterior Consistency for Bayesian Relevance Vector Machines
- A Characterization of Semi-Supervised Adversarially-Robust PAC Learnability
- A Machine-Learning-Aided Visual Analysis Workflow for Investigating Air Pollution Data
- Incremental Learning of Structured Memory via Closed-Loop Transcription
- Regularized Q-learning
- Learning Temporal Rules from Noisy Timeseries Data
- Do People Engage Cognitively with AI? Impact of AI Assistance on Incidental Learning
- PARSE: Pairwise Alignment of Representations in Semi-Supervised EEG Learning for Emotion Recognition
- Including Facial Expressions in Contextual Embeddings for Sign Language Generation
- Give me a knee radiograph, I will tell you where the knee joint area is: a deep convolutional neural network adventure