Papers
Fri 10 Jun 2022
164 papers
- Large-Scale Retrieval for Reinforcement LearningOffline RL and imitation learning from data → Offline RL algorithms
- Bayesian Estimation of Differential PrivacyLLM safety and security → Membership inference attacks
- How Much is Enough? A Study on Diffusion Times in Score-based Generative ModelsDiffusion models → Diffusion foundations and sampling
- Image Generation with Multimodal Priors using Denoising Diffusion Probabilistic ModelsDiffusion models → Diffusion foundations and sampling
- GAMR: A Guided Attention Model for (visual) ReasoningLLM reasoning → Multimodal reasoning
- Imitation Learning via Differentiable PhysicsOffline RL and imitation learning from data → Imitation learning methods
- Machine Learning Application in Health
- Think About the Stakeholders First! Towards an Algorithmic Transparency Playbook for Regulatory Compliance
- Using Interpretable Machine Learning to Massively Increase the Number of Antibody-Virus Interactions Across Studies
- Emoji-based Fine-grained Attention Network for Sentiment Analysis in the Microblog Comments
- Unsupervised Sentence Simplification via Dependency Parsing
- Label Noise-Resistant Mean Teaching for Weakly Supervised Fake News Detection
- Putting GPT-3's Creativity to the (Alternative Uses) Test
- Toward Dynamic Stability Assessment of Power Grid Topologies using Graph Neural Networks
- Flexible Differentiable Optimization via Model Transformations
- Seeing the forest and the tree: Building representations of both individual and collective dynamics with transformers
- A Synapse-Threshold Synergistic Learning Approach for Spiking Neural Networks
- Causal Discovery in Hawkes Processes by Minimum Description Length
- Extending Process Discovery with Model Complexity Optimization and Cyclic States Identification: Application to Healthcare Processes
- An Enactivist-Inspired Mathematical Model of Cognition
- A Correlation-Ratio Transfer Learning and Variational Stein's Paradox
- Fast building segmentation from satellite imagery and few local labels
- Generalizable Neural Radiance Fields for Novel View Synthesis with Transformer
- An application of neural networks to a problem in knot theory and group theory (untangling braids)
- A multi-objective constrained POMDP model for breast cancer screening
- Object Detection, Recognition, Deep Learning, and the Universal Law of Generalization
- Anchor-Changing Regularized Natural Policy Gradient for Multi-Objective Reinforcement Learning
- Social Practices for Social Driven Conversations in Serious Games
- Cross-TOP: Zero-Shot Cross-Schema Task-Oriented Parsing
- Differentiable Rendering of Neural SDFs through Reparameterization
- Synthetic Over-sampling for Imbalanced Node Classification with Graph Neural Networks
- Memory Classifiers: Two-stage Classification for Robustness in Machine Learning
- Object Instance Identification in Dynamic Environments
- Intrinsic dimensionality and generalization properties of the R-norm inductive bias
- Graph-in-Graph Network for Automatic Gene Ontology Description Generation
- EigenFairing: 3D Model Fairing using Image Coherence
- ProActive: Self-Attentive Temporal Point Process Flows for Activity Sequences
- Localized adversarial artifacts for compressed sensing MRI
- From Labels to Priors in Capsule Endoscopy: A Prior Guided Approach for Improving Generalization with Few Labels
- AHD ConvNet for Speech Emotion Classification
- Decoupling Predictions in Distributed Learning for Multi-Center Left Atrial MRI Segmentation
- Poissonian Blurred Image Deconvolution by Framelet based Local Minimal Prior
- Learning to Estimate Shapley Values with Vision Transformers
- Less Is More: Linear Layers on CLIP Features as Powerful VizWiz Model
- PILC: Practical Image Lossless Compression with an End-to-end GPU Oriented Neural Framework
- Dual-Branch Squeeze-Fusion-Excitation Module for Cross-Modality Registration of Cardiac SPECT and CT
- Superresolution and Segmentation of OCT scans using Multi-Stage adversarial Guided Attention Training
- Does Self-supervised Learning Really Improve Reinforcement Learning from Pixels?
- When Does Adaptivity Help for Quantum State Learning?
- Causal Balancing for Domain Generalization
- Meta Optimal Transport
- Balanced Product of Calibrated Experts for Long-Tailed Recognition
- Is Self-Supervised Learning More Robust Than Supervised Learning?
- Explaining Image Classifiers Using Contrastive Counterfactuals in Generative Latent Spaces
- Interactively Learning Preference Constraints in Linear Bandits
- Rethinking Spatial Invariance of Convolutional Networks for Object Counting
- Lost in Transmission: On the Impact of Networking Corruptions on Video Machine Learning Models
- Accelerated Algorithms for Constrained Nonconvex-Nonconcave Min-Max Optimization and Comonotone Inclusion
- List-Decodable Sparse Mean Estimation via Difference-of-Pairs Filtering
- ROI-Constrained Bidding via Curriculum-Guided Bayesian Reinforcement Learning
- StructCoder: Structure-Aware Transformer for Code Generation
- Dimensional Modeling of Emotions in Text with Appraisal Theories: Corpus Creation, Annotation Reliability, and Prediction
- Optical Diffraction Tomography based on 3D Physics-Inspired Neural Network (PINN)
- Measuring the Carbon Intensity of AI in Cloud Instances
- Log-concave density estimation in undirected graphical models
- ClamNet: Using contrastive learning with variable depth Unets for medical image segmentation
- A Multi-Task Benchmark for Korean Legal Language Understanding and Judgement Prediction
- Anisotropic View Distance Metric for High-Dimensional Data: Theory, Geometry, and Fast Computation
- On the safe use of prior densities for Bayesian model selection
- Hierarchical Federated Learning with Privacy
- Dynamic mean field programming
- Nominal Metaphor Generation with Multitask Learning
- Learning the Space of Deep Models
- On Convergence of FedProx: Local Dissimilarity Invariant Bounds, Non-smoothness and Beyond
- SERE: Exploring Feature Self-relation for Self-supervised Transformer
- GD-VAEs: Geometric Dynamic Variational Autoencoders for Learning Nonlinear Dynamics and Dimension Reductions
- Human-AI Interaction Design in Machine Teaching
- Lightweight Conditional Model Extrapolation for Streaming Data under Class-Prior Shift
- A Causal Research Pipeline and Tutorial for Psychologists and Social Scientists
- Multifidelity Reinforcement Learning with Control Variates
- An Image Processing Pipeline for Camera Trap Time-Lapse Recordings
- MEAT: Maneuver Extraction from Agent Trajectories
- Teacher Perception of Automatically Extracted Grammar Concepts for L2 Language Learning
- Referring Image Matting
- Weakly-supervised segmentation using inherently-explainable classification models and their application to brain tumour classification
- Fast Deep Autoencoder for Federated learning
- Distributionally Robust End-to-End Portfolio Construction
- Real-time Hyper-Dimensional Reconfiguration at the Edge using Hardware Accelerators
- Globally-Optimal Contrast Maximisation for Event Cameras
- Stochastic Zeroth order Descent with Structured Directions
- REKnow: Enhanced Knowledge for Joint Entity and Relation Extraction
- PAVI: Plate-Amortized Variational Inference
- Deep Multi-Agent Reinforcement Learning with Hybrid Action Spaces based on Maximum Entropy
- Hankel low-rank approximation and completion in time series analysis and forecasting: a brief review
- Saccade Mechanisms for Image Classification, Object Detection and Tracking
- Federated Momentum Contrastive Clustering
- Learning self-calibrated optic disc and cup segmentation from multi-rater annotations
- Muffliato: Peer-to-Peer Privacy Amplification for Decentralized Optimization and Averaging
- Tensor Train for Global Optimization Problems in Robotics
- Diffeomorphic Counterfactuals with Generative Models
All 164
- Fundamental Limits in Formal Verification of Message-Passing Neural Networks
- Social Network Structure Shapes Innovation: Experience-sharing in RL with SAPIENS
- Sentiment analysis on electricity twitter posts
- Scalable Deep Gaussian Markov Random Fields for General Graphs
- Going Beyond the Cookie Theft Picture Test: Detecting Cognitive Impairments using Acoustic Features
- Building an Icelandic Entity Linking Corpus
- Weighted Ensembles for Active Learning with Adaptivity
- Subjective Quality Assessment for Images Generated by Computer Graphics
- The Symmetric Generalized Eigenvalue Problem as a Nash Equilibrium
- Zero-Shot Audio Classification using Image Embeddings
- Positional Label for Self-Supervised Vision Transformer
- Unsupervised and Few-shot Parsing from Pretrained Language Models
- Convolutional layers are equivariant to discrete shifts but not continuous translations
- Refining neural network predictions using background knowledge
- NR-DFERNet: Noise-Robust Network for Dynamic Facial Expression Recognition
- Borrowing or Codeswitching? Annotating for Finer-Grained Distinctions in Language Mixing
- Deep Learning-based Massive MIMO CSI Acquisition for 5G Evolution and 6G
- Merak: An Efficient Distributed DNN Training Framework with Automated 3D Parallelism for Giant Foundation Models
- Self-Supervised Deep Subspace Clustering with Entropy-norm
- Evolutionary Echo State Network: evolving reservoirs in the Fourier space
- Deep Multi-View Semi-Supervised Clustering with Sample Pairwise Constraints
- Neural Template: Topology-aware Reconstruction and Disentangled Generation of 3D Meshes
- Generate, Evaluate, and Select: A Dialogue System with a Response Evaluator for Diversity-Aware Response Generation
- Sort by Structure: Language Model Ranking as Dependency Probing
- Response to: Significance and stability of deep learning-based identification of subtypes within major psychiatric disorders. Molecular Psychiatry (2022)
- Ego2HandsPose: A Dataset for Egocentric Two-hand 3D Global Pose Estimation
- RuCoCo: a new Russian corpus with coreference annotation
- A bio-inspired implementation of a sparse-learning spike-based hippocampus memory model
- A Novel Chinese Dialect TTS Frontend with Non-Autoregressive Neural Machine Translation
- Offline Stochastic Shortest Path: Learning, Evaluation and Towards Optimality
- Fisher SAM: Information Geometry and Sharpness Aware Minimisation
- PatchComplete: Learning Multi-Resolution Patch Priors for 3D Shape Completion on Unseen Categories
- NAGphormer: A Tokenized Graph Transformer for Node Classification in Large Graphs
- ABCDE: An Agent-Based Cognitive Development Environment
- Efficient Heterogeneous Treatment Effect Estimation With Multiple Experiments and Multiple Outcomes
- Out of Sight, Out of Mind: A Source-View-Wise Feature Aggregation for Multi-View Image-Based Rendering
- NeRF-In: Free-Form NeRF Inpainting with RGB-D Priors
- Provable Guarantees for Sparsity Recovery with Deterministic Missing Data Patterns
- Explaining Neural Networks without Access to Training Data
- Adversarial Counterfactual Environment Model Learning
- AntPivot: Livestream Highlight Detection via Hierarchical Attention Mechanism
- Deep Leakage from Model in Federated Learning
- mathsfG2Retro as a Two-Step Graph Generative Models for Retrosynthesis Prediction
- Enhancing Clean Label Backdoor Attack with Two-phase Specific Triggers
- Unsupervised Foggy Scene Understanding via Self Spatial-Temporal Label Diffusion
- Convex Hull Prediction for Adaptive Video Streaming by Recurrent Learning
- The 1st Data Science for Pavements Challenge
- Multi-fidelity Hierarchical Neural Processes
- Ask to Know More: Generating Counterfactual Explanations for Fake Claims
- The Gender Gap in Face Recognition Accuracy Is a Hairy Problem
- Binarizing Split Learning for Data Privacy Enhancement and Computation Reduction
- Symbolic image detection using scene and knowledge graphs
- Conformal Prediction Intervals for Markov Decision Process Trajectories
- Mixed integer linear optimization formulations for learning optimal binary classification trees
- Beyond the Gates of Euclidean Space: Temporal-Discrimination-Fusions and Attention-based Graph Neural Network for Human Activity Recognition
- Heterogeneous Face Recognition via Face Synthesis with Identity-Attribute Disentanglement
- Masked Autoencoders are Robust Data Augmentors
- Neural Laplace: Learning diverse classes of differential equations in the Laplace domain
- Hierarchical mixtures of Gaussians for combined dimensionality reduction and clustering
- In Defense of Core-set: A Density-aware Core-set Selection for Active Learning
- Communication Efficient Distributed Learning for Kernelized Contextual Bandits
- Training Neural Networks using SAT solvers
- R4D: Utilizing Reference Objects for Long-Range Distance Estimation
- The Slingshot Mechanism: An Empirical Study of Adaptive Optimizers and the Grokking Phenomenon