Papers
Thu 7 Jul 2022
168 papers
- Can Language Models perform Abductive Commonsense Reasoning?LLM reasoning → Reasoning benchmarks and evaluation
- A Novel Unified Conditional Score-based Generative Framework for Multi-modal Medical Image CompletionDiffusion models → Medical imaging and segmentation
- Unified Learning from Demonstrations, Corrections, and Preferences during Physical Human-Robot InteractionOffline RL and imitation learning from data → Robot learning from demonstration
- Challenges and Pitfalls of Bayesian UnlearningLLM safety and security → Machine unlearning
- Energy-based Legged Robots Terrain Traversability Modeling via Deep Inverse Reinforcement LearningOffline RL and imitation learning from data → Real-world robot offline RL
- Multi-Task Retrieval-Augmented Text Generation with Relevance SamplingRetrieval-augmented generation → RAG robustness and adaptive retrieval
- Multi-objective Optimization of Notifications Using Offline Reinforcement LearningOffline RL and imitation learning from data → Decision transformers and sequence modeling
- Riemannian Diffusion Schr"odinger BridgeDiffusion models → Diffusion foundations and sampling
- Layers, Folds, and Semi-Neuronal Information Processing
- Variational multiscale reinforcement learning for discovering reduced order closure models of nonlinear spatiotemporal transport systems
- Domain Adapting Deep Reinforcement Learning for Real-world Speech Emotion Recognition
- Decentralized digital twins of complex dynamical systems
- Multisymplectic Formulation of Deep Learning Using Mean--Field Type Control and Nonlinear Stability of Training Algorithm
- Bayesian Hyperparameter Optimization for Deep Neural Network-Based Network Intrusion Detection
- Predicting Word Learning in Children from the Performance of Computer Vision Systems
- Online Bayesian Meta-Learning for Cognitive Tracking Radar
- Towards Knowledge-based Mining of Mental Disorder Patterns from Textual Data
- Enhancing Fairness of Visual Attribute Predictors
- Learning Causal Effects on Hypergraphs
- Predicting Opinion Dynamics via Sociologically-Informed Neural Networks
- More ConvNets in the 2020s: Scaling up Kernels Beyond 51x51 using Sparsity
- PoseGU: 3D Human Pose Estimation with Novel Human Pose Generator and Unbiased Learning
- Learning and generalization of one-hidden-layer neural networks, going beyond standard Gaussian data
- One for All: Simultaneous Metric and Preference Learning over Multiple Users
- GaitTAKE: Gait Recognition by Temporal Attention and Keypoint-guided Embedding
- Learning-based Autonomous Channel Access in the Presence of Hidden Terminals
- Individual Preference Stability for Clustering
- Hyper-Universal Policy Approximation: Learning to Generate Actions from a Single Image using Hypernets
- Quote Erat Demonstrandum: A Web Interface for Exploring the Quotebank Corpus
- CausalAgents: A Robustness Benchmark for Motion Forecasting using Causal Relationships
- Generalization Guarantee of Training Graph Convolutional Networks with Graph Topology Sampling
- The ACII 2022 Affective Vocal Bursts Workshop & Competition: Understanding a critically understudied modality of emotional expression
- A Study on the Predictability of Sample Learning Consistency
- The use of deep learning enables high diagnostic accuracy in detecting syndesmotic instability on weight-bearing CT scanning
- Finite-rate sparse quantum codes aplenty
- Mirror Complementary Transformer Network for RGB-thermal Salient Object Detection
- G2L: A Geometric Approach for Generating Pseudo-labels that Improve Transfer Learning
- An Embedding-Dynamic Approach to Self-supervised Learning
- BibleTTS: a large, high-fidelity, multilingual, and uniquely African speech corpus
- Highlight Specular Reflection Separation based on Tensor Low-rank and Sparse Decomposition Using Polarimetric Cues
- RWT-SLAM: Robust Visual SLAM for Highly Weak-textured Environments
- VMAS: A Vectorized Multi-Agent Simulator for Collective Robot Learning
- A Novel IoT-based Framework for Non-Invasive Human Hygiene Monitoring using Machine Learning Techniques
- TF-GNN: Graph Neural Networks in TensorFlow
- Should All Proposals be Treated Equally in Object Detection?
- HierarchicalForecast: A Reference Framework for Hierarchical Forecasting in Python
- False Negative Reduction in Semantic Segmentation under Domain Shift using Depth Estimation
- Meta-Learning the Difference: Preparing Large Language Models for Efficient Adaptation
- Recent Results of Energy Disaggregation with Behind-the-Meter Solar Generation
- Finding Fallen Objects Via Asynchronous Audio-Visual Integration
- Bridging the Gap between Object and Image-level Representations for Open-Vocabulary Detection
- Training Transformers Together
- Red PANDA: Disambiguating Anomaly Detection by Removing Nuisance Factors
- VeriDark: A Large-Scale Benchmark for Authorship Verification on the Dark Web
- Inferring Structural Parameters of Low-Surface-Brightness-Galaxies with Uncertainty Quantification using Bayesian Neural Networks
- For Learning in Symmetric Teams, Local Optima are Global Nash Equilibria
- Stochastic optimal well control in subsurface reservoirs using reinforcement learning
- TFCNs: A CNN-Transformer Hybrid Network for Medical Image Segmentation
- Adaptive Personlization in Federated Learning for Highly Non-i.i.d. Data
- Learning to restore images degraded by atmospheric turbulence using uncertainty
- Differentially Private Stochastic Linear Bandits: (Almost) for Free
- Fairness and Bias in Robot Learning
- Back to the Source: Diffusion-Driven Test-Time Adaptation
- LASSIE: Learning Articulated Shapes from Sparse Image Ensemble via 3D Part Discovery
- Semi-supervised Object Detection via Virtual Category Learning
- SC2EGSet: StarCraft II Esport Replay and Game-state Dataset
- Binary Iterative Hard Thresholding Converges with Optimal Number of Measurements for 1-Bit Compressed Sensing
- Machine Learning to Predict Aerodynamic Stall
- AsNER -- Annotated Dataset and Baseline for Assamese Named Entity recognition
- Domain Knowledge Driven 3D Dose Prediction Using Moment-Based Loss Function
- VecGAN: Image-to-Image Translation with Interpretable Latent Directions
- Robust Watermarking for Video Forgery Detection with Improved Imperceptibility and Robustness
- Representation Learning in Continuous-Time Dynamic Signed Networks
- Neural Stein critics with staged L2-regularization
- On the Relationship Between Adversarial Robustness and Decision Region in Deep Neural Networks
- Diagnosing and Remedying Shot Sensitivity with Cosine Few-Shot Learners
- Bayesian Modeling of Language-Evoked Event-Related Potentials
- Non-Linear Pairwise Language Mappings for Low-Resource Multilingual Acoustic Model Fusion
- Investigating the Impact of Cross-lingual Acoustic-Phonetic Similarities on Multilingual Speech Recognition
- Efficient Pruning for Machine Learning Under Homomorphic Encryption
- Neural Language Models are not Born Equal to Fit Brain Data, but Training Helps
- Machine learning of percolation models using graph convolutional neural networks
- Joint Super-Resolution and Inverse Tone-Mapping: A Feature Decomposition Aggregation Network and A New Benchmark
- A simple normalization technique using window statistics to improve the out-of-distribution generalization on medical images
- Group Equality in Adaptive Submodular Maximization
- Market Making with Scaled Beta Policies
- Human-Robot Commensality: Bite Timing Prediction for Robot-Assisted Feeding in Groups
- Sampling from Pre-Images to Learn Heuristic Functions for Classical Planning
- Exploring the sequence length bottleneck in the Transformer for Image Captioning
- Calibrate to Interpret
- Multimodal Feature Extraction for Memes Sentiment Classification
- Multimodal E-Commerce Product Classification Using Hierarchical Fusion
- Win-Win Cooperation: Bundling Sequence and Span Models for Named Entity Recognition
- D2HNet: Joint Denoising and Deblurring with Hierarchical Network for Robust Night Image Restoration
- NESC: Robust Neural End-2-End Speech Coding with GANs
- A Comprehensive Empirical Study of Bias Mitigation Methods for Machine Learning Classifiers
- gym-DSSAT: a crop model turned into a Reinforcement Learning environment
- A Solver + Gradient Descent Training Algorithm for Deep Neural Networks
- Vessel-following model for inland waterways based on deep reinforcement learning
- Part-of-Speech Tagging of Odia Language Using statistical and Deep Learning-Based Approaches
All 168
- Robust optimal well control using an adaptive multi-grid reinforcement learning framework
- Learning the Quality of Machine Permutations in Job Shop Scheduling
- CoQAR: Question Rewriting on CoQA
- Entropy-Based Feature Extraction For Real-Time Semantic Segmentation
- Evaluating Human-like Explanations for Robot Actions in Reinforcement Learning Scenarios
- BMD-GAN: Bone mineral density estimation using x-ray image decomposition into projections of bone-segmented quantitative computed tomography using hierarchical learning
- Revisiting Pretraining Objectives for Tabular Deep Learning
- An Exploration of How Training Set Composition Bias in Machine Learning Affects Identifying Rare Objects
- Leveraging Log Instructions in Log-based Anomaly Detection
- Dual Stream Computer-Generated Image Detection Network Based On Channel Joint And Softpool
- MCTS with Refinement for Proposals Selection Games in Scene Understanding
- Privacy-Preserving Synthetic Educational Data Generation
- SPR:Supervised Personalized Ranking Based on Prior Knowledge for Recommendation
- Learning Music-Dance Representations through Explicit-Implicit Rhythm Synchronization
- Chilled Sampling for Uncertainty Quantification: A Motivation From A Meteorological Inverse Problem
- Deformer: Towards Displacement Field Learning for Unsupervised Medical Image Registration
- FastHebb: Scaling Hebbian Training of Deep Neural Networks to ImageNet Level
- End-to-end Speech-to-Punctuated-Text Recognition
- Harnessing Out-Of-Distribution Examples via Augmenting Content and Style
- DLME: Deep Local-flatness Manifold Embedding
- Algebraic and machine learning approach to hierarchical triple-star stability
- Self-Supervised Velocity Estimation for Automotive Radar Object Detection Networks
- Active Learning and Multi-label Classification for Ellipsis and Coreference Detection in Conversational Question-Answering
- A single T-gate makes distribution learning hard
- Improving Few-Shot Image Classification Using Machine- and User-Generated Natural Language Descriptions
- Style Interleaved Learning for Generalizable Person Re-identification
- PointMCD: Boosting Deep Point Cloud Encoders via Multi-view Cross-modal Distillation for 3D Shape Recognition
- UIILD: A Unified Interpretable Intelligent Learning Diagnosis Framework for Intelligent Tutoring Systems
- Semi-unsupervised Learning for Time Series Classification
- Equivariant Representation Learning via Class-Pose Decomposition
- An Additive Instance-Wise Approach to Multi-class Model Interpretation
- Deep learning based Hand gesture recognition system and design of a Human-Machine Interface
- Masked Surfel Prediction for Self-Supervised Point Cloud Learning
- A Simple and Provably Efficient Algorithm for Asynchronous Federated Contextual Linear Bandits
- Uncertainty-Aware Self-supervised Neural Network for Liver T1ρ Mapping with Relaxation Constraint
- Quantum Advantage in Variational Bayes Inference
- A conditional gradient homotopy method with applications to Semidefinite Programming
- A State Transition Model for Mobile Notifications via Survival Analysis
- EPIC-KITCHENS-100 Unsupervised Domain Adaptation Challenge for Action Recognition 2022: Team HNU-FPV Technical Report
- Backpropagation on Dynamical Networks
- Online SuBmodular + SuPermodular (BP) Maximization with Bandit Feedback
- Attention Round for Post-Training Quantization
- Word Embedding for Social Sciences: An Interdisciplinary Survey
- Pre-training helps Bayesian optimization too
- Adaptation of Surgical Activity Recognition Models Across Operating Rooms
- DRL-ISP: Multi-Objective Camera ISP with Deep Reinforcement Learning
- What Makes for Automatic Reconstruction of Pulmonary Segments
- Towards the Practical Utility of Federated Learning in the Medical Domain
- Cross-Scale Vector Quantization for Scalable Neural Speech Coding
- Device-Cloud Collaborative Recommendation via Meta Controller
- Contrastive Learning from Spatio-Temporal Mixed Skeleton Sequences for Self-Supervised Skeleton-Based Action Recognition
- Shadow-Background-Noise 3D Spatial Decomposition Using Sparse Low-Rank Gaussian Properties for Video-SAR Moving Target Shadow Enhancement
- Back to the Basics: Revisiting Out-of-Distribution Detection Baselines
- Multi-Label Learning to Rank through Multi-Objective Optimization
- Deep Rotation Correction without Angle Prior
- A Large Scale Search Dataset for Unbiased Learning to Rank
- Multi-Task Lung Nodule Detection in Chest Radiographs with a Dual Head Network
- AV-Gaze: A Study on the Effectiveness of Audio Guided Visual Attention Estimation for Non-Profilic Faces
- Single-image Defocus Deblurring by Integration of Defocus Map Prediction Tracing the Inverse Problem Computation
- Self-Supervised RF Signal Representation Learning for NextG Signal Classification with Deep Learning
- Vision Transformers: State of the Art and Research Challenges
- Dual-Stream Transformer for Generic Event Boundary Captioning
- Sensitivity Analysis on Transferred Neural Architectures of BERT and GPT-2 for Financial Sentiment Analysis
- Not All Models Are Equal: Predicting Model Transferability in a Self-challenging Fisher Space
- On the instrumental variable estimation with many weak and invalid instruments
- FedHeN: Federated Learning in Heterogeneous Networks
- Enhancing a Student Productivity Model for Adaptive Problem-Solving Assistance
- Partial Shape Similarity via Alignment of Multi-Metric Hamiltonian Spectra