Papers
Wed 30 Nov 2022
226 papers
- Time-Efficient Reward Learning via Visually Assisted Cluster RankingLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
- One Risk to Rule Them All: A Risk-Sensitive Perspective on Model-Based Offline Reinforcement LearningOffline RL and imitation learning from data → Offline RL algorithms
- Denoising Diffusion for Sampling SAT SolutionsDiffusion models → Diffusion foundations and sampling
- Fast Inference from Transformers via Speculative DecodingEfficient LLM inference and serving → Speculative decoding
- Weisfeiler and Leman Go RelationalLLM reasoning → Knowledge- and tool-augmented reasoning
- High-Fidelity Guided Image Synthesis with Latent Diffusion ModelsDiffusion models → Image generation, text-to-image and editing
- Self-Supervised Continual Graph Learning in Adaptive Riemannian SpacesKnowledge distillation → Graph neural network distillation
- Hint-dynamic Knowledge DistillationKnowledge distillation → General knowledge distillation methods
- Knowledge Distillation based Degradation Estimation for Blind Super-ResolutionKnowledge distillation → General knowledge distillation methods
- Towards Improving Exploration in Self-Imitation Learning using Intrinsic MotivationOffline RL and imitation learning from data → Imitation learning methods
- Attention-Based Depth Distillation with 3D-Aware Positional Encoding for Monocular 3D Object DetectionKnowledge distillation → Detection and dense prediction distillation
- Score-based Continuous-time Discrete Diffusion ModelsDiffusion models → Diffusion foundations and sampling
- Explicit Knowledge Transfer for Weakly-Supervised Code GenerationKnowledge distillation → Knowledge distillation for LLMs
- 3D Neural Field Generation using Triplane DiffusionDiffusion models → 3D, point cloud and scene generation
- Using uncertainty-aware machine learning models to study aerosol-cloud interactions
- Extreme Image Transformations Affect Humans and Machines Differently
- CatlNet: Learning Communication and Coordination Policies from CaTL+ Specifications
- Normalized Contrastive Learning for Text-Video Retrieval
- Neural Network Learner for Minesweeper
- Automatic Identification of Motivation for Code-Switching in Speech Transcripts
- An Overview of Indian Spoken Language Recognition from Machine Learning Perspective
- Overlapping oriented imbalanced ensemble learning method based on projective clustering and stagewise hybrid sampling
- Funnel-based Reward Shaping for Signal Temporal Logic Tasks in Reinforcement Learning
- Interpretation of Neural Networks is Susceptible to Universal Adversarial Perturbations
- An Empirical Study on the Efficacy of Deep Active Learning for Image Classification
- Limitations on approximation by deep and shallow neural networks
- Real-time Bidding Strategy in Display Advertising: An Empirical Analysis
- KGML-xDTD: A Knowledge Graph-based Machine Learning Framework for Drug Treatment Prediction and Mechanism Description
- Welfare and Fairness in Multi-objective Reinforcement Learning
- Understanding Cryptocoins Trends Correlations
- Denoising Deep Generative Models
- Preliminary Study on SSCF-derived Polar Coordinate for ASR
- New Probabilistic-Dynamic Multi-Method Ensembles for Optimization based on the CRO-SL
- OpenApePose: a database of annotated ape photographs for pose estimation
- Prioritizing Policies for Furthering Responsible Artificial Intelligence in the United States
- xTrimoABFold: De novo Antibody Structure Prediction without MSA
- FuRPE: Learning Full-body Reconstruction from Part Experts
- An enhanced simulation-based multi-objective optimization approach with knowledge discovery for reconfigurable manufacturing systems
- Quantum Neural Networks for a Supply Chain Logistics Application
- A perspective on the use of health digital twins in computational pathology
- Learning Agile Paths from Optimal Control
- Open Relation and Event Type Discovery with Type Abstraction
- SPADE: Semi-supervised Anomaly Detection under Distribution Mismatch
- Layout-aware Dreamer for Embodied Referring Expression Grounding
- Deep Learning-Based Vehicle Speed Prediction for Ecological Adaptive Cruise Control in Urban and Highway Scenarios
- Novel Modelling Strategies for High-frequency Stock Trading Data
- FIESTA: Autoencoders for accurate fiber segmentation in tractography
- Word Alignment in the Era of Deep Learning: A Tutorial
- DEL-Dock: Molecular Docking-Enabled Modeling of DNA-Encoded Libraries
- Answering Private Linear Queries Adaptively using the Common Mechanism
- Universal Neural Optimal Transport
- Evidential Conditional Neural Processes
- Self-Supervised Feature Learning for Long-Term Metric Visual Localization
- Towards True Lossless Sparse Communication in Multi-Agent Systems
- Task-Specific Embeddings for Ante-Hoc Explainable Text Classification
- Rethinking Causality-driven Robot Tool Segmentation with Temporal Constraints
- MrSARP: A Hierarchical Deep Generative Prior for SAR Image Super-resolution
- Auxiliary Learning as a step towards Artificial General Intelligence
- Single Slice Thigh CT Muscle Group Segmentation with Domain Adaptation and Self-Training
- Part-based Face Recognition with Vision Transformers
- Feature Selection with Distance Correlation
- Data-driven Science and Machine Learning Methods in Laser-Plasma Physics
- Semi-Supervised Heterogeneous Graph Learning with Multi-level Data Augmentation
- Random Copolymer inverse design system orienting on Accurate discovering of Antimicrobial peptide-mimetic copolymers
- Optical multi-task learning using multi-wavelength diffractive deep neural networks
- Location analysis of players in UEFA EURO 2020 and 2022 using generalized valuation of defense by estimating probabilities
- Knowledge-augmented Deep Learning and Its Applications: A Survey
- Scalable Pathogen Detection from Next Generation DNA Sequencing with Deep Learning
- Variational Laplace Autoencoders
- Interpretability with full complexity by constraining feature information
- Plateau-reduced Differentiable Path Tracing
- Non-Deterministic Approximation Fixpoint Theory and Its Application in Disjunctive Logic Programming
- SinGRAF: Learning a 3D Generative Radiance Field for a Single Scene
- CREPE: Open-Domain Question Answering with False Presuppositions
- CLIPascene: Scene Sketching with Different Types and Levels of Abstraction
- Safe and Efficient Reinforcement Learning Using Disturbance-Observer-Based Control Barrier Functions
- Efficient Reinforcement Learning Through Trajectory Generation
- Pex: Memory-efficient Microcontroller Deep Learning through Partial Execution
- Tight Certification of Adversarially Trained Neural Networks via Nonconvex Low-Rank Semidefinite Relaxations
- NeRFInvertor: High Fidelity NeRF-GAN Inversion for Single-shot Real Image Animation
- ObjCAViT: Improving Monocular Depth Estimation Using Natural Language Models And Image-Object Cross-Attention
- AIO-P: Expanding Neural Performance Predictors Beyond Image Classification
- GENNAPE: Towards Generalized Neural Architecture Performance Estimators
- Topological Data Analysis for Speech Processing
- ExtremeBERT: A Toolkit for Accelerating Pretraining of Customized BERT
- Resource Sharing Through Multi-Round Matchings
- EURO: ESPnet Unsupervised ASR Open-source Toolkit
- Nonlinear Advantage: Trained Networks Might Not Be As Complex as You Think
- Investigation of Proper Orthogonal Decomposition for Echo State Networks
- Optimizing Explanations by Network Canonization and Hyperparameter Search
- How to Train an Accurate and Efficient Object Detection Model on Any Dataset
- Misogyny classification of German newspaper forum comments
- Bi-directional Feature Reconstruction Network for Fine-Grained Few-Shot Image Classification
- Proximal Residual Flows for Bayesian Inverse Problems
- On Regret-optimal Cooperative Nonstochastic Multi-armed Bandits
- ConvLab-3: A Flexible Dialogue System Toolkit Based on a Unified Data Format
- Learning Label Modular Prompts for Text Classification in the Wild
- Multidimensional analysis using sensor arrays with deep learning for high-precision and high-accuracy diagnosis
- BudgetLongformer: Can we Cheaply Pretrain a SotA Legal Language Model From Scratch?
- Targets in Reinforcement Learning to solve Stackelberg Security Games
All 226
- BEVUDA: Multi-geometric Space Alignments for Domain Adaptive BEV 3D Object Detection
- sEHR-CE: Language modelling of structured EHR data for efficient and generalizable patient cohort expansion
- Global Convergence of Localized Policy Iteration in Networked Multi-Agent Reinforcement Learning
- Multiresolution Textual Inversion
- BEVPoolv2: A Cutting-edge Implementation of BEVDet Toward Deployment
- Self-Emphasizing Network for Continuous Sign Language Recognition
- Reinforcement Learning for Multi-Truck Vehicle Routing Problems
- Interpreting Vulnerabilities of Multi-Instance Learning to Adversarial Perturbations
- Fair Ranking with Noisy Protected Attributes
- SNAF: Sparse-view CBCT Reconstruction with Neural Attenuation Fields
- Rationale-Guided Few-Shot Classification to Detect Abusive Language
- From Actions to Events: A Transfer Learning Approach Using Improved Deep Belief Networks
- Spatio-Temporal Crop Aggregation for Video Representation Learning
- Neural Network Representation of Time Integrators
- High-Dimensional Wide Gap k-Means Versus Clustering Axioms
- A data set providing synthetic and real-world fisheye video sequences
- Directed Acyclic Graph Structure Learning from Dynamic Graphs
- Continuous Methods : Adaptively intrusive reduced order model closure
- A hybrid motion estimation technique for fisheye video sequences based on equisolid re-projection
- Continual Learning with Distributed Optimization: Does CoCoA Forget?
- A Pipeline for Generating, Annotating and Employing Synthetic Data for Real World Question Answering
- Privacy-Preserving Federated Deep Clustering based on GAN
- Rendezvous in Time: An Attention-based Temporal Fusion approach for Surgical Triplet Recognition
- Pattern Attention Transformer with Doughnut Kernel
- BASiS: Batch Aligned Spectral Embedding Space
- On the Design of Communication-Efficient Federated Learning for Health Monitoring
- Weakly Supervised 3D Multi-person Pose Estimation for Large-scale Scenes based on Monocular Camera and Single LiDAR
- DSNet: a simple yet efficient network with dual-stream attention for lesion segmentation
- Using Text Classification with a Bayesian Correction for Estimating Overreporting in the Creditor Reporting System on Climate Adaptation Finance
- AIONER: All-in-one scheme-based biomedical named entity recognition using deep learning
- Predicting Properties of Quantum Systems with Conditional Generative Models
- ALARM: Active LeArning of Rowhammer Mitigations
- DiffPose: Toward More Reliable 3D Pose Estimation
- Evaluating Digital Agriculture Recommendations with Causal Inference
- VideoDubber: Machine Translation with Speech-Aware Length Control for Video Dubbing
- Differentiable optimization of the Debye-Wolf integral for light shaping and adaptive optics in two-photon microscopy
- 3D GAN Inversion with Facial Symmetry Prior
- Learning Motion-Robust Remote Photoplethysmography through Arbitrary Resolution Videos
- The Cost of Learning: Efficiency vs. Efficacy of Learning-Based RRM for 6G
- Quadapter: Adapter for GPT-2 Quantization
- Learning non-stationary and discontinuous functions using clustering, classification and Gaussian process modelling
- Rethinking Disparity: A Depth Range Free Multi-View Stereo Based on Disparity
- Generating Realistic Synthetic Relational Data through Graph Variational Autoencoders
- T2G-Former: Organizing Tabular Features into Relation Graphs Promotes Heterogeneous Feature Interaction
- A Unifying Theory of Distance from Calibration
- Context-Aware Ensemble Learning for Time Series
- X-PuDu at SemEval-2022 Task 6: Multilingual Learning for English and Arabic Sarcasm Detection
- MVRackLay: Monocular Multi-View Layout Estimation for Warehouse Racks and Shelves
- Generalized Deep Learning-based Proximal Gradient Descent for MR Reconstruction
- Transformers are Short Text Classifiers: A Study of Inductive Short Text Classifiers on Benchmarks and Real-world Datasets
- A Deep Learning Approach to the Prediction of Drug Side-Effects on Molecular Graphs
- NeAF: Learning Neural Angle Fields for Point Normal Estimation
- Logic and Commonsense-Guided Temporal Knowledge Graph Completion
- Rephrasing the Reference for Non-Autoregressive Machine Translation
- A Major Obstacle for NLP Research: Let's Talk about Time Allocation!
- ATASI-Net: An Efficient Sparse Reconstruction Network for Tomographic SAR Imaging with Adaptive Threshold
- Revisiting text decomposition methods for NLI-based factuality scoring of summaries
- Challenging mitosis detection algorithms: Global labels allow centroid localization
- Neighbour Consistency Guided Pseudo-Label Refinement for Unsupervised Person Re-Identification
- Universal Feature Selection Tool (UniFeat): An Open-Source Tool for Dimensionality Reduction
- Linking Sketch Patches by Learning Synonymous Proximity for Graphic Sketch Representation
- Reconstructing Hand-Held Objects from Monocular Video
- MLC at HECKTOR 2022: The Effect and Importance of Training Data when Analyzing Cases of Head and Neck Tumors using Machine Learning
- WeatherFusionNet: Predicting Precipitation from Satellite Data
- A Probabilistic-Logic based Commonsense Representation Framework for Modelling Inferences with Multiple Antecedents and Varying Likelihoods
- Efficient Adversarial Input Generation via Neural Net Patching
- Camelira: An Arabic Multi-Dialect Morphological Disambiguator
- Toward Robust Diagnosis: A Contour Attention Preserving Adversarial Defense for COVID-19 Detection
- Generalised Spherical Text Embedding
- NOPE-SAC: Neural One-Plane RANSAC for Sparse-View Planar 3D Reconstruction
- Dr.3D: Adapting 3D GANs to Artistic Drawings
- Gradient Domain Weighted Guided Image Filtering
- Adaptive adversarial training method for improving multi-scale GAN based on generalization bound theory
- Two-branch Multi-scale Deep Neural Network for Generalized Document Recapture Attack Detection
- SafeSpace MFNet: Precise and Efficient MultiFeature Drone Detection Network
- Robust and Fast Measure of Information via Low-rank Representation
- An Optimal Transport-driven Approach for Cultivating Latent Space in Online Incremental Learning
- Rethinking Out-of-Distribution Detection From a Human-Centric Perspective
- From Coarse to Fine: Hierarchical Pixel Integration for Lightweight Image Super-Resolution
- KRLS: Improving End-to-End Response Generation in Task Oriented Dialog with Reinforced Keywords Learning
- Handling Missing Data via Max-Entropy Regularized Graph Autoencoder
- Uncertainty-Aware Image Captioning
- GeoUDF: Surface Reconstruction from 3D Point Clouds via Geometry-guided Distance Representation
- Improving Cross-Modal Retrieval with Set of Diverse Embeddings
- General policy mapping: online continual reinforcement learning inspired on the insect brain
- Taming Hyperparameter Tuning in Continuous Normalizing Flows Using the JKO Scheme
- Split-PU: Hardness-aware Training Strategy for Positive-Unlabeled Learning
- VI-PINNs: Variance-involved Physics-informed Neural Networks for Fast and Accurate Prediction of Partial Differential Equations
- DimenFix: A novel meta-dimensionality reduction method for feature preservation
- HEAT: Hardware-Efficient Automatic Tensor Decomposition for Transformer Compression
- ClaRet -- A CNN Architecture for Optical Coherence Tomography
- Protein Language Models and Structure Prediction: Connection and Progression
- Quasi Non-Negative Quaternion Matrix Factorization with Application to Color Face Recognition
- Growing Instance Mask on Leaf
- Understanding transit ridership in an equity context through a comparison of statistical and machine learning algorithms
- A minor extension of the logistic equation for growth of word counts on online media: Parametric description of diversity of growth phenomena in society
- Towards Training GNNs using Explanation Directed Message Passing
- Boosted Dynamic Neural Networks
- Where Am I Now? Dynamically Finding Optimal Sensor States to Minimize Localization Uncertainty for a Perception-Denied Rover
- Findings of the WMT 2022 Shared Task on Translation Suggestion
- Policy Optimization over General State and Action Spaces
- Coordinating Cross-modal Distillation for Molecular Property Prediction
- Extracting Semantic Knowledge from GANs with Unsupervised Learning
- Statistical treatment of convolutional neural network super-resolution of inland surface wind for subgrid-scale variability quantification
- An Efficient Split Fine-tuning Framework for Edge and Cloud Collaborative Learning
- Conservative-Progressive Collaborative Learning for Semi-supervised Semantic Segmentation
- Interpretability and accessibility of machine learning in selected food processing, agriculture and health applications
- SGDraw: Scene Graph Drawing Interface Using Object-Oriented Representation
- Automated anomaly-aware 3D segmentation of bones and cartilages in knee MR images from the Osteoarthritis Initiative
- Visual-tactile Fusion for Transparent Object Grasping in Complex Backgrounds
- Computationally Efficient Reinforcement Learning: Targeted Exploration leveraging Simple Rules
- A Node-collaboration-informed Graph Convolutional Network for Precise Representation to Undirected Weighted Graphs
- Automatic Discovery of Multi-perspective Process Model using Reinforcement Learning
- Capturing long-range interaction with reciprocal space neural network
- FREDSR: Fourier Residual Efficient Diffusive GAN for Single Image Super Resolution
- ShaDocNet: Learning Spatial-Aware Tokens in Transformer for Document Shadow Removal
- Domain Mismatch Doesn't Always Prevent Cross-Lingual Transfer Learning
- FedGPO: Heterogeneity-Aware Global Parameter Optimization for Efficient Federated Learning
- Dynamic Sparse Training via Balancing the Exploration-Exploitation Trade-off
- Geoclidean: Few-Shot Generalization in Euclidean Geometry
- Stochastic Parameterization of Column Physics using Generative Adversarial Networks
- Correlation recurrent units: A novel neural architecture for improving the predictive performance of time-series data
- CLIP-Nav: Using CLIP for Zero-Shot Vision-and-Language Navigation
- COMET: A Comprehensive Cluster Design Methodology for Distributed Deep Learning Training
- Progressive Knowledge Transfer Based on Human Visual Perception Mechanism for Perceptual Quality Assessment of Point Clouds
- Iterative Scene Graph Generation with Generative Transformers