Papers
Wed 5 Oct 2022
204 papers
- Reward-Mixing MDPs with a Few Latent Contexts are LearnableLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
- Towards Safe Mechanical Ventilation Treatment Using Deep Offline Reinforcement LearningOffline RL and imitation learning from data → Safe offline RL
- DALL-E-Bot: Introducing Web-Scale Diffusion Models to RoboticsDiffusion models → Diffusion and flow policies for robotics
- clip2latent: Text driven sampling of a pre-trained StyleGAN using denoising diffusion and CLIPDiffusion models → Image generation, text-to-image and editing
- Informed sampling-based trajectory planner for automated driving in dynamic urban environmentsEnd-to-end autonomous driving → Imitation-learning end-to-end planners
- Imagen Video: High Definition Video Generation with Diffusion ModelsDiffusion models → Video generation
- Spatial-Temporal-Aware Safe Multi-Agent Reinforcement Learning of Connected Autonomous Vehicles in Challenging ScenariosEnd-to-end autonomous driving → Cooperative and V2X driving
- LDEdit: Towards Generalized Text Guided Image Manipulation via Latent Diffusion ModelsMultimodal LLMs / vision-language models → Image editing and quality assessment +1
- CW-ERM: Improving Autonomous Driving Planning with Closed-loop Weighted Empirical Risk MinimizationEnd-to-end autonomous driving → Imitation-learning end-to-end planners +1
- Automated Graph Self-supervised Learning via Multi-teacher Knowledge DistillationKnowledge distillation → Graph neural network distillation
- Teaching Yourself: Graph Self-Distillation on Neighborhood for Node ClassificationKnowledge distillation → Graph neural network distillation
- Meta-Ensemble Parameter LearningKnowledge distillation → General knowledge distillation methods
- Option-Aware Adversarial Inverse Reinforcement Learning for Robotic ControlOffline RL and imitation learning from data → Inverse reinforcement learning
- Satellite-derived solar radiation for intra-hour and intra-day applications: Biases and uncertainties by season and altitude
- Active Image Indexing
- Restricted Bernoulli Matrix Factorization: Balancing the trade-off between prediction accuracy and coverage in classification based collaborative filtering
- Addressing contingency in algorithmic (mis)information classification: Toward a responsible machine learning agenda
- APGKT: Exploiting Associative Path on Skills Graph for Knowledge Tracing
- Misaligned orientations of 4f optical neural network for image classification accuracy on various datasets
- Reprogramming Pretrained Language Models for Antibody Sequence Infilling
- Two-stream Network for ECG Signal Classification
- A review on Epileptic Seizure Detection using Machine Learning
- Digital twins of nonlinear dynamical systems
- Every word counts: A multilingual analysis of individual human alignment with model attention
- On Parallel or Distributed Asynchronous Iterations with Unbounded Delays and Possible Out of Order Messages or Flexible Communication for Convex Optimization Problems and Machine Learning
- Exploring Effectiveness of Explanations for Appropriate Trust: Lessons from Cognitive Psychology
- Trustworthy clinical AI solutions: a unified review of uncertainty quantification in deep learning models for medical image analysis
- Mesh-Tension Driven Expression-Based Wrinkles for Synthetic Faces
- Tractable Optimality in Episodic Latent MABs
- AlphaFold Distillation for Protein Design
- RankMe: Assessing the downstream performance of pretrained self-supervised representations by their rank
- Vision+X: A Survey on Multimodal Learning in the Light of Data
- Antibody Representation Learning for Drug Discovery
- Smooth Non-Rigid Shape Matching via Effective Dirichlet Energy Optimization
- Transferring dense object detection models to event-based data
- Spectral Regularization Allows Data-frugal Learning over Combinatorial Spaces
- From Threat Reports to Continuous Threat Intelligence: A Comparison of Attack Technique Extraction Methods from Textual Artifacts
- Exploration of A Self-Supervised Speech Model: A Study on Emotional Corpora
- CCC-wav2vec 2.0: Clustering aided Cross Contrastive Self-supervised learning of speech representations
- Star-Graph Multimodal Matching Component Analysis for Data Fusion and Transfer Learning
- Query The Agent: Improving sample efficiency through epistemic uncertainty estimation
- Functional Labeled Optimal Partitioning
- DigiFace-1M: 1 Million Digital Face Images for Face Recognition
- AOE-Net: Entities Interactions Modeling with Adaptive Attention Mechanism for Temporal Action Proposals Generation
- A Closer Look at Robustness to L-infinity and Spatial Perturbations and their Composition
- Reading Chinese in Natural Scenes with a Bag-of-Radicals Prior
- Privacy-Preserving Text Classification on BERT Embeddings with Homomorphic Encryption
- Efficient Learning of Mesh-Based Physical Simulation with BSMS-GNN
- Revisiting Structured Dropout
- Improved Anomaly Detection by Using the Attention-Based Isolation Forest
- Sample-and-Forward: Communication-Efficient Control of the False Discovery Rate in Networks
- Water Simulation and Rendering from a Still Photograph
- JoeyS2T: Minimalistic Speech-to-Text Modeling with JoeyNMT
- Deep learning for ECoG brain-computer interface: end-to-end vs. hand-crafted features
- Attention-based Ingredient Phrase Parser
- Towards Semi-automatic Detection and Localization of Indoor Accessibility Issues using Mobile Depth Scanning and Computer Vision
- Toward Knowledge-Driven Speech-Based Models of Depression: Leveraging Spectrotemporal Variations in Speech Vowels
- "No, they did not": Dialogue response dynamics in pre-trained language models
- Dual-Domain Cross-Iteration Squeeze-Excitation Network for Sparse Reconstruction of Brain MRI
- Equalizing Credit Opportunity in Algorithms: Aligning Algorithmic Fairness Research with U.S. Fair Lending Regulation
- TartanCalib: Iterative Wide-Angle Lens Calibration using Adaptive SubPixel Refinement of AprilTags
- Revisiting Syllables in Language Modelling and their Application on Low-Resource Machine Translation
- Large Language Models are Pretty Good Zero-Shot Video Game Bug Detectors
- A novel non-linear transformation based multi-user identification algorithm for fixed text keystroke behavioral dynamics
- On Adversarial Robustness of Deep Image Deblurring
- Honest Students from Untrusted Teachers: Learning an Interpretable Question-Answering Pipeline from a Pretrained Language Model
- Depth Is All You Need for Monocular 3D Detection
- Analyzing historical diagnosis code data from NIH N3C and RECOVER Programs using deep learning to determine risk factors for Long Covid
- Token Classification for Disambiguating Medical Abbreviations
- Fisher information lower bounds for sampling
- BaseTransformers: Attention over base data-points for One Shot Learning
- Learning from aggregated data with a maximum entropy model
- DEGAN: Time Series Anomaly Detection using Generative Adversarial Network Discriminators and Density Estimation
- TgDLF2.0: Theory-guided deep-learning for electrical load forecasting via Transformer and transfer learning
- Practical Adversarial Attacks on Spatiotemporal Traffic Forecasting Models
- Time Will Tell: New Outlooks and A Baseline for Temporal Multi-View 3D Object Detection
- Making Your First Choice: To Address Cold Start Problem in Vision Active Learning
- Ask Me Anything: A simple strategy for prompting language models
- Boundary-Aware Uncertainty for Feature Attribution Explainers
- A deep learning model for brain vessel segmentation in 3DRA with arteriovenous malformations
- A Fourier Approach to Mixture Learning
- GLM-130B: An Open Bilingual Pre-trained Model
- Why Random Pruning Is All We Need to Start Sparse
- Dynamical Isometry for Residual Networks
- The Vendi Score: A Diversity Evaluation Metric for Machine Learning
- The Influence of Explainable Artificial Intelligence: Nudging Behaviour or Boosting Capability?
- Decomposed Prompting: A Modular Approach for Solving Complex Tasks
- ciDATGAN: Conditional Inputs for Tabular GANs
- Medical Image Retrieval via Nearest Neighbor Search on Pre-trained Image Features
- Emotion Twenty Questions Dialog System for Lexical Emotional Intelligence
- Phenaki: Variable Length Video Generation From Open Domain Textual Description
- Temporally Consistent Transformers for Video Generation
- Geometry Driven Progressive Warping for One-Shot Face Animation
- Bayesian Prompt Learning for Image-Language Model Generalization
- NeuralMeshing: Differentiable Meshing of Implicit Neural Representations
- Goal Recognition as a Deep Learning Task: the GRNet Approach
- Dynamical systems' based neural networks
- Spatio-Temporal Learnable Proposals for End-to-End Video Object Detection
- SoccerNet 2022 Challenges Results
- Image Masking for Robust Self-Supervised Monocular Depth Estimation
All 204
- A kernel-based quantum random forest for improved classification
- Schema Encoding for Transferable Dialogue State Tracking
- Fitting a Directional Microstructure Model to Diffusion-Relaxation MRI Data with Self-Supervised Machine Learning
- Visual Backtracking Teleoperation: A Data Collection Protocol for Offline Image-Based Reinforcement Learning
- Particle clustering in turbulence: Prediction of spatial and statistical properties with deep learning
- Using Full-Text Content to Characterize and Identify Best Seller Books
- Revisiting Graph Contrastive Learning from the Perspective of Graph Spectrum
- Learning Across Domains and Devices: Style-Driven Source-Free Domain Adaptation in Clustered Federated Learning
- Promising or Elusive? Unsupervised Object Segmentation from Real-world Single Images
- FQDet: Fast-converging Query-based Detector
- Real-Time Reinforcement Learning for Vision-Based Robotics Utilizing Local and Remote Computers
- Multi-stream Fusion for Class Incremental Learning in Pill Image Classification
- SHINE-Mapping: Large-Scale 3D Mapping Using Sparse Hierarchical Implicit Neural Representations
- Multiclass Learnability Beyond the PAC Framework: Universal Rates and Partial Concept Classes
- Progressive Text-to-Image Generation
- TC-SKNet with GridMask for Low-complexity Classification of Acoustic scene
- Efficient probabilistic reconciliation of forecasts for real-valued and count time series
- Unsupervised Sentence Textual Similarity with Compositional Phrase Semantics
- Novel Radiomic Measurements of Tumor- Associated Vasculature Morphology on Clinical Imaging as a Biomarker of Treatment Response in Multiple Cancers
- Extending Conformal Prediction to Hidden Markov Models with Exact Validity via de Finetti's Theorem for Markov Chains
- Weak-shot Semantic Segmentation via Dual Similarity Transfer
- From Intelligent Agents to Trustworthy Human-Centred Multiagent Systems
- Cost Aware Asynchronous Multi-Agent Active Search
- Hiding Images in Deep Probabilistic Models
- Constant regret for sequence prediction with limited advice
- Granularity-aware Adaptation for Image Retrieval over Multiple Tasks
- HeartSpot: Privatized and Explainable Data Compression for Cardiomegaly Detection
- On Neural Consolidation for Transfer in Reinforcement Learning
- Over-the-Air Federated Learning with Privacy Protection via Correlated Additive Perturbations
- Thermal (and Hybrid Thermal/Audio) Side-Channel Attacks on Keyboard Input
- Decanus to Legatus: Synthetic training for 2D-3D human pose lifting
- Comprint: Image Forgery Detection and Localization using Compression Fingerprints
- Null Hypothesis Test for Anomaly Detection
- Neural Distillation as a State Representation Bottleneck in Reinforcement Learning
- CorefDiffs: Co-referential and Differential Knowledge Flow in Document Grounded Conversations
- Join, select, and insert: efficient out-of-core algorithms for hierarchical segmentation trees
- On the Statistical Complexity of Estimation and Testing under Privacy Constraints
- Game Theoretic Rating in N-player general-sum games with Equilibria
- PriorNet: lesion segmentation in PET-CT including prior tumor appearance information
- TimesNet: Temporal 2D-Variation Modeling for General Time Series Analysis
- Rediscovery of Numerical L"uscher's Formula from the Neural Network
- Multi-objective optimization via equivariant deep hypervolume approximation
- Feature Importance for Time Series Data: Improving KernelSHAP
- An Active Learning Reliability Method for Systems with Partially Defined Performance Functions
- Differentiable Mathematical Programming for Object-Centric Representation Learning
- The Influence of Learning Rule on Representation Dynamics in Wide Neural Networks
- Fine-Tuning with Differential Privacy Necessitates an Additional Hyperparameter Search
- Improving uplift model evaluation on RCT data
- Relational Proxies: Emergent Relationships as Fine-Grained Discriminators
- SECOE: Alleviating Sensors Failure in Machine Learning-Coupled IoT Systems
- Common Vulnerability Scoring System Prediction based on Open Source Intelligence Information Sources
- Decentralized Hyper-Gradient Computation over Time-Varying Directed Networks
- Stock Volatility Prediction using Time Series and Deep Learning Approach
- Development and validation of deep learning based embryo selection across multiple days of transfer
- ISFL: Federated Learning for Non-i.i.d. Data with Local Importance Sampling
- Optimization-Informed Neural Networks
- ChemAlgebra: Algebraic Reasoning on Chemical Reactions
- Centralized Feature Pyramid for Object Detection
- Functional Central Limit Theorem and Strong Law of Large Numbers for Stochastic Gradient Langevin Dynamics
- Tripletformer for Probabilistic Interpolation of Irregularly sampled Time Series
- Transformer-based conditional generative adversarial network for multivariate time series generation
- WUDA: Unsupervised Domain Adaptation Based on Weak Source Domain Labels
- Bilinear Exponential Family of MDPs: Frequentist Regret Bound with Tractable Exploration and Planning
- Multi-View Independent Component Analysis with Shared and Individual Sources
- Jitter Does Matter: Adapting Gaze Estimation to New Domains
- Locate before Answering: Answer Guided Question Localization for Video Question Answering
- Exploring The Role of Mean Teachers in Self-supervised Masked Auto-Encoders
- On the Learning Mechanisms in Physical Reasoning
- Two Video Data Sets for Tracking and Retrieval of Out of Distribution Objects
- Advanced Deep Learning Architectures for Accurate Detection of Subsurface Tile Drainage Pipes from Remote Sensing Images
- Non-Convergence and Limit Cycles in the Adam optimizer
- Nonparametric Decoding for Generative Retrieval
- Improving Sentiment Analysis By Emotion Lexicon Approach on Vietnamese Texts
- Graph Classification via Discriminative Edge Feature Learning
- Learning to Act: Novel Integration of Algorithms and Models for Epidemic Preparedness
- Coarse-to-Fine Point Cloud Registration with SE(3)-Equivariant Representations
- FedMT: Federated Learning with Mixed-type Labels
- Natural Color Fool: Towards Boosting Black-box Unrestricted Attacks
- GT-GAN: General Purpose Time Series Synthesis with Generative Adversarial Networks
- MOTSLAM: MOT-assisted monocular dynamic SLAM using single-view depth estimation
- Inharmonious Region Localization via Recurrent Self-Reasoning
- Clustering Semantic Predicates in the Open Research Knowledge Graph
- Learning Video-independent Eye Contact Segmentation from In-the-Wild Videos
- Point Cloud Recognition with Position-to-Structure Attention Transformers
- Inharmonious Region Localization with Auxiliary Style Feature
- GMMSeg: Gaussian Mixture based Generative Semantic Segmentation Models
- DreamShard: Generalizable Embedding Table Placement for Recommender Systems
- Exploring Effective Knowledge Transfer for Few-shot Object Detection
- Atari-5: Distilling the Arcade Learning Environment down to Five Games
- InterFace:Adjustable Angular Margin Inter-class Loss for Deep Face Recognition
- Multi-task Self-supervised Graph Neural Networks Enable Stronger Task Generalization
- Conformalized Fairness via Quantile Regression
- Multi-Camera Collaborative Depth Prediction via Consistent Structure Estimation
- WavSpA: Wavelet Space Attention for Boosting Transformers' Long Sequence Learning Ability
- ImpressLearn: Continual Learning via Combined Task Impressions
- MAtt: A Manifold Attention Network for EEG Decoding
- A Multi-Stage Automated Online Network Data Stream Analytics Framework for IIoT Systems
- Manipulation and Peer Mechanisms: A Survey
- Cloud removal Using Atmosphere Model
- GAPX: Generalized Autoregressive Paraphrase-Identification X
- Energy and Time Based Topology Control Approach to Enhance the Lifetime of WSN in an economic zone
- Towards Prototype-Based Self-Explainable Graph Neural Network
- The Calibration Generalization Gap
- COMPS: Conceptual Minimal Pair Sentences for testing Robust Property Knowledge and its Inheritance in Pre-trained Language Models