Papers
Thu 22 Dec 2022
130 papers
- Methodological reflections for AI alignment research using human feedbackLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
- When are Lemons Purple? The Concept Association Bias of Vision-Language ModelsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
- Scalable Adaptive Computation for Iterative GenerationDiffusion models → Video generation
- StoRM: A Diffusion-based Stochastic Regeneration Model for Speech Enhancement and DereverberationDiffusion models → Audio, speech and music
- Text Generation with Diffusion Language Models: A Pre-training Approach with Continuous Paragraph DenoiseDiffusion models → Discrete and text diffusion
- Tune-A-Video: One-Shot Tuning of Image Diffusion Models for Text-to-Video GenerationDiffusion models → Video generation
- CAMeMBERT: Cascading Assistant-Mediated Multilingual BERTKnowledge distillation → Knowledge distillation for LLMs
- A Review of Scene Representations for Robot Manipulators
- Creating awareness about security and safety on highways to mitigate wildlife-vehicle collisions by detecting and recognizing wildlife fences using deep learning and drone technology
- Exceeding Computational Complexity Trial-and-Error Dynamic Action and Intelligence
- Unsupervised learning for structure detection in plastically deformed crystals
- On Machine Learning Knowledge Representation In The Form Of Partially Unitary Operator. Knowledge Generalizing Operator
- Improving Convergence for Quantum Variational Classifiers using Weight Re-Mapping
- A Learned Simulation Environment to Model Student Engagement and Retention in Automated Online Courses
- A Local-Pattern Related Look-Up Table
- Cross-Dataset Propensity Estimation for Debiasing Recommender Systems
- Emotion Recognition with Pre-Trained Transformers Using Multimodal Signals
- Rapid Extraction of Respiratory Waveforms from Photoplethysmography: A Deep Encoder Approach
- Alignment Entropy Regularization
- Shakes on a Plane: Unsupervised Depth Estimation from Unstabilized Photography
- Infrared Image Super-Resolution: Systematic Review, and Future Trends
- Architecture and Knowledge Representation for Composable Inductive Programming
- A Topic Modeling Approach to Classifying Open Street Map Health Clinics and Schools in Sub-Saharan Africa
- RouteNet-Fermi: Network Modeling with Graph Neural Networks
- Enhancing the prediction of disease outcomes using electronic health records and pretrained deep learning models
- MN-DS: A Multilabeled News Dataset for News Articles Hierarchical Classification
- Semantically-consistent Landsat 8 image to Sentinel-2 image translation for alpine areas
- On Calibrating Semantic Segmentation Models: Analyses and An Algorithm
- Benchmarking Machine Learning Models to Predict Corporate Bankruptcy
- A Semantic Framework for Neuro-Symbolic Computing
- Pushing the performances of ASR models on English and Spanish accents
- Deep learning for size-agnostic inverse design of random-network 3D printed mechanical metamaterials
- Reduced-order autoregressive dynamics of a complex financial system: a PCA-based approach
- Re-basin via implicit Sinkhorn differentiation
- Graph Learning with Localized Neighborhood Fairness
- Deep Learning of Semi-Competing Risk Data via a New Neural Expectation-Maximization Algorithm
- Langevin algorithms for Markovian Neural Networks and Deep Stochastic control
- OPT-IML: Scaling Language Model Instruction Meta Learning through the Lens of Generalization
- Stochastic analysis of the Elo rating algorithm in round-robin tournaments
- Multi-Lingual DALL-E Storytime
- DisCoScene: Spatially Disentangled Generative Radiance Fields for Controllable 3D-aware Scene Synthesis
- A Wearable Data Collection System for Studying Micro-Level E-Scooter Behavior in Naturalistic Road Environment
- Removing Objects From Neural Radiance Fields
- Efficient Induction of Language Models Via Probabilistic Concept Formation
- Word Embedding Neural Networks to Advance Knee Osteoarthritis Research
- SupeRGB-D: Zero-shot Instance Segmentation in Cluttered Indoor Environments
- Beyond SOT: Tracking Multiple Generic Objects at Once
- Realizing Molecular Machine Learning through Communications for Biological AI: Future Directions and Challenges
- Machine Learning with Probabilistic Law Discovery: A Concise Introduction
- An Adaptive Simulated Annealing-Based Machine Learning Approach for Developing an E-Triage Tool for Hospital Emergency Operations
- Decoding surface codes with deep reinforcement learning and probabilistic policy reuse
- Parameter Inference based on Gaussian Processes Informed by Nonlinear Partial Differential Equations
- A Study of Left Before Treatment Complete Emergency Department Patients: An Optimized Explanatory Machine Learning Framework
- Impossibility Theorems for Feature Attribution
- Variational Reasoning over Incomplete Knowledge Graphs for Conversational Recommendation
- Multilingual News Location Detection using an Entity-Based Siamese Network with Semi-Supervised Contrastive Learning and Knowledge Base
- Data-Centric Artificial Intelligence
- Fully 3D Implementation of the End-to-end Deep Image Prior-based PET Image Reconstruction Using Block Iterative Algorithm
- The Quantum Path Kernel: a Generalized Quantum Neural Tangent Kernel for Deep Quantum Machine Learning
- Jamdani Motif Generation using Conditional GAN
- Renormalization in the neural network-quantum field theory correspondence
- GAN-based Domain Inference Attack
- BSAC-CoEx: Coexistence of URLLC and Distributed Learning Services via Device Selection
- Monocular 3D Object Detection using Multi-Stage Approaches with Attention and Slicing aided hyper inference
- EuclidNets: An Alternative Operation for Efficient Inference of Deep Learning Models
- Automatically Annotating Indoor Images with CAD Models via RGB-D Scans
- Training Integer-Only Deep Recurrent Neural Networks
- Adversarial Machine Learning and Defense Game for NextG Signal Classification with Deep Learning
- Fixed-budget online adaptive learning for physics-informed neural networks. Towards parameterized problem inference
- Few-shot human motion prediction for heterogeneous sensors
- S-Graphs+: Real-time Localization and Mapping leveraging Hierarchical Representations
- Aliasing is a Driver of Adversarial Attacks
- Mind Your Heart: Stealthy Backdoor Attack on Dynamic Deep Neural Network in Edge Computing
- Deep Simplex Classifier for Maximizing the Margin in Both Euclidean and Angular Spaces
- Certified Policy Smoothing for Cooperative Multi-Agent Reinforcement Learning
- Depth Estimation maps of lidar and stereo images
- Towards Sustainable Artificial Intelligence: An Overview of Environmental Protection Uses and Issues
- The State of the Art in Enhancing Trust in Machine Learning Models with the Use of Visualizations
- Time to Market Reduction for Hydrogen Fuel Cell Stacks using Generative Adversarial Networks
- TransPath: Learning Heuristics For Grid-Based Pathfinding via Transformers
- Federated Learning -- Methods, Applications and beyond
- Co-clustering based exploratory analysis of mixed-type data tables
- Reusable Options through Gradient-based Meta Learning
- Model Based Co-clustering of Mixed Numerical and Binary Data
- GOOD: Exploring Geometric Cues for Detecting Objects in an Open World
- Some recent advances in reasoning based on analogical proportions
- Reinforcement Learning Based Approaches to Adaptive Context Caching in Distributed Context Management Systems
- Robust Meta-Representation Learning via Global Label Inference and Classification
- Reversible Column Networks
- Timestamp-Supervised Action Segmentation from the Perspective of Clustering
- Set-Transformer BeamsNet for AUV Velocity Forecasting in Complete DVL Outage Scenarios
- Predictive Coding Based Multiscale Network with Encoder-Decoder LSTM for Video Prediction
- Towards Causal Credit Assignment
- Hybrid Quantum-Classical Generative Adversarial Network for High Resolution Image Generation
- DDColor: Towards Photo-Realistic Image Colorization via Dual Decoders
- Sequential Decision Problems with Weak Feedback
- Synopsis: Sequential Decision Problems with Weak Feedback
- Deformable Surface Reconstruction via Riemannian Metric Preservation
- Metadata-guided Consistency Learning for High Content Images
- TxAllo: Dynamic Transaction Allocation in Sharded Blockchain Systems
All 130
- DaDe: Delay-adaptive Detector for Streaming Perception
- Ultra-High-Definition Low-Light Image Enhancement: A Benchmark and Transformer-Based Method
- Mask Focal Loss: A unifying framework for dense crowd counting with canonical object detection networks
- Generative Colorization of Structured Mobile Web Pages
- SHLE: Devices Tracking and Depth Filtering for Stereo-based Height Limit Estimation
- Multi Lane Detection
- AsyncFLEO: Asynchronous Federated Learning for LEO Satellite Constellations with High-Altitude Platforms
- Mean-field neural networks-based algorithms for McKean-Vlasov control problems *
- Co-evolving morphology and control of soft robots using a single genome
- Confidence-Aware Paced-Curriculum Learning by Label Smoothing for Surgical Scene Understanding
- Supervised Anomaly Detection Method Combining Generative Adversarial Networks and Three-Dimensional Data in Vehicle Inspections
- Accelerating Barnes-Hut t-SNE Algorithm by Efficient Parallelization on Multi-Core CPUs
- Group Sparse Coding for Image Denoising
- Scalable Multi-Agent Reinforcement Learning for Warehouse Logistics with Robotic and Human Co-Workers
- Understanding and Improving the Role of Projection Head in Self-Supervised Learning
- SALVE: Self-supervised Adaptive Low-light Video Enhancement
- Learning to swim efficiently in a nonuniform flow field
- A Mathematical Framework for Learning Probability Distributions
- Spatio-Visual Fusion-Based Person Re-Identification for Overhead Fisheye Images
- Restoring Vision in Hazy Weather with Hierarchical Contrastive Learning
- Multi-queue Momentum Contrast for Microvideo-Product Retrieval
- IPProtect: protecting the intellectual property of visual datasets during data valuation
- Understanding Postpartum Parents' Experiences via Two Digital Platforms
- Vision-Based Environmental Perception for Autonomous Driving
- A machine learning framework for neighbor generation in metaheuristic search
- Commitment with Signaling under Double-sided Information Asymmetry
- Offline Clustering Approach to Self-supervised Learning for Class-imbalanced Image Data
- Novel Deep Learning Framework For Bovine Iris Segmentation
- Local Policy Improvement for Recommender Systems
- Automatically Bounding the Taylor Remainder Series: Tighter Bounds and New Applications