Papers
Mon 1 May 2023
129 papers
- In-Context Learning Unlocked for Diffusion ModelsDiffusion models → Image generation, text-to-image and editing
- CLIP-S4: Language-Guided Self-Supervised Semantic SegmentationMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
- Evaluating statistical language models as pragmatic reasonersLLM reasoning → Reasoning benchmarks and evaluation
- Bridging the Gap: A Survey on Integrating (Human) Feedback for Natural Language GenerationLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
- Explanation through Reward Model Reconciliation using POMDP Tree SearchLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
- Learning to Reason and Memorize with Self-NotesLLM reasoning → Reasoning benchmarks and evaluation
- Self-Evaluation Guided Beam Search for ReasoningLLM reasoning → Test-time compute and efficient thinking
- Diffusion Models for Time Series Applications: A SurveyDiffusion models → Flow matching, time series and science
- 3D Molecular Geometry Analysis with 2D Graphs
- MARS: Mask Attention Refinement with Sequential Quadtree Nodes for Car Damage Instance Segmentation
- Correlation-Driven Multi-Level Multimodal Learning for Anomaly Detection on Multiple Energy Sources
- On the stability test for reproducing kernel Hilbert spaces
- Deep Graph Representation Learning and Optimization for Influence Maximization
- Scalable Data Point Valuation in Decentralized Learning
- Probabilistic Formal Modelling to Uncover and Interpret Interaction Styles
- Predicting blood pressure under circumstances of missing data: An analysis of missing data patterns and imputation methods using NHANES
- Augmented Electronic Ising Machine as an Effective SAT Solver
- BCEdge: SLO-Aware DNN Inference Services with Adaptive Batching on Edge Platforms
- A Parameter-free Adaptive Resonance Theory-based Topological Clustering Algorithm Capable of Continual Learning
- Cancer-inspired Genomics Mapper Model for the Generation of Synthetic DNA Sequences with Desired Genomics Signatures
- Efficient Sensitivity Analysis for Parametric Robust Markov Chains
- Human adaptation to adaptive machines converges to game-theoretic equilibria
- Learning Controllable Adaptive Simulation for Multi-resolution Physics
- CSP: Self-Supervised Contrastive Spatial Pre-Training for Geospatial-Visual Representations
- Local and Global Contextual Features Fusion for Pedestrian Intention Prediction
- Leveraging Language Representation for Material Recommendation, Ranking, and Exploration
- Logion: Machine Learning for Greek Philology
- A Novel Model for Driver Lane Change Prediction in Cooperative Adaptive Cruise Control Systems
- LSTM-based Preceding Vehicle Behaviour Prediction during Aggressive Lane Change for ACC Application
- Performative Prediction with Bandit Feedback: Learning through Reparameterization
- Autoencoders for discovering manifold dimension and coordinates in data from complex dynamical systems
- Computing Expected Motif Counts for Exchangeable Graph Generative Models
- AI & Blockchain as sustainable teaching and learning tools to cope with the 4IR
- Contextual Multilingual Spellchecker for User Queries
- Bird Distribution Modelling using Remote Sensing and Citizen Science data
- Physical Adversarial Attacks for Surveillance: A Survey
- Personalized Federated Learning under Mixture of Distributions
- semantic neural model approach for face recognition from sketch
- LooPy: A Research-Friendly Mix Framework for Music Information Retrieval on Electronic Dance Music
- SafeWebUH at SemEval-2023 Task 11: Learning Annotator Disagreement in Derogatory Text: Comparison of Direct Training vs Aggregation
- Venn Diagram Multi-label Class Interpretation of Diabetic Foot Ulcer with Color and Sharpness Enhancement
- Model-agnostic Measure of Generalization Difficulty
- Company classification using zero-shot learning
- Synthetic Data for Face Recognition: Current State and Future Prospects
- Deception Detection with Feature-Augmentation by soft Domain Transfer
- Towards a Phenomenological Understanding of Neural Networks: Data
- A novel algorithm can generate data to train machine learning models in conditions of extreme scarcity of real world data
- Meat Freshness Prediction
- Attention-based Spatial-Temporal Graph Neural ODE for Traffic Prediction
- Ternary Instantaneous Noise-based Logic
- ArK: Augmented Reality with Knowledge Interactive Emergent Ability
- CryCeleb: A Speaker Verification Dataset Based on Infant Cry Sounds
- A Spectral Algorithm for List-Decodable Covariance Estimation in Relative Frobenius Norm
- Probabilistic 3D segmentation for aleatoric uncertainty quantification in full 3D medical data
- Large Linguistic Models: Investigating LLMs' metalinguistic abilities
- Poisoning Language Models During Instruction Tuning
- StyleAvatar: Real-time Photo-realistic Portrait Avatar from a Single Video
- Generating Texture for 3D Human Avatar from a Single Image using Sampling and Refinement Networks
- Variational Inference for Bayesian Neural Networks under Model and Parameter Uncertainty
- A comparison of short-term probabilistic forecasts for the incidence of COVID-19 using mechanistic and statistical time series models
- Cross-Institutional Transfer Learning for Educational Models: Implications for Model Performance, Fairness, and Equity
- Joint Modelling of Spoken Language Understanding Tasks with Integrated Dialog History
- IoTFlowGenerator: Crafting Synthetic IoT Device Traffic Flows for Cyber Deception
- Early Detection of Alzheimer's Disease using Bottleneck Transformers
- The Impact of the Geometric Properties of the Constraint Set in Safe Optimization with Bandit Feedback
- Exactly Tight Information-Theoretic Generalization Error Bound for the Quadratic Gaussian Problem
- Redundancy and Concept Analysis for Code-trained Language Models
- Towards the Flatter Landscape and Better Generalization in Federated Learning under Client-level Differential Privacy
- Estimating the Density Ratio between Distributions with High Discrepancy using Multinomial Logistic Regression
- Attack-SAM: Towards Attacking Segment Anything Model With Adversarial Examples
- Revisiting Robustness in Graph Machine Learning
- Automated Paper Screening for Clinical Reviews Using Large Language Models
- Strategic Resource Selection with Homophilic Agents
- LCAUnet: A skin lesion segmentation network with enhanced edge and body fusion
- First- and Second-Order Bounds for Adversarial Linear Contextual Bandits
- Racial Bias within Face Recognition: A Survey
- Neurosymbolic AI -- Why, What, and How
- Interpreting Deep Forest through Feature Contribution and MDI Feature Importance
- Performance and Energy Consumption of Parallel Machine Learning Algorithms
- SelfDocSeg: A Self-Supervised vision-based Approach towards Document Segmentation
- GeneFace++: Generalized and Stable Real-Time Audio-Driven 3D Talking Face Generation
- AI-based Radio and Computing Resource Allocation and Path Planning in NOMA NTNs: AoI Minimization under CSI Uncertainty
- Point Cloud Semantic Segmentation
- Towards Unbiased Training in Federated Open-world Semi-supervised Learning
- Multi-scale Transformer-based Network for Emotion Recognition from Multi Physiological Signals
- Heterogeneous Social Value Orientation Leads to Meaningful Diversity in Sequential Social Dilemmas
- RViDeformer: Efficient Raw Video Denoising Transformer with a Larger Benchmark Dataset
- FCA: Taming Long-tailed Federated Medical Image Classification by Classifier Anchoring
- Unsupervised anomaly detection algorithms on real-world data: how many do we need?
- What Do Self-Supervised Vision Transformers Learn?
- Strengthening structural baselines for graph classification using Local Topological Profile
- Predictions Based on Pixel Data: Insights from PDEs and Finite Differences
- Event Camera as Region Proposal Network
- Adaptively Topological Tensor Network for Multi-view Subspace Clustering
- ZeroSearch: Local Image Search from Text with Zero Shot Learning
- Full Scaling Automation for Sustainable Development of Green Data Centers
- Double and Single Descent in Causal Inference with an Application to High-Dimensional Synthetic Control
- TPMIL: Trainable Prototype Enhanced Multiple Instance Learning for Whole Slide Image Classification
- Joint tone mapping and denoising of thermal infrared images via multi-scale Retinex and multi-task learning
- On the Complexity of Multi-Agent Decision Making: From Learning in Games to Partial Monitoring
All 129
- Enhanced Multi-level Features for Very High Resolution Remote Sensing Scene Classification
- Rethinking Boundary Detection in Deep Learning Models for Medical Image Segmentation
- Robustified Learning for Online Optimization with Memory Costs
- Learning Terrain-Aware Kinodynamic Model for Autonomous Off-Road Rally Driving With Model Predictive Path Integral Control
- End-to-End Lane detection with One-to-Several Transformer
- Bidirectional Copy-Paste for Semi-Supervised Medical Image Segmentation
- PRSeg: A Lightweight Patch Rotate MLP Decoder for Semantic Segmentation
- Reservoir Computing with Error Correction: Long-term Behaviors of Stochastic Dynamical Systems
- Part Aware Contrastive Learning for Self-Supervised Action Recognition
- EvoluNet: Advancing Dynamic Non-IID Transfer Learning on Graphs
- Activation Functions Not To Active: A Plausible Theory on Interpreting Neural Networks
- An Iterative Algorithm for Rescaled Hyperbolic Functions Regression
- Representations and Exploration for Deep Reinforcement Learning using Singular Value Decomposition
- Discover and Cure: Concept-aware Mitigation of Spurious Correlation
- Overcoming the Trade-off Between Accuracy and Plausibility in 3D Hand Shape Reconstruction
- Procedural Content Generation via Knowledge Transformation (PCG-KT)
- Inferring the past: a combined CNN-LSTM deep learning framework to fuse satellites for historical inundation mapping
- Learning Self-Prior for Mesh Inpainting Using Self-Supervised Graph Convolutional Networks
- TRACE: Table Reconstruction Aligned to Corner and Edges
- CNN-based fully automatic mitral valve extraction using CT images and existence probability maps
- A Simplified Framework for Contrastive Learning for Node Representations
- Proper Scoring Rules for Survival Analysis
- Refined Response Distillation for Class-Incremental Player Detection
- Self-supervised Activity Representation Learning with Incremental Data: An Empirical Study
- Differentiable Neural Networks with RePU Activation: with Applications to Score Estimation and Isotonic Regression
- Boosting Weakly-Supervised Temporal Action Localization with Text Information
- Low-Resourced Machine Translation for Senegalese Wolof Language
- Classification and Online Clustering of Zero-Day Malware
- ISAAC Newton: Input-based Approximate Curvature for Newton's Method