Papers
Mon 16 Jan 2023
94 papers
- Dissociating language and thought in large language modelsLLM reasoning → Reasoning benchmarks and evaluation
- UATVR: Uncertainty-Adaptive Text-Video RetrievalMultimodal LLMs / vision-language models → Video understanding with MLLMs
- Neuro-Symbolic World Models for Adapting to Open World NoveltyWorld models → Latent dynamics models and model-based RL
- Monocular Cyclist Detection with Convolutional Neural Networks
- BayesSpeech: A Bayesian Transformer Network for Automatic Speech Recognition
- Bayesian Detection of Mesoscale Structures in Pathway Data on Graphs
- Digital Twins for Marine Operations: A Brief Review on Their Implementation
- Estimating the energy requirements for long term memory formation
- Dual Personalization on Federated Recommendation
- Fully Elman Neural Network: A Novel Deep Recurrent Neural Network Optimized by an Improved Harris Hawks Algorithm for Classification of Pulmonary Arterial Wedge Pressure
- EHRSQL: A Practical Text-to-SQL Benchmark for Electronic Health Records
- Optimization Algorithms in Smart Grids: A Systematic Literature Review
- Multimodal Side-Tuning for Document Classification
- A Robust Classification Framework for Byzantine-Resilient Stochastic Gradient Descent
- Machine learning techniques for the Schizophrenia diagnosis: A comprehensive review and future research directions
- Large Deviations for Classification Performance Analysis of Machine Learning Systems
- Continuous Trajectory Generation Based on Two-Stage GAN
- On Using Deep Learning Proxies as Forward Models in Deep Learning Problems
- Data-aware customization of activation functions reduces neural network error
- Ae2I: A Double Autoencoder for Imputation of Missing Values
- Asymptotic normality and optimality in nonsmooth stochastic approximation
- Diverse Multimedia Layout Generation with Multi Choice Learning
- Masked Vector Quantization
- A Transformer-based Diffusion Probabilistic Model for Heart Rate and Blood Pressure Forecasting in Intensive Care Unit
- TAAL: Test-time Augmentation for Active Learning in Medical Image Segmentation
- ClassBases at CASE-2022 Multilingual Protest Event Detection Tasks: Multilingual Protest News Detection and Automatically Replicating Manually Created Event Datasets
- Data-Driven Estimation of Heterogeneous Treatment Effects
- PromptShots at the FinNLP-2022 ERAI Tasks: Pairwise Comparison and Unsupervised Ranking
- TEDB System Description to a Shared Task on Euphemism Detection 2022
- Antenna Array Calibration Via Gaussian Process Models
- Learning from Very Little Data: On the Value of Landscape Analysis for Predicting Software Project Health
- Improving the Bootstrap of Blind Equalizers with Variational Autoencoders
- Causal Recurrent Variational Autoencoder for Medical Time Series Generation
- Cross-institution text mining to uncover clinical associations: a case study relating social factors and code status in intensive care medicine
- Ankh: Optimized Protein Language Model Unlocks General-Purpose Modelling
- Scalable Surface Water Mapping up to Fine-scale using Geometric Features of Water from Topographic Airborne LiDAR Data
- Error-related Potential Variability: Exploring the Effects on Classification and Transferability
- Distinguish Sense from Nonsense: Out-of-Scope Detection for Virtual Assistants
- Data-Driven Encoding: A New Numerical Method for Computation of the Koopman Operator
- Case-Base Neural Networks: survival analysis with time-varying, higher-order interactions
- Intrinsic Gaussian Process on Unknown Manifolds with Probabilistic Metrics
- XNLI 2.0: Improving XNLI dataset and performance on Cross Lingual Understanding (XLU)
- Efficient data transport over multimode light-pipes with Megapixel images using differentiable ray tracing and Machine-learning
- CRYPTEXT: Database and Interactive Toolkit of Human-Written Text Perturbations in the Wild
- Simplex Autoencoders
- Using Kaldi for Automatic Speech Recognition of Conversational Austrian German
- Towards an Automatic Consolidation of French Law
- Msanii: High Fidelity Music Synthesis on a Shoestring Budget
- PlasmoFAB: A Benchmark to Foster Machine Learning for Plasmodium falciparum Protein Antigen Candidate Prediction
- HiFlash: Communication-Efficient Hierarchical Federated Learning with Adaptive Staleness Control and Heterogeneity-aware Client-Edge Association
- Sparse resultant based minimal solvers in computer vision and their connection with the action matrix
- Modeling Uncertain Feature Representation for Domain Generalization
- Linguistic Query-Guided Mask Generation for Referring Image Segmentation
- Faster Gradient-Free Algorithms for Nonsmooth Nonconvex Stochastic Optimization
- AI Alignment Dialogues: An Interactive Approach to AI Alignment in Support Agents
- Mind the Gap: Modelling Difference Between Censored and Uncensored Electric Vehicle Charging Demand
- Enforcing Privacy in Distributed Learning with Performance Guarantees
- Opening up Minds with Argumentative Dialogues
- β-DARTS++: Bi-level Regularization for Proxy-robust Differentiable Architecture Search
- I See-Through You: A Framework for Removing Foreground Occlusion in Both Sparse and Dense Light Field Images
- PECAN: Leveraging Policy Ensemble for Context-Aware Zero-Shot Human-AI Coordination
- OLKAVS: An Open Large-Scale Korean Audio-Visual Speech Dataset
- Disambiguation of One-Shot Visual Classification Tasks: A Simplex-Based Approach
- Evaluating clinical diversity and plausibility of synthetic capsule endoscopic images
- A2-UAV: Application-Aware Content and Network Optimization of Edge-Assisted UAV Systems
- Post-Train Adaptive U-Net for Image Segmentation
- PyExperimenter: Easily distribute experiments and track results
- Deep Learning Models to Study Sentence Comprehension in the Human Brain
- Approximation of optimization problems with constraints through kernel Sum-Of-Squares
- Hybrid quantum-classical convolutional neural networks to improve molecular protein binding affinity predictions
- Img2Tab: Automatic Class Relevant Concept Discovery from StyleGAN Features for Explainable Image Classification
- An Error-Guided Correction Model for Chinese Spelling Error Correction
- Stability Analysis of Sharpness-Aware Minimization
- LYSTO: The Lymphocyte Assessment Hackathon and Benchmark Dataset
- Sensor data-driven analysis for identification of causal relationships between exposure to air pollution and respiratory rate in asthmatics
- Inference via robust optimal transportation: theory and methods
- Representation Learning for Tablet and Paper Domain Adaptation in Favor of Online Handwriting Recognition
- Meta Generative Attack on Person Reidentification
- DPE: Disentanglement of Pose and Expression for General Video Portrait Editing
- Improving Target Speaker Extraction with Sparse LDA-transformed Speaker Embeddings
- The Role of Baselines in Policy Gradient Optimization
- Computational Assessment of Hyperpartisanship in News Titles
- DarkVision: A Benchmark for Low-light Image/Video Perception
- Multimodality Helps Unimodality: Cross-Modal Few-Shot Learning with Multimodal Models
- Adaptive Depth Graph Attention Networks
- Collaborative Perception in Autonomous Driving: Methods, Datasets and Challenges
- Understanding Best Subset Selection: A Tale of Two C(omplex)ities
- Machine Learning-Aided Efficient Decoding of Reed-Muller Subcodes
- BEAGLE: Forensics of Deep Learning Backdoor Attack for Better Defense
- Kernel-based off-policy estimation without overlap: Instance optimality beyond semiparametric efficiency
- A separation logic for sequences in pointer programs and its decidability
- Swarm-SLAM : Sparse Decentralized Collaborative Simultaneous Localization and Mapping Framework for Multi-Robot Systems
- Novelty Detection in Network Traffic: Using Survival Analysis for Feature Identification
- Deep Learning based Novel Cascaded Approach for Skin Lesion Analysis