Papers
Thu 15 Dec 2022
181 papers
- Membership Inference Attacks Against Latent Factor ModelLLM safety and security → Membership inference attacks
- Improving Chess Commentaries by Combining Language Models with Symbolic Reasoning EnginesLLM reasoning → Reasoning for agents, planning and code
- FiDO: Fusion-in-Decoder optimized for stronger performance and faster inferenceRetrieval-augmented generation → Generation and context integration
- Bridging the Gap Between Offline and Online Reinforcement Learning Evaluation MethodologiesOffline RL and imitation learning from data → Offline RL algorithms
- Constitutional AI: Harmlessness from AI FeedbackLLM reasoning → Reinforcement learning for reasoning +1
- Mod-Squad: Designing Mixture of Experts As Modular Multi-Task LearnersMixture-of-experts → Mixture of LoRA experts
- On Second Thought, Let's Not Think Step by Step! Bias and Toxicity in Zero-Shot ReasoningLLM reasoning → Prompting and chain-of-thought reasoning
- Generating Realistic Brain MRIs via a Conditional Diffusion Probabilistic ModelDiffusion models → Medical imaging and segmentation
- ROSCOE: A Suite of Metrics for Scoring Step-by-Step ReasoningLLM reasoning → Reasoning benchmarks and evaluation
- TeTIm-Eval: a novel curated evaluation data set for comparing text-to-image modelsDiffusion models → Image generation, text-to-image and editing
- Gradient-based Intra-attention Pruning on Pre-trained Language ModelsKnowledge distillation → Knowledge distillation for LLMs
- Universal Generative Modeling in Dual-domain for Dynamic MR ImagingDiffusion models → Medical imaging and segmentation
- Driver Assistance Eco-driving and Transmission Control with Deep Reinforcement LearningEnd-to-end autonomous driving → Cooperative and V2X driving
- Fixing MoE Over-Fitting on Low-Resource Languages in Multilingual Machine TranslationMixture-of-experts → MoE large language models
- Scaffold-Based Multi-Objective Drug Candidate Optimization
- White-box Inference Attacks against Centralized Machine Learning and Federated Learning
- Deep leakage from gradients
- Ring That Bell: A Corpus and Method for Multimodal Metaphor Detection in Videos
- A new weighted ensemble model for phishing detection based on feature selection
- Holistic risk assessment of inference attacks in machine learning
- Measuring Annotator Agreement Generally across Complex Structured, Multi-object, and Free-text Annotation Tasks
- NAWQ-SR: A Hybrid-Precision NPU Engine for Efficient On-Device Super-Resolution
- Exploring Tradeoffs in Spiking Neural Networks
- Learning Inter-Annual Flood Loss Risk Models From Historical Flood Insurance Claims and Extreme Rainfall Data
- Statistical Design and Analysis for Robust Machine Learning: A Case Study from COVID-19
- Audio-based AI classifiers show no evidence of improved COVID-19 screening over simple symptoms checkers
- Optimized Symbolic Interval Propagation for Neural Network Verification
- Neural Network Augmented Compartmental Pandemic Models
- SteerNeRF: Accelerating NeRF Rendering via Smooth Viewpoint Trajectory
- Best-Answer Prediction in Q&A Sites Using User Information
- Asymptotic Analysis of Deep Residual Networks
- Saved You A Click: Automatically Answering Clickbait Titles
- The KITMUS Test: Evaluating Knowledge Integration from Multiple Sources in Natural Language Understanding Systems
- Multi-Resolution Online Deterministic Annealing: A Hierarchical and Progressive Learning Architecture
- Dual Moving Average Pseudo-Labeling for Source-Free Inductive Domain Adaptation
- Learning Sparsity and Randomness for Data-driven Low Rank Approximation
- NBC-Softmax : Darkweb Author fingerprinting and migration tracking
- Local Branching Relaxation Heuristics for Integer Linear Programs
- Non-IID Transfer Learning on Graphs
- Reliable Measures of Spread in High Dimensional Latent Spaces
- Graphon Pooling for Reducing Dimensionality of Signals and Convolutional Operators on Graphs
- BNSynth: Bounded Boolean Functional Synthesis
- Huber-energy measure quantization
- MM-SHAP: A Performance-agnostic Metric for Measuring Multimodal Contributions in Vision and Language Models & Tasks
- First De-Trend then Attend: Rethinking Attention for Time-Series Forecasting
- Efficient Long Sequence Modeling via State Space Augmented Transformer
- On Evaluating Adversarial Robustness of Chest X-ray Classification: Pitfalls and Best Practices
- Bayesian posterior approximation with stochastic ensembles
- Backdoor Attack Detection in Computer Vision by Applying Matrix Factorization on the Weights of Deep Networks
- Injecting Domain Knowledge in Language Models for Task-Oriented Dialogue Systems
- An Empirical Study of Deep Learning Models for Vulnerability Detection
- Dataflow Analysis-Inspired Deep Learning for Efficient Vulnerability Detection
- Learning to repeatedly solve routing problems
- Joint processing of linguistic properties in brains and language models
- MAViL: Masked Audio-Video Learners
- NeRF-Art: Text-Driven Neural Radiance Fields Stylization
- VolRecon: Volume Rendering of Signed Ray Distance Functions for Generalizable Multi-View Reconstruction
- MetaPortrait: Identity-Preserving Talking Head Generation with Fast Personalized Adaptation
- Rethinking Vision Transformers for MobileNet Size and Speed
- Learning a Fast 3D Spectral Approach to Object Segmentation and Tracking over Space and Time
- Real-Time Neural Light Field on Mobile Devices
- UnitY: Two-pass Direct Speech-to-speech Translation with Discrete Units
- DAMP: Doubly Aligned Multilingual Parser for Task-Oriented Dialogue
- Objaverse: A Universe of Annotated 3D Objects
- Sliced Optimal Partial Transport
- Silhouette: Toward Performance-Conscious and Transferable CPU Embeddings
- CLIPPO: Image-and-Language Understanding from Pixels Only
- Benchmarking Robustness of Multimodal Image-Text Models under Distribution Shift
- Attributed Question Answering: Evaluation and Modeling for Attributed Large Language Models
- Demonstration of machine-learning-enhanced Bayesian quantum state estimation
- Privately Estimating a Gaussian: Efficient, Robust and Optimal
- FlexiViT: One Model for All Patch Sizes
- Multi-VALUE: A Framework for Cross-Dialectal English NLP
- A New Deep Boosted CNN and Ensemble Learning based IoT Malware Detection
- Rollout Algorithms and Approximate Dynamic Programming for Bayesian Optimization and Sequential Estimation
- Online Handbook of Argumentation for AI: Volume 3
- Alternating Objectives Generates Stronger PGD-Based Adversarial Attacks
- Vision Transformers are Parameter-Efficient Audio-Visual Learners
- Revisiting the Gold Standard: Grounding Summarization Evaluation with Robust Human Evaluation
- Distributed-Training-and-Execution Multi-Agent Reinforcement Learning for Power Control in HetNet
- Scalable Bayesian Uncertainty Quantification for Neural Network Potentials: Promise and Pitfalls
- A Data Source Dependency Analysis Framework for Large Scale Data Science Projects
- Active Inference and Reinforcement Learning: A unified inference on continuous state and action spaces under partial observability
- Variable Clustering via Distributionally Robust Nodewise Regression
- RWEN-TTS: Relation-aware Word Encoding Network for Natural Text-to-Speech Synthesis
- Visually-augmented pretrained language models for NLP tasks without images
- A Study on the Intersection of GPU Utilization and CNN Inference
- Bridging POMDPs and Bayesian decision making for robust maintenance planning under model uncertainty: An application to railway systems
- The Effects of Character-Level Data Augmentation on Style-Based Dating of Historical Manuscripts
- Construction of a Surrogate Model: Multivariate Time Series Prediction with a Hybrid Model
- The Effects of In-domain Corpus Size on pre-training BERT
- Urban Scene Semantic Segmentation with Low-Cost Coarse Annotation
- Automatic vehicle trajectory data reconstruction at scale
- EVAL: Explainable Video Anomaly Localization
- Integrating Multimodal Data for Joint Generative Modeling of Complex Dynamics
- Emergent Behaviors in Multi-Agent Target Acquisition
- Full Contextual Attention for Multi-resolution Transformers in Semantic Segmentation
- Meta-Learned Kernel For Blind Super-Resolution Kernel Estimation
- Identifying AGN host galaxies with convolutional neural networks
- Manifestations of Xenophobia in AI Systems
All 181
- Forgetful Forests: high performance learning data structures for streaming data under concept drift
- Localizing Scan Targets from Human Pose for Autonomous Lung Ultrasound Imaging
- Multi-Level Association Rule Mining for Wireless Network Time Series Data
- QueryPose: Sparse Multi-Person Pose Regression via Spatial-Aware Part-Level Query
- The effects of gender bias in word embeddings on depression prediction
- Attention as a Guide for Simultaneous Speech Translation
- DETR4D: Direct Multi-View 3D Object Detection with Sparse Attention
- Differentiating Nonsmooth Solutions to Parametric Monotone Inclusion Problems
- Realistic Synthetic Social Networks with Graph Neural Networks
- MASTER: Multi-task Pre-trained Bottlenecked Masked Autoencoders are Better Dense Retrievers
- Spatially-resolved Thermometry from Line-of-Sight Emission Spectroscopy via Machine Learning
- Unsupervised Object Localization: Observing the Background to Discover Objects
- Hybrid Quantum Generative Adversarial Networks for Molecular Simulation and Drug Discovery
- Towards Hardware-Specific Automatic Compression of Neural Networks
- DUIDD: Deep-Unfolded Interleaved Detection and Decoding for MIMO Wireless Systems
- Chaotic Variational Auto Encoder based One Class Classifier for Insurance Fraud Detection
- Efficient Visual Computing with Camera RAW Snapshots
- Enhancing Indic Handwritten Text Recognition Using Global Semantic Information
- Calibrating AI Models for Wireless Communications via Conformal Prediction
- Runtime Monitoring for Out-of-Distribution Detection in Object Detection Neural Networks
- Temporal Saliency Detection Towards Explainable Transformer-based Timeseries Forecasting
- CLAM: Selective Clarification for Ambiguous Questions with Generative Language Models
- A scalable framework for annotating photovoltaic cell defects in electroluminescence images
- COLA: Improving Conversational Recommender Systems by Collaborative Augmentation
- DeepLSD: Line Segment Detection and Refinement with Deep Image Gradients
- Spatial-Temporal Anomaly Detection for Sensor Attacks in Autonomous Vehicles
- Event-based Visual Tracking in Dynamic Environments
- Advancing Multilingual Pre-training: TRIP Triangular Document-level Pre-training for Multilingual Language Models
- Combating Uncertainty and Class Imbalance in Facial Expression Recognition
- Interpretable ML for Imbalanced Data
- Sim-to-Real Transfer for Quadrupedal Locomotion via Terrain Transformer
- A large-scale and PCR-referenced vocal audio dataset for COVID-19
- HUM3DIL: Semi-supervised Multi-modal 3D Human Pose Estimation for Autonomous Driving
- Attention-based Multiple Instance Learning for Survival Prediction on Lung Cancer Tissue Microarrays
- Physics-Informed Neural Networks for Material Model Calibration from Full-Field Displacement Data
- Deep Learning-Based Automatic Assessment of AgNOR-scores in Histopathology Images
- FreCDo: A Large Corpus for French Cross-Domain Dialect Identification
- Colab NAS: Obtaining lightweight task-specific convolutional neural networks following Occam's razor
- Retrieval-based Disentangled Representation Learning with Natural Language Supervision
- CNN-based real-time 2D-3D deformable registration from a single X-ray projection
- Anomaly Detection in Driving by Cluster Analysis Twice
- Multi-Agent Reinforcement Learning with Shared Resources for Inventory Management
- Transformers learn in-context by gradient descent
- Summary-Oriented Vision Modeling for Multimodal Abstractive Summarization
- Multi-task Fusion for Efficient Panoptic-Part Segmentation
- Using Two Losses and Two Datasets Simultaneously to Improve TempoWiC Accuracy
- Writer Retrieval and Writer Identification in Greek Papyri
- Interpolation with the polynomial kernels
- Body-Part Joint Detection and Association via Extended Object Representation
- Two-stage Contextual Transformer-based Convolutional Neural Network for Airway Extraction from CT Images
- Improve Text Classification Accuracy with Intent Information
- Relightable Neural Human Assets from Multi-view Gradient Illuminations
- Adaptive Multi-Agent Continuous Learning System
- Let's consider more general nonlinear approaches to study teleconnections of climate variables
- Reinforcement Learning in Credit Scoring and Underwriting
- EM-Paste: EM-guided Cut-Paste with DALL-E Augmentation for Image-level Weakly Supervised Instance Segmentation
- NeuralDome: A Neural Modeling Pipeline on Multi-View Human-Object Interactions
- Neuroevolution of Physics-Informed Neural Nets: Benchmark Problems and Comparative Results
- SBSS: Stacking-Based Semantic Segmentation Framework for Very High Resolution Remote Sensing Image
- Curriculum Learning Meets Weakly Supervised Modality Correlation Learning
- Proposal Distribution Calibration for Few-Shot Object Detection
- Efficient Pre-training of Masked Language Model via Concept-based Curriculum Masking
- DCS-RISR: Dynamic Channel Splitting for Efficient Real-world Image Super-Resolution
- Residual Policy Learning for Powertrain Control
- Output-Dependent Gaussian Process State-Space Model
- Text-Guided Mask-free Local Image Retouching
- Enhanced Training of Query-Based Object Detection via Selective Query Recollection
- Solve the Puzzle of Instance Segmentation in Videos: A Weakly Supervised Framework with Spatio-Temporal Collaboration
- Dissecting Distribution Inference
- DeepJoin: Joinable Table Discovery with Pre-trained Language Models
- Rethinking the Role of Pre-Trained Networks in Source-Free Domain Adaptation
- Edema Estimation From Facial Images Taken Before and After Dialysis via Contrastive Multi-Patient Pre-Training
- Learning to Detect Semantic Boundaries with Image-level Class Labels
- Evaluation of direct attacks to fingerprint verification systems
- Man-recon: manifold learning for reconstruction with deep autoencoder for smart seismic interpretation
- Learning Markerless Robot-Depth Camera Calibration and End-Effector Pose Estimation
- AirfRANS: High Fidelity Computational Fluid Dynamics Dataset for Approximating Reynolds-Averaged Navier-Stokes Solutions
- Explainable Machine Learning for Hydrocarbon Prospect Risking
- Robustness Evaluation of Regression Tasks with Skewed Domain Preferences
- Multi-level and multi-modal feature fusion for accurate 3D object detection in Connected and Automated Vehicles
- DOC-NAD: A Hybrid Deep One-class Classifier for Network Anomaly Detection