Papers
Wed 28 Sep 2022
207 papers
- Neural Methods for Logical Reasoning Over Knowledge GraphsLLM reasoning → Knowledge- and tool-augmented reasoning
- Improving alignment of dialogue agents via targeted human judgementsLLM agents and tool use → General LLM agent frameworks and benchmarks +1
- FiD-Light: Efficient and Effective Retrieval-Augmented Text GenerationRetrieval-augmented generation → RAG pipeline design and evaluation
- Spectral Diffusion ProcessesDiffusion models → Diffusion foundations and sampling
- On the Robustness of Random Forest Against Untargeted Data Poisoning: An Ensemble-Based ApproachLLM safety and security → Backdoor and data poisoning attacks
- Argumentative Reward Learning: Reasoning About Human PreferencesLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
- Thinking Hallucination for Video CaptioningLLM reasoning → Hallucination detection and mitigation
- Bimanual rope manipulation skill synthesis through context dependent correction policy learning from human demonstrationOffline RL and imitation learning from data → Robot manipulation imitation learning
- Adaptive Sparse ViT: Towards Learnable Adaptive Token Pruning by Fully Exploiting Self-AttentionEfficient LLM inference and serving → Token pruning and merging for ViTs
- Using contradictions improves question answering systems
- Predictive Crypto-Asset Automated Market Making Architecture for Decentralized Finance using Deep Reinforcement Learning
- Cross-Domain Neural Entity Linking
- Discussion about Attacks and Defenses for Fair and Robust Recommendation System Design
- Multiclass Sentiment Prediction for Stock Trading
- Explainable classification of astronomical uncertain time series
- Scheduling for Urban Air Mobility using Safe Learning
- Exploiting Instance-based Mixed Sampling via Auxiliary Source Domain Supervision for Domain-adaptive Action Detection
- A deep learning approach to the probabilistic numerical solution of path-dependent partial differential equations
- Hyperspectral Remote Sensing Benchmark Database for Oil Spill Detection with an Isolation Forest-Guided Unsupervised Detector
- Transfer Learning with Pretrained Remote Sensing Transformers
- Non-contrastive representation learning for intervals from well logs
- Low-Resolution Action Recognition for Tiny Actions Challenge
- medigan: a Python library of pretrained generative models for medical image synthesis
- Lazy Probabilistic Roadmaps Revisited
- Reducing Positional Variance in Cross-sectional Abdominal CT Slices with Deep Conditional Generative Models
- Constrained Dynamic Movement Primitives for Safe Learning of Motor Skills
- The Chamber Ensemble Generator: Limitless High-Quality MIR Data via Generative Modeling
- Machine Learning for Optical Motion Capture-driven Musculoskeletal Modelling from Inertial Motion Capture Data
- CompNet: A Designated Model to Handle Combinations of Images and Designed features
- Parameterized Quantum Circuits with Quantum Kernels for Machine Learning: A Hybrid Quantum-Classical Approach
- Synthesizing Annotated Image and Video Data Using a Rendering-Based Pipeline for Improved License Plate Recognition
- A Diver Attention Estimation Framework for Effective Underwater Human-Robot Interaction
- GeONet: a neural operator for learning the Wasserstein geodesic
- Breaking Time Invariance: Assorted-Time Normalization for RNNs
- Out-of-Distribution Detection for LiDAR-based 3D Object Detection
- Efficient Medical Image Assessment via Self-supervised Learning
- Increasing the Accuracy of a Neural Network Using Frequency Selective Mesh-to-Grid Resampling
- Minimax Optimal Kernel Operator Learning via Multilevel Training
- View-Invariant Localization using Semantic Objects in Changing Environments
- Category-Level Global Camera Pose Estimation with Multi-Hypothesis Point Cloud Correspondences
- Improving Text-to-SQL Semantic Parsing with Fine-grained Query Understanding
- Optimistic Posterior Sampling for Reinforcement Learning with Few Samples and Tight Guarantees
- Masked Multi-Step Multivariate Time Series Forecasting with Future Information
- Applying Machine Learning for Duplicate Detection, Throttling and Prioritization of Equipment Commissioning Audits at Fulfillment Network
- RALACs: Action Recognition in Autonomous Vehicles using Interaction Encoding and Optical Flow
- Biological connectomes as a representation for the architecture of artificial neural networks
- L2XGNN: Learning to Explain Graph Neural Networks
- FIRE: A Failure-Adaptive Reinforcement Learning Framework for Edge Computing Migrations
- Variational Bayes for robust radar single object tracking
- Neighborhood Gradient Clustering: An Efficient Decentralized Learning Method for Non-IID Data Distributions
- Downstream Datasets Make Surprisingly Good Pretraining Corpora
- Feature Decoupling in Self-supervised Representation Learning for Open Set Recognition
- Assessing Coarse-to-Fine Deep Learning Models for Optic Disc and Cup Segmentation in Fundus Images
- UNesT: Local Spatial Representation Learning with Hierarchical Transformer for Efficient Medical Segmentation
- Clinical Language Understanding Evaluation (CLUE)
- Semantic Segmentation of Vegetation in Remote Sensing Imagery Using Deep Learning
- Happy or grumpy? A Machine Learning Approach to Analyze the Sentiment of Airline Passengers' Tweets
- Generalized Kernel Regularized Least Squares
- Audio Barlow Twins: Self-Supervised Audio Representation Learning
- Pareto Actor-Critic for Equilibrium Selection in Multi-Agent Reinforcement Learning
- The Change You Want to See
- Who is GPT-3? An Exploration of Personality, Values and Demographics
- Scalably learning quantum many-body Hamiltonians from dynamical data
- Label Noise Robustness of Conformal Prediction
- Proceedings of the AI-HRI Symposium at AAAI-FSS 2022
- DexTransfer: Real World Multi-fingered Dexterous Grasping with Minimal Human Demonstrations
- Multilingual Search with Subword TF-IDF
- Causal Proxy Models for Concept-Based Model Explanations
- Audio Retrieval with WavText5K and CLAP Training
- Towards Multimodal Prediction of Spontaneous Humour: A Novel Dataset and First Results
- Generalization in Deep Reinforcement Learning for Robotic Navigation by Reward Shaping
- Less is More: Rethinking Few-Shot Learning and Recurrent Neural Nets
- 360FusionNeRF: Panoramic Neural Radiance Fields with Joint Guidance
- A Multi-scale Graph Signature for Persistence Diagrams based on Return Probabilities of Random Walks
- A Survey on Physical Adversarial Attack in Computer Vision
- Physics-aware Differentiable Discrete Codesign for Diffractive Optical Neural Networks
- B2B Advertising: Joint Dynamic Scoring of Account and Users
- Compositional Score Modeling for Simulation-based Inference
- A Closer Look at Evaluating the Bit-Flip Attack Against Deep Neural Networks
- Obstacle Identification and Ellipsoidal Decomposition for Fast Motion Planning in Unknown Dynamic Environments
- Road Rutting Detection using Deep Learning on Images
- Online Subset Selection using α-Core with no Augmented Regret
- DMAP: a Distributed Morphological Attention Policy for Learning to Locomote with a Changing Body
- Longitudinal Variability Analysis on Low-dose Abdominal CT with Deep Learning-based Segmentation
- Automated Quality Controlled Analysis of 2D Phase Contrast Cardiovascular Magnetic Resonance Imaging
- Prompt-driven efficient Open-set Semi-supervised Learning
- Spatial Pruned Sparse Convolution for Efficient 3D Object Detection
- Active Transfer Prototypical Network: An Efficient Labeling Algorithm for Time-Series Data
- Class-Imbalanced Complementary-Label Learning via Weighted Loss
- An Automatic Evaluation of the WMT22 General Machine Translation Task
- Programmable and Customized Intelligence for Traffic Steering in 5G Networks Using Open RAN Architectures
- CALIP: Zero-Shot Enhancement of CLIP with Parameter-free Attention
- Unrolled Compressed Blind-Deconvolution
- Supervised Contrastive Learning as Multi-Objective Optimization for Fine-Tuning Large Pre-trained Language Models
- TVLT: Textless Vision-Language Transformer
- Automatic Analysis of Available Source Code of Top Artificial Intelligence Conference Papers
- Guiding Safe Exploration with Weakest Preconditions
- Mobile Edge Computing, Metaverse, 6G Wireless Communications, Artificial Intelligence, and Blockchain: Survey and Their Convergence
- Multi-scale Attention Network for Single Image Super-Resolution
- From Zero to Production: Baltic-Ukrainian Machine Translation Systems to Aid Refugees
All 207
- Towards Automatic Forecasting: Evaluation of Time-Series Forecasting Models for Chickenpox Cases Estimation in Hungary
- Deep learning for gradient flows using the Brezis-Ekeland principle
- Debiasing Graph Neural Networks via Learning Disentangled Causal Substructure
- Cyclegan Network for Sheet Metal Welding Drawing Translation
- Exploring the Relationship between Architecture and Adversarially Robust Generalization
- Segmentation method of U-net sheet metal engineering drawing based on CBAM attention mechanism
- Weighted Contrastive Hashing
- Deepfake audio detection by speaker verification
- Data Augmentation using Feature Generation for Volumetric Medical Images
- Securing Federated Learning against Overwhelming Collusive Attackers
- Offensive Language Detection on Twitter
- Combining Reinforcement Learning and Tensor Networks, with an Application to Dynamical Large Deviations
- Momentum Gradient Descent Federated Learning with Local Differential Privacy
- PTSD in the Wild: A Video Database for Studying Post-Traumatic Stress Disorder Recognition in Unconstrained Environments
- Global Weighted Tensor Nuclear Norm for Tensor Robust Principal Component Analysis
- Backward Reachability Analysis of Neural Feedback Loops: Techniques for Linear and Nonlinear Systems
- Recipro-CAM: Fast gradient-free visual explanations for convolutional neural networks
- Effective General-Domain Data Inclusion for the Machine Translation Task by Vanilla Transformers
- City-scale Incremental Neural Mapping with Three-layer Sampling and Panoptic Representation
- Efficient block contrastive learning via parameter-free meta-node approximation
- LL-GNN: Low Latency Graph Neural Networks on FPGAs for High Energy Physics
- Popularity Driven Data Integration
- Adma-GAN: Attribute-Driven Memory Augmented GANs for Text-to-Image Generation
- Verifying Safety of Behaviour Trees in Event-B
- Advising Autonomous Cars about the Rules of the Road
- Monitoring ROS2: from Requirements to Autonomous Robots
- Motion Transformer for Unsupervised Image Animation
- Leveraging machine learning for less developed languages: Progress on Urdu text detection
- Keyword Extraction from Short Texts with a Text-To-Text Transfer Transformer
- Vision based Crop Row Navigation under Varying Field Conditions in Arable Fields
- CEFER: A Four Facets Framework based on Context and Emotion embedded features for Implicit and Explicit Emotion Recognition
- A Review of Modern Approaches for Coronary Angiography Imaging Analysis
- Towards Explaining Autonomy with Verbalised Decision Tree States
- Medical Image Captioning via Generative Pretrained Transformers
- Toward Certification of Machine-Learning Systems for Low Criticality Airborne Applications
- From Understanding the Population Dynamics of the NSGA-II to the First Proven Lower Bounds
- 3D Neural Sculpting (3DNS): Editing Neural Signed Distance Functions
- SoftTreeMax: Policy Gradient with Tree Search
- Anomaly detection optimization using big data and deep learning to reduce false-positive
- Graph Soft-Contrastive Learning via Neighborhood Ranking
- Machine Beats Machine: Machine Learning Models to Defend Against Adversarial Attacks
- Big data analysis and distributed deep learning for next-generation intrusion detection system optimization
- Dynamic MDETR: A Dynamic Multimodal Transformer Decoder for Visual Grounding
- Forecasting Sensor Values in Waste-To-Fuel Plants: a Case Study
- ArNLI: Arabic Natural Language Inference for Entailment and Contradiction Detection
- Obj2Seq: Formatting Objects as Sequences with Class Prompt for Visual Tasks
- Revamping Multilingual Agreement Bidirectionally via Switched Back-translation for Multilingual Neural Machine Translation
- Racial Bias in the Beautyverse
- DPNet: Dual-Path Network for Real-time Object Detection with Lightweight Attention
- Attention Spiking Neural Networks
- Experimental study of time series forecasting methods for groundwater level prediction
- DeViT: Deformed Vision Transformers in Video Inpainting
- A simple but strong baseline for online continual learning: Repeated Augmented Rehearsal
- An Efficient Multitask Learning Architecture for Affective Vocal Burst Analysis
- Hierarchical MixUp Multi-label Classification with Imbalanced Interdisciplinary Research Proposals
- SmartMocap: Joint Estimation of Human and Camera Motion using Uncalibrated RGB Cameras
- Disentangling Transfer in Continual Reinforcement Learning
- Strong Instance Segmentation Pipeline for MMSports Challenge
- UCEpic: Unifying Aspect Planning and Lexical Constraints for Generating Explanations in Recommendation
- MLink: Linking Black-Box Models from Multiple Domains for Collaborative Inference
- YATO: Yet Another deep learning based Text analysis Open toolkit
- A General Scattering Phase Function for Inverse Rendering
- InFi: End-to-End Learning to Filter Input for Resource-Efficiency in Mobile-Centric Inference
- Unified Loss of Pair Similarity Optimization for Vision-Language Retrieval
- Rethinking Blur Synthesis for Deep Real-World Image Deblurring
- USEEK: Unsupervised SE(3)-Equivariant 3D Keypoints for Generalizable Manipulation
- Natural Language Processing Methods to Identify Oncology Patients at High Risk for Acute Care with Clinical Notes
- Variance Tolerance Factors For Interpreting ALL Neural Networks
- Identifying Differential Equations to predict Blood Glucose using Sparse Identification of Nonlinear Systems
- Shape-constrained Symbolic Regression with NSGA-III
- Deep Learning based Automatic Quantification of Urethral Plate Quality using the Plate Objective Scoring Tool (POST)
- VREN: Volleyball Rally Dataset with Expression Notation Language
- Deeply Supervised Layer Selective Attention Network: Towards Label-Efficient Learning for Medical Image Classification
- Online Policy Optimization for Robust MDP
- Mutual Information Assisted Ensemble Recommender System for Identifying Critical Risk Factors in Healthcare Prognosis
- Multi-Sample Training for Neural Image Compression
- SEMICON: A Learning-to-hash Solution for Large-scale Fine-grained Image Retrieval
- Learning Deep Representations via Contrastive Learning for Instance Retrieval
- Supervised Class-pairwise NMF for Data Representation and Classification
- Label Distribution Learning via Implicit Distribution Representation
- TokenFlow: Rethinking Fine-grained Cross-modal Alignment in Vision-Language Retrieval
- Denoising of 3D MR images using a voxel-wise hybrid residual MLP-CNN model to improve small lesion diagnostic confidence
- Revisiting Few-Shot Learning from a Causal Perspective
- Signed Latent Factors for Spamming Activity Detection
- Streaming Video Temporal Action Segmentation In Real Time
- Asynchronous and Error-prone Longitudinal Data Analysis via Functional Calibration
- FedVeca: Federated Vectorized Averaging on Non-IID Data with Adaptive Bi-directional Global Objective
- Translation, Scale and Rotation: Cross-Modal Alignment Meets RGB-Infrared Vehicle Detection
- Analysis and prediction of heart stroke from ejection fraction and serum creatinine using LSTM deep learning approach
- PCB-RandNet: Rethinking Random Sampling for LIDAR Semantic Segmentation in Autonomous Driving Scene
- A Machine Learning Approach for DeepFake Detection
- TRBoost: A Generic Gradient Boosting Machine based on Trust-region Method
- A Parameter-free Nonconvex Low-rank Tensor Completion Model for Spatiotemporal Traffic Data Recovery
- Attacking Compressed Vision Transformers
- CourtNet for Infrared Small-Target Detection
- Solar Flare Index Prediction Using SDO/HMI Vector Magnetic Data Products with Statistical and Machine Learning Methods
- Data-driven Parsing Evaluation for Child-Parent Interactions
- An Embarrassingly Simple Approach to Semi-Supervised Few-Shot Learning
- ButterflyFlow: Building Invertible Layers with Butterfly Matrices
- METS-CoV: A Dataset of Medical Entity and Targeted Sentiment on COVID-19 Related Tweets
- Target Features Affect Visual Search, A Study of Eye Fixations
- Clustering-Induced Generative Incomplete Image-Text Clustering (CIGIT-C)
- Consensus Knowledge Graph Learning via Multi-view Sparse Low Rank Block Model
- Image Compressed Sensing with Multi-scale Dilated Convolutional Neural Network
- Structured Summarization: Unified Text Segmentation and Segment Labeling as a Generation Task
- MTU-Net: Multi-level TransUNet for Space-based Infrared Tiny Ship Detection
- RuDSI: graph-based word sense induction dataset for Russian