Papers
Sun 20 Mar 2022
118 papers
- Build a Robust QA System with Transformer-based Mixture of ExpertsMixture-of-experts → MoE large language models
- Towards Large-Scale Interpretable Knowledge Graph Reasoning for Dialogue SystemsLLM reasoning → Knowledge- and tool-augmented reasoning
- Open-Vocabulary One-Stage Detection with Hierarchical Visual-Language Knowledge DistillationKnowledge distillation → Detection and dense prediction distillation
- A Neural-Symbolic Approach to Natural Language UnderstandingLLM reasoning → Reasoning benchmarks and evaluation
- Perceiving the World: Question-guided Reinforcement Learning for Text-based Games
- Delta Keyword Transformer: Bringing Transformers to the Edge through Dynamically Pruned Multi-Head Self-Attention
- ZOOMER: Boosting Retrieval on Web-scale Graphs by Regions of Interest
- Deep Learning based Intelligent Coin-tap Test for Defect Recognition
- Explainable Misinformation Detection Across Multiple Social Media Platforms
- Robust Action Gap Increasing with Clipped Advantage Learning
- Hybrid training of optical neural networks
- Phase Recognition in Contrast-Enhanced CT Scans based on Deep Learning and Random Sampling
- VinDr-Mammo: A large-scale benchmark dataset for computer-aided diagnosis in full-field digital mammography
- Repairing Brain-Computer Interfaces with Fault-Based Data Acquisition
- Mitigating Gender Bias in Machine Translation through Adversarial Learning
- RareGAN: Generating Samples for Rare Classes
- Fully Convolutional Fractional Scaling
- A direct geometry processing cartilage generation method using segmented bone models from datasets with poor cartilage visibility
- Lateral Ego-Vehicle Control without Supervision using Point Clouds
- From Stance to Concern: Adaptation of Propositional Analysis to New Tasks and Domains
- Continual Sequence Generation with Adaptive Compositional Modules
- Forecasting Sparse Movement Speed of Urban Road Networks with Nonstationary Temporal Matrix Factorization
- Breast Cancer Induced Bone Osteolysis Prediction Using Temporal Variational Auto-Encoders
- Confidence intervals for nonparametric regression
- FUTR3D: A Unified Sensor Fusion Framework for 3D Detection
- Multimodal learning-based inversion models for the space-time reconstruction of satellite-derived geophysical fields
- V2X-ViT: Vehicle-to-Everything Cooperative Perception with Vision Transformer
- Transform your Smartphone into a DSLR Camera: Learning the ISP in the Wild
- Explicit User Manipulation in Reinforcement Learning Based Recommender Systems
- Enriching Unsupervised User Embedding via Medical Concepts
- Automated Detection of Acute Promyelocytic Leukemia in Blood Films and Bone Marrow Aspirates with Annotation-free Deep Learning
- Calibration of Machine Reading Systems at Scale
- Multi-Modal Learning Using Physicians Diagnostics for Optical Coherence Tomography Classification
- Immersive Text Game and Personality Classification
- Differentiable Reasoning over Long Stories -- Assessing Systematic Generalisation in Neural Models
- Hierarchical Reinforcement Learning of Locomotion Policies in Response to Approaching Objects: A Preliminary Study
- Does DQN really learn? Exploring adversarial training schemes in Pong
- PediCXR: An open, large-scale chest radiograph dataset for interpretation of common thoracic diseases in children
- Learning from Multiple Expert Annotators for Enhancing Anomaly Detection in Medical Image Analysis
- A Novel Transparency Strategy-based Data Augmentation Approach for BI-RADS Classification of Mammograms
- Convergence rates of the stochastic alternating algorithm for bi-objective optimization
- Model-based Multi-agent Reinforcement Learning: Recent Progress and Prospects
- A physical approach to qualia and the emergence of conscious observers in qualia space
- The Dark Side: Security Concerns in Machine Learning for EDA
- Towards Clinical Practice: Design and Implementation of Convolutional Neural Network-Based Assistive Diagnosis System for COVID-19 Case Detection from Chest X-Ray Images
- Geometric Methods for Sampling, Optimisation, Inference and Adaptive Agents
- Policy Gradients using Variational Quantum Circuits
- Point3D: tracking actions as moving points with 3D CNNs
- Neuro-physical dynamic load modeling using differentiable parametric optimization
- Cluster & Tune: Boost Cold Start Performance in Text Classification
- Small Batch Sizes Improve Training of Low-Resource Neural MT
- Multi-view Multi-behavior Contrastive Learning in Recommendation
- Distributionally robust risk evaluation with a causality constraint and structural information
- Self-supervised Point Cloud Completion on Real Traffic Scenes via Scene-concerned Bottom-up Mechanism
- Accelerating Integrated Task and Motion Planning with Neural Feasibility Checking
- LEReg: Empower Graph Neural Networks with Local Energy Regularization
- CRISPnet: Color Rendition ISP Net
- Who Shares Fake News? Uncovering Insights from Social Media Users' Post Histories
- 3D Human Pose Estimation Using M"obius Graph Convolutional Networks
- A Learning Convolutional Neural Network Approach for Network Robustness Prediction
- Towards 3D Scene Understanding by Referring Synthetic Models
- Parallel Instance Query Network for Named Entity Recognition
- Document Dewarping with Control Points
- Unsupervised Domain Adaptation for Nighttime Aerial Tracking
- Multi-Agent Terraforming: Efficient Multi-Agent Path Finding via Environment Manipulation
- End-to-End Video Text Spotting with Transformer
- Iwin: Human-Object Interaction Detection via Transformer with Irregular Windows
- Stochastic Video Prediction with Structure and Motion
- Recognising the importance of preference change: A call for a coordinated multidisciplinary research effort in the age of AI
- Reinforcement learning reward function in unmanned aerial vehicle control tasks
- Learning on the Job: Long-Term Behavioural Adaptation in Human-Robot Interactions
- Learning Whole Heart Mesh Generation From Patient Images For Computational Simulations
- An Adaptive and Scalable ANN-based Model-Order-Reduction Method for Large-Scale TO Designs
- Soft-CP: A Credible and Effective Data Augmentation for Semantic Segmentation of Medical Lesions
- Attention Aided CSI Wireless Localization
- Adversarial Parameter Attack on Deep Neural Networks
- NeuralReshaper: Single-image Human-body Retouching with Deep Neural Networks
- MicroRacer: a didactic environment for Deep Reinforcement Learning
- Depth Estimation by Combining Binocular Stereo and Monocular Structured-Light
- SimAN: Exploring Self-Supervised Representation Learning of Scene Text via Similarity-Aware Normalization
- TVConv: Efficient Translation Variant Convolution for Layout-aware Visual Processing
- Inferring Articulated Rigid Body Dynamics from RGBD Video
- Hierarchical Inductive Transfer for Continual Dialogue Learning
- Entailment Relation Aware Paraphrase Generation
- DEIM: An effective deep encoding and interaction model for sentence matching
- Encoder-Decoder Architecture for Supervised Dynamic Graph Learning: A Survey
- Optimizing Camera Placements for Overlapped Coverage with 3D Camera Projections
- Portrait Eyeglasses and Shadow Removal by Leveraging 3D Synthetic Data
- ECAPA-TDNN for Multi-speaker Text-to-speech Synthesis
- Federated Spatial Reuse Optimization in Next-Generation Decentralized IEEE 802.11 WLANs
- Inspection-L: Self-Supervised GNN Node Embeddings for Money Laundering Detection in Bitcoin
- Unidirectional Thin Adapter for Efficient Adaptation of Deep Neural Networks
- Optical Flow for Video Super-Resolution: A Survey
- simCrossTrans: A Simple Cross-Modality Transfer Learning for Object Detection with ConvNets or Vision Transformers
- Adversarial Mutual Leakage Network for Cell Image Segmentation
- Partitioning Image Representation in Contrastive Learning
- Fine-Tuning Graph Neural Networks via Graph Topology induced Optimal Transport
- CrossBeam: Learning to Search in Bottom-Up Program Synthesis
- On the Computation of Necessary and Sufficient Explanations
- Over-parameterization: A Necessary Condition for Models that Extrapolate
All 118
- A 3D Generative Model for Structure-Based Drug Design
- Smoothing Advantage Learning
- VGSE: Visually-Grounded Semantic Embeddings for Zero-Shot Learning
- Quantum Multi-Agent Reinforcement Learning via Variational Quantum Circuit Design
- Towards Structuring Real-World Data at Scale: Deep Learning for Extracting Key Oncology Information from Clinical Text with Patient-Level Supervision
- Vision Transformer with Convolutions Architecture Search
- End-to-End Human-Gaze-Target Detection with Transformers
- Interpretability of Fine-grained Classification of Sadness and Depression
- g2pW: A Conditional Weighted Softmax BERT for Polyphone Disambiguation in Mandarin
- PipeGCN: Efficient Full-Graph Training of Graph Convolutional Networks with Pipelined Feature Communication
- STEMM: Self-learning with Speech-text Manifold Mixup for Speech Translation
- A Study on Robustness to Perturbations for Representations of Environmental Sound
- MetaOnce: A Metaverse Framework Based on Multi-scene Relations and Entity-relation-event Game
- Subspace Modeling for Fast Out-Of-Distribution and Anomaly Detection
- CoWs on Pasture: Baselines and Benchmarks for Language-Driven Zero-Shot Object Navigation
- How do noise tails impact on deep ReLU networks?
- Attri-VAE: attribute-based interpretable representations of medical images with variational autoencoders
- How does the pre-training objective affect what large language models learn about linguistic properties?