Papers
Sat 30 Apr 2022
85 papers
- Visual Spatial ReasoningLLM reasoning → Spatial and embodied reasoning
- Solution of DeBERTaV3 on CommonsenseQA
- Using Wordle for Learning to Design and Compare Strategies
- Visualizing and Explaining Language Models
- Mosaic Zonotope Shadow Matching for Risk-Aware Autonomous Localization in Harsh Urban Environments
- HDGT: Heterogeneous Driving Graph Transformer for Multi-Agent Trajectory Prediction via Scene Encoding
- Electrocardiographic Deep Learning for Predicting Post-Procedural Mortality
- Ultra-sensitive Flexible Sponge-Sensor Array for Muscle Activities Detection and Human Limb Motion Recognition
- A CNN Approach for 5G mmWave Positioning Using Beamformed CSI Measurements
- Optimizing One-pixel Black-box Adversarial Attacks
- Fair Feature Subset Selection using Multiobjective Genetic Algorithm
- Fractional Vegetation Cover Estimation using Hough Lines and Linear Iterative Clustering
- RADNet: A Deep Neural Network Model for Robust Perception in Moving Autonomous Systems
- A Short and General Duality Proof for Wasserstein Distributionally Robust Optimization
- Combined Learning of Neural Network Weights for Privacy in Collaborative Tasks
- Adapting and Evaluating Influence-Estimation Methods for Gradient-Boosted Decision Trees
- Towards Process-Oriented, Modular, and Versatile Question Generation that Meets Educational Needs
- Graph Anisotropic Diffusion
- Orthogonal Statistical Learning with Self-Concordant Loss
- End-to-End Signal Classification in Signed Cumulative Distribution Transform Space
- LayoutBERT: Masked Language Layout Model for Object Insertion
- Opponent Modeling in Negotiation Dialogues by Related Data Adaptation
- Engineering flexible machine learning systems by traversing functionally-invariant paths
- Continual Learning with Foundation Models: An Empirical Study of Latent Replay
- HateCheckHIn: Evaluating Hindi Hate Speech Detection Models
- Artificial Intelligence and Medicine: A literature review
- Detoxifying Language Models with a Toxic Corpus
- FairSR: Fairness-aware Sequential Recommendation through Multi-Task Learning with Preference Graph Embeddings
- Source Domain Subset Sampling for Semi-Supervised Domain Adaptation in Semantic Segmentation
- Learning to Get Up
- AdapterBias: Parameter-efficient Token-dependent Representation Shift for Adapters in NLP Tasks
- Composition-aware Graphic Layout GAN for Visual-textual Presentation Designs
- SHAPE: An Unified Approach to Evaluate the Contribution and Cooperation of Individual Modalities
- ONCE-3DLanes: Building Monocular 3D Lane Detection
- A Survey of Machine Narrative Reading Comprehension Assessments
- TTOpt: A Maximum Volume Quantized Tensor Train-based Optimization and its Application to Reinforcement Learning
- Learning Effective SDEs from Brownian Dynamics Simulations of Colloidal Particles
- Leveraging Emotion-specific Features to Improve Transformer Performance for Emotion Classification
- Understanding the Generalization Performance of Spectral Clustering Algorithms
- Dynamic Curriculum Learning for Great Ape Detection in the Wild
- Clues Before Answers: Generation-Enhanced Multiple-Choice QA
- Improving Visual Grounding with Visual-Linguistic Verification and Iterative Reasoning
- Deep Learning-Enabled Semantic Communication Systems with Task-Unaware Transmitter and Dynamic Data
- Probing Cross-Lingual Lexical Knowledge from Multilingual Sentence Encoders
- Complete Verification via Multi-Neuron Relaxation Guided Branch-and-Bound
- EasyNLP: A Comprehensive and Easy-to-use Toolkit for Natural Language Processing
- Unsupervised Visible-light Images Guided Cross-Spectrum Depth Estimation from Dual-Modality Cameras
- Heterogeneous Graph Neural Networks using Self-supervised Reciprocally Contrastive Learning
- PGD: A Large-scale Professional Go Dataset for Data-driven Analytics
- Approximating Permutations with Neural Network Components for Travelling Photographer Problem
- A Two-Stream AMR-enhanced Model for Document-level Event Argument Extraction
- Recognising Known Configurations of Garments For Dual-Arm Robotic Flattening
- Loss Function Entropy Regularization for Diverse Decision Boundaries
- StorSeismic: A new paradigm in deep learning for seismic processing
- A New Evaluation Method: Evaluation Data and Metrics for Chinese Grammar Error Correction
- An attention model for the formation of collectives in real-world domains
- Coarse-to-Fine Video Denoising with Dual-Stage Spatial-Channel Transformer
- DefakeHop++: An Enhanced Lightweight Deepfake Detector
- Software Testing for Machine Learning
- Explainable Artificial Intelligence for Bayesian Neural Networks: Towards trustworthy predictions of ocean dynamics
- Cracking White-box DNN Watermarks via Invariant Neuron Transforms
- Trust in Human-AI Interaction: Scoping Out Models, Measures, and Methods
- Reliable Label Correction is a Good Booster When Learning with Extremely Noisy Labels
- Towards Feature Distribution Alignment and Diversity Enhancement for Data-Free Quantization
- Practice Makes a Solver Perfect: Data Augmentation for Math Word Problem Solvers
- Building a Role Specified Open-Domain Dialogue System Leveraging Large-Scale Language Models
- FEDIC: Federated Learning on Non-IID and Long-Tailed Data via Calibrated Distillation
- A Heteroskedasticity-Robust Overidentifying Restriction Test with High-Dimensional Covariates
- Self-Programming Artificial Intelligence Using Code-Generating Language Models
- NeuralEF: Deconstructing Kernels by Deep Neural Networks
- Deep Ensemble as a Gaussian Process Approximate Posterior
- Elucidating Meta-Structures of Noisy Labels in Semantic Segmentation by Deep Neural Networks
- SVTR: Scene Text Recognition with a Single Visual Model
- AnimalTrack: A Benchmark for Multi-Animal Tracking in the Wild
- To Know by the Company Words Keep and What Else Lies in the Vicinity
- DIRA: Dynamic Domain Incremental Regularised Adaptation
- Look Closer to Supervise Better: One-Shot Font Generation via Component-Based Discriminator
- Multimodal Representation Learning With Text and Images
- Identification of Physical Processes and Unknown Parameters of 3D Groundwater Contaminant Problems via Theory-guided U-net
- Learn to Understand Negation in Video Retrieval
- ExSum: From Local Explanations to Model Understanding
- Gaze-enhanced Crossmodal Embeddings for Emotion Recognition
- SciEv: Finding Scientific Evidence Papers for Scientific News
- Unsupervised Contrastive Learning based Transformer for Lung Nodule Detection
- A Scalable 5,6-Qubit Grover's Quantum Search Algorithm