Papers
Mon 18 Apr 2022
133 papers
- CHAI: A CHatbot AI for Task-Oriented Dialogue with Offline Reinforcement LearningOffline RL and imitation learning from data → Language-conditioned policies and VLAs
- StableMoE: Stable Routing Strategy for Mixture of ExpertsMixture-of-experts → Expert routing strategies
- StepGame: A New Benchmark for Robust Multi-Hop Spatial Reasoning in TextsLLM reasoning → Spatial and embodied reasoning
- SynopSet: Multiscale Visual Abstraction Set for Explanatory Analysis of DNA Nanotechnology Simulations
- The Equity Framework: Fairness Beyond Equalized Predictive Outcomes
- Demographic-Reliant Algorithmic Fairness: Characterizing the Risks of Demographic Data Collection in the Pursuit of Fairness
- NFT Appraisal Prediction: Utilizing Search Trends, Public Market Data, Linear Regression and Recurrent Neural Networks
- Multi-task Deep Neural Networks for Massive MIMO CSI Feedback
- Verification of Locally Tight Programs
- CgAT: Center-Guided Adversarial Training for Deep Hashing-Based Retrieval
- Context-Aware Language Modeling for Goal-Oriented Dialogue Systems
- Gated Multimodal Fusion with Contrastive Learning for Turn-taking Prediction in Human-robot Dialogue
- Predictive Accuracy of a Hybrid Generalized Long Memory Model for Short Term Electricity Price Forecasting
- Cross-view Brain Decoding
- Entropy-based Stability-Plasticity for Lifelong Learning
- Special Session: Towards an Agile Design Methodology for Efficient, Reliable, and Secure ML Systems
- BSAL: A Framework of Bi-component Structure and Attribute Learning for Link Prediction
- UNBUS: Uncertainty-aware Deep Botnet Detection System in Presence of Perturbed Samples
- An advanced spatio-temporal convolutional recurrent neural network for storm surge predictions
- Optical Remote Sensing Image Understanding with Weak Supervision: Concepts, Methods, and Perspectives
- Optimizing Tensor Network Contraction Using Reinforcement Learning
- PR-DAD: Phase Retrieval Using Deep Auto-Decoders
- Benchmarking Domain Generalization on EEG-based Emotion Recognition
- Spatial-Temporal Hypergraph Self-Supervised Learning for Crime Prediction
- INFOrmation Prioritization through EmPOWERment in Visual Model-Based RL
- A Region-Based Deep Learning Approach to Automated Retail Checkout
- VQGAN-CLIP: Open Domain Image Generation and Editing with Natural Language Guidance
- MASSIVE: A 1M-Example Multilingual Natural Language Understanding Dataset with 51 Typologically-Diverse Languages
- On Parametric Optimal Execution and Machine Learning Surrogates
- Adaptive Noisy Data Augmentation for Regularized Estimation and Inference in Generalized Linear Models
- Training and Evaluation of Deep Policies using Reinforcement Learning and Generative Models
- Expert-Calibrated Learning for Online Optimization with Switching Costs
- A Comprehensive Survey on Trustworthy Graph Neural Networks: Privacy, Robustness, Fairness, and Explainability
- Learning Similarity Preserving Binary Codes for Recommender Systems
- Cylin-Painting: Seamless 360textdegree Panoramic Image Outpainting and Beyond
- CBR-iKB: A Case-Based Reasoning Approach for Question Answering over Incomplete Knowledge Bases
- Imagination-Augmented Natural Language Understanding
- Dress Code: High-Resolution Multi-Category Virtual Try-On
- An Optimal Time Variable Learning Framework for Deep Neural Networks
- Spot the Difference: A Novel Task for Embodied Agents in Changing Environments
- DeepCore: A Comprehensive Library for Coreset Selection in Deep Learning
- Active Learning Helps Pretrained Models Learn the Intended Task
- Inductive Biases for Object-Centric Representations in the Presence of Complex Textures
- Enhancing Non-mass Breast Ultrasound Cancer Classification With Knowledge Transfer
- Self Supervised Lesion Recognition For Breast Ultrasound Diagnosis
- Research on Domain Information Mining and Theme Evolution of Scientific Papers
- Predictive analytics for appointment bookings
- AB/BA analysis: A framework for estimating keyword spotting recall improvement while maintaining audio privacy
- Simultaneous Multiple-Prompt Guided Generation Using Differentiable Optimal Transport
- AI for human assessment: What do professional assessors need?
- Revisiting Consistency Regularization for Semi-supervised Change Detection in Remote Sensing Images
- Neural Space-filling Curves
- Learning to Listen: Modeling Non-Deterministic Dyadic Facial Motion
- VSA: Learning Varied-Size Window Attention in Vision Transformers
- Deep Equilibrium Optical Flow Estimation
- Exploring Dimensionality Reduction Techniques in Multilingual Transformers
- STONet: A Neural-Operator-Driven Spatio-temporal Network
- Temporally Efficient Vision Transformer for Video Instance Segmentation
- Robust, Nonparametric, Efficient Decomposition of Spectral Peaks under Distortion and Interference
- Caption Feature Space Regularization for Audio Captioning
- Zero-shot Entity and Tweet Characterization with Designed Conditional Prompts and Contexts
- TranS: Transition-based Knowledge Graph Embedding with Synthetic Relation Representation
- Dynamic Network Adaptation at Inference
- Unsupervised Contrastive Domain Adaptation for Semantic Segmentation
- L3Cube-HingCorpus and HingBERT: A Code Mixed Hindi-English Dataset and BERT Language Models
- Fast and Memory-Efficient Network Towards Efficient Image Super-Resolution
- CenterNet++ for Object Detection
- LayoutLMv3: Pre-training for Document AI with Unified Text and Image Masking
- Subspace Nonnegative Matrix Factorization for Feature Representation
- Multiple-environment Self-adaptive Network for Aerial-view Geo-localization
- Strengthening Subcommunities: Towards Sustainable Growth in AI Research
- Detecting Deepfakes with Self-Blended Images
- Learning to Execute Actions or Ask Clarification Questions
- Benign Overfitting in Time Series Linear Models with Over-Parameterization
- Detecting, Tracking and Counting Motorcycle Rider Traffic Violations on Unconstrained Roads
- AutoMLBench: A Comprehensive Experimental Evaluation of Automated Machine Learning Frameworks
- MHSCNet: A Multimodal Hierarchical Shot-aware Convolutional Network for Video Summarization
- Extracting Targeted Training Data from ASR Models, and How to Mitigate It
- Active Learning with Weak Supervision for Gaussian Processes
- Time Series Clustering for Grouping Products Based on Price and Sales Patterns
- BSRT: Improving Burst Super-Resolution with Swin Transformer and Flow-Guided Deformable Alignment
- A Comprehensive Survey on Data-Efficient GANs in Image Generation
- GL-CLeF: A Global-Local Contrastive Learning Framework for Cross-lingual Spoken Language Understanding
- Hierarchical Optimal Transport for Comparing Histopathology Datasets
- Application of Transfer Learning and Ensemble Learning in Image-level Classification for Breast Histopathology
- Tracking monocular camera pose and deformation for SLAM inside the human body
- Saliency in Augmented Reality
- Heavy Rain Face Image Restoration: Integrating Physical Degradation Model and Facial Component Guided Adversarial Learning
- A Convergence Analysis of Nesterov's Accelerated Gradient Method in Training Deep Linear Neural Networks
- UMass PCL at SemEval-2022 Task 4: Pre-trained Language Model Ensembles for Detecting Patronizing and Condescending Language
- Unsupervised domain adaptation and super resolution on drone images for autonomous dry herbage biomass estimation
- Differentiable Time-Frequency Scattering on GPU
- Factual Error Correction for Abstractive Summaries Using Entity Retrieval
- Visio-Linguistic Brain Encoding
- Joint Multi-view Unsupervised Feature Selection and Graph Learning
- Fast optimization of common basis for matrix set through Common Singular Value Decomposition
- Preference Enhanced Social Influence Modeling for Network-Aware Cascade Prediction
- The Devil is in the Frequency: Geminated Gestalt Autoencoder for Self-Supervised Visual Pre-Training
- Empirical Evaluation and Theoretical Analysis for Representation Learning: A Survey
- How to Attain Communication-Efficient DNN Training? Convert, Compress, Correct
All 133
- OMG: Observe Multiple Granularities for Natural Language-Based Vehicle Retrieval
- TigerLily: Finding drug interactions in silico with the Graph
- A Greedy and Optimistic Approach to Clustering with a Specified Uncertainty of Covariates
- Understanding Gradual Domain Adaptation: Improved Analysis, Optimal Path and Beyond
- UTNLP at SemEval-2022 Task 6: A Comparative Analysis of Sarcasm Detection Using Generative-based and Mutation-based Data Augmentation
- Self-Supervised Arbitrary-Scale Point Clouds Upsampling via Implicit Neural Representation
- Semi-Supervised Super-Resolution
- Sardino: Ultra-Fast Dynamic Ensemble for Secure Visual Sensing at Mobile Edge
- Modality-Balanced Embedding for Video Retrieval
- Real-World Deep Local Motion Deblurring
- HRCF: Enhancing Collaborative Filtering via Hyperbolic Geometric Regularization
- Usage of specific attention improves change point detection
- TABi: Type-Aware Bi-Encoders for Open-Domain Entity Retrieval
- A Study on Prompt-based Few-Shot Learning Methods for Belief State Tracking in Task-oriented Dialog Systems
- TOD-CNN: An Effective Convolutional Neural Network for Tiny Object Detection in Sperm Videos
- On Arbitrary Compression for Decentralized Consensus and Stochastic Optimization over Directed Networks
- Multi-scale Anomaly Detection for Big Time Series of Industrial Sensors
- A dynamical systems based framework for dimension reduction
- End-to-end Weakly-supervised Single-stage Multiple 3D Hand Mesh Reconstruction from a Single RGB Image
- Back to the Future: Bidirectional Information Decoupling Network for Multi-turn Dialogue Modeling
- Characterizing and Understanding Distributed GNN Training on GPUs
- Detect Rumors in Microblog Posts for Low-Resource Domains via Adversarial Contrastive Learning
- Dynamic Position Encoding for Transformers
- Ingredient Extraction from Text in the Recipe Domain
- Trinary Tools for Continuously Valued Binary Classifiers
- A Practical Cross-Device Federated Learning Framework over 5G Networks
- Animal Kingdom: A Large and Diverse Dataset for Animal Behavior Understanding
- Less is More: Learning to Refine Dialogue History for Personalized Dialogue Generation
- Parallel Network with Channel Attention and Post-Processing for Carotid Arteries Vulnerable Plaque Segmentation in Ultrasound Images
- FedKL: Tackling Data Heterogeneity in Federated Reinforcement Learning by Penalizing KL Divergence
- Non-Parallel Text Style Transfer with Self-Parallel Supervision
- End-to-end Dense Video Captioning as Sequence Generation
- HFT-ONLSTM: Hierarchical and Fine-Tuning Multi-label Text Classification