Papers
Sat 16 Oct 2021
120 papers
- Generative Adversarial Imitation Learning for End-to-End Autonomous Driving on Urban EnvironmentsEnd-to-end autonomous driving → Imitation-learning end-to-end planners +1
- HRKD: Hierarchical Relational Knowledge Distillation for Cross-domain Language Model CompressionKnowledge distillation → Knowledge distillation for LLMs
- Characterizing Improper Input Validation Vulnerabilities of Mobile Crowdsourcing ServicesLLM safety and security → Prompt injection and agent security
- A Good Prompt Is Worth Millions of Parameters: Low-resource Prompt-based Learning for Vision-Language ModelsMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
- Statistical Consequences of Dueling Bandits
- An Evolutionary Correlation-aware Feature Selection Method for Classification Problems
- A Nested Weighted Tchebycheff Multi-Objective Bayesian Optimization Approach for Flexibility of Unknown Utopia Estimation in Expensive Black-box Design Problems
- Summ^N: A Multi-Stage Summarization Framework for Long Input Dialogues and Documents
- An Acceleration Method Based on Deep Learning and Multilinear Feature Space
- Improving Transformers with Probabilistic Attention Keys
- Noise-Augmented Privacy-Preserving Empirical Risk Minimization with Dual-purpose Regularizer and Privacy Budget Retrieval and Recycling
- Blockchain and Federated Edge Learning for Privacy-Preserving Mobile Crowdsensing
- Fast Strain Estimation and Frame Selection in Ultrasound Elastography using Machine Learning
- Face Verification with Challenging Imposters and Diversified Demographics
- Finding Critical Scenarios for Automated Driving Systems: A Systematic Literature Review
- Learning UI Navigation through Demonstrations composed of Macro Actions
- Equivariant Finite Normalizing Flows
- Local Advantage Actor-Critic for Robust Multi-Agent Deep Reinforcement Learning
- Conceptual Modeling and Artificial Intelligence: Mutual Benefits from Complementary Worlds
- DPC: Unsupervised Deep Point Correspondence via Cross and Self Construction
- Towards Robust Waveform-Based Acoustic Models
- Hydra: A System for Large Multi-Model Deep Learning
- Achieving the Pareto Frontier of Regret Minimization and Best Arm Identification in Multi-Armed Bandits
- Learning velocity model for complex media with deep convolutional neural networks
- SAGAN: Adversarial Spatial-asymmetric Attention for Noisy Nona-Bayer Reconstruction
- Convolutional Deep Denoising Autoencoders for Radio Astronomical Images
- GradSign: Model Performance Inference with Theoretical Insights
- Deep Learning and Spectral Embedding for Graph Partitioning
- Deep Active Learning by Leveraging Training Dynamics
- MAAD: A Model and Dataset for "Attended Awareness" in Driving
- Physics-guided Deep Markov Models for Learning Nonlinear Dynamical Systems with Uncertainty
- LSA: Modeling Aspect Sentiment Coherency via Local Sentiment Aggregation
- Mapping illegal waste dumping sites with neural-network classification of satellite imagery
- A Variational Bayesian Approach to Learning Latent Variables for Acoustic Knowledge Transfer
- A MIMO Radar-based Few-Shot Learning Approach for Human-ID
- n-stage Latent Dirichlet Allocation: A Novel Approach for LDA
- Automated Remote Sensing Forest Inventory Using Satellite Imagery
- Pseudo-label refinement using superpixels for semi-supervised brain tumour segmentation
- ASR4REAL: An extended benchmark for speech models
- Intelligent Video Editing: Incorporating Modern Talking Face Generation Algorithms in a Video Editor
- Visual-aware Attention Dual-stream Decoder for Video Captioning
- Nys-Newton: Nystr"om-Approximated Curvature for Stochastic Optimization
- Explore before Moving: A Feasible Path Estimation and Memory Recalling Framework for Embodied Navigation
- Deep Image Debanding
- ASFormer: Transformer for Action Segmentation
- Dynamic Graph Echo State Networks
- BNAS v2: Learning Architectures for Binary Networks with Empirical Improvements
- FrugalScore: Learning Cheaper, Lighter and Faster Evaluation Metricsfor Automatic Text Generation
- Neural Network Pruning Through Constrained Reinforcement Learning
- DPNAS: Neural Architecture Search for Deep Learning with Differential Privacy
- Multi-View Stereo Network with attention thin volume
- On the Robustness of Reading Comprehension Models to Entity Renaming
- PAGnol: An Extra-Large French Generative Model
- Virtual Augmentation Supported Contrastive Learning of Sentence Representations
- Towards Making the Most of Multilingual Pretraining for Zero-Shot Neural Machine Translation
- A Unified Speaker Adaptation Approach for ASR
- Answering Open-Domain Multi-Answer Questions via a Recall-then-Verify Framework
- Hey AI, Can You Solve Complex Tasks by Talking to Agents?
- Substructure Distribution Projection for Zero-Shot Cross-Lingual Dependency Parsing
- Sparse Distillation: Speeding Up Text Classification by Using Bigger Student Models
- Lifelong Pretraining: Continually Adapting Language Models to Emerging Corpora
- Pro-KD: Progressive Distillation by Following the Footsteps of the Teacher
- A theoretical and empirical study of new adaptive algorithms with additional momentum steps and shifted updates for stochastic non-convex optimization
- Sharpness-Aware Minimization Improves Language Model Generalization
- An Empirical Survey of the Effectiveness of Debiasing Techniques for Pre-trained Language Models
- The Power of Prompt Tuning for Low-Resource Semantic Parsing
- Locally Adaptive Structure and Texture Similarity for Image Quality Assessment
- DISAPERE: A Dataset for Discourse Structure in Peer Review Discussions
- MarkupLM: Pre-training of Text and Markup Language for Visually-rich Document Understanding
- Multimodal Dialogue Response Generation
- Analyzing Dynamic Adversarial Training Data in the Limit
- AugmentedCode: Examining the Effects of Natural Language Resources in Code Retrieval Models
- What can we learn from universal Turing machines?
- DFW-PP: Dynamic Feature Weighting based Popularity Prediction for Social Media Content
- BAPGAN: GAN-based Bone Age Progression of Femur and Phalange X-ray Images
- Mode and Ridge Estimation in Euclidean and Directional Product Spaces: A Mean Shift Approach
- Think Before You Speak: Explicitly Generating Implicit Commonsense Knowledge for Response Generation
- On Model Selection Consistency of Lasso for High-Dimensional Ising Models
- PRIMERA: Pyramid-based Masked Sentence Pre-training for Multi-document Summarization
- Hybrid Mutimodal Fusion for Dimensional Emotion Recognition
- Improvised Aerial Object Detection approach for YOLOv3 Using Weighted Luminance
- Lifelong Topological Visual Navigation
- Understanding Multimodal Procedural Knowledge by Sequencing Multimodal Instructional Manuals
- Extremely Simple Streaming Forest
- Learning Cooperation and Online Planning Through Simulation and Graph Convolutional Network
- FedMM: Saddle Point Optimization for Federated Adversarial Domain Adaptation
- Joint 3D Human Shape Recovery and Pose Estimation from a Single Image with Bilayer Graph
- Fast Projection onto the Capped Simplex with Applications to Sparse Regression in Bioinformatics
- Case-based Reasoning for Better Generalization in Textual Reinforcement Learning
- Improving Compositional Generalization with Self-Training for Data-to-Text Generation
- On the Safety of Conversational Models: Taxonomy, Dataset, and Benchmark
- Heterogeneous Graph-Based Multimodal Brain Network Learning
- Seeking Patterns, Not just Memorizing Procedures: Contrastive Learning for Solving Math Word Problems
- Leveraging Knowledge in Multilingual Commonsense Reasoning
- A Short Study on Compressing Decoder-Based Language Models
- Controllable Semantic Parsing via Retrieval Augmentation
- Knowledge Enhanced Pretrained Language Models: A Compreshensive Survey
- Good Examples Make A Faster Learner: Simple Demonstration-based Learning for Low-resource NER
- Accelerating Training and Inference of Graph Neural Networks with Fast Sampling and Pipelining
- Adversarial Attacks on Gaussian Process Bandits
All 120
- TESDA: Transform Enabled Statistical Detection of Attacks in Deep Neural Networks
- Self-Annotated Training for Controllable Image Captioning
- How Well Do You Know Your Audience? Toward Socially-aware Question Generation
- Prix-LM: Pretraining for Multilingual Knowledge Base Construction
- Online Target Q-learning with Reverse Experience Replay: Efficiently finding the Optimal Policy for Linear MDPs
- Unsupervised Natural Language Inference Using PHL Triplet Generation
- Meta-Learning with Adjoint Methods
- Metadata Shaping: Natural Language Annotations for the Tail
- TorchEsegeta: Framework for Interpretability and Explainability of Image-based Deep Learning Models
- COVID-19 Detection in Chest X-ray Images Using Swin-Transformer and Transformer in Transformer
- EncT5: A Framework for Fine-tuning T5 as Non-autoregressive Models
- Deep learning-based detection of intravenous contrast in computed tomography scans
- Finding Backdoors to Integer Programs: A Monte Carlo Tree Search Framework
- Dataset Knowledge Transfer for Class-Incremental Learning without Memory
- Understanding Dataset Difficulty with V-Usable Information
- Robustness Challenges in Model Distillation and Pruning for Natural Language Understanding
- Nuances in Margin Conditions Determine Gains in Active Learning
- Open Domain Question Answering with A Unified Knowledge Interface
- Multilingual unsupervised sequence segmentation transfers to extremely low-resource languages
- Invariant Language Modeling