Papers
Sun 18 Apr 2021
142 papers
- Learning Interpretable End-to-End Vision-Based Motion Planning for Autonomous Driving with Optical Flow DistillationEnd-to-end autonomous driving → End-to-end system architecture
- Data-Efficient Language-Supervised Zero-Shot Learning with Self-DistillationKnowledge distillation → Multimodal distillation
- Quick Learner Automated Vehicle Adapting its Roadmanship to Varying Traffic Cultures with Meta Reinforcement LearningEnd-to-end autonomous driving → Reinforcement learning for driving
- End-to-End Interactive Prediction and Planning with Optical Flow Distillation for Autonomous DrivingEnd-to-end autonomous driving → End-to-end system architecture
- Improving Neural Model Performance through Natural Language Feedback on Their ExplanationsLLM alignment / RLHF / preference optimisation → Process reward models for reasoning
- GraphSVX: Shapley Value Explanations for Graph Neural Networks
- Style-Aware Normalized Loss for Improving Arbitrary Style Transfer
- Off-Policy Risk Assessment in Contextual Bandits
- Functional Protein Structure Annotation Using a Deep Convolutional Generative Adversarial Network
- Deep Clustering with Measure Propagation
- A recipe for annotating grounded clarifications
- Generating explanations for answer set programming applications
- On the Use of Context for Predicting Citation Worthiness of Sentences in Scholarly Articles
- Non-asymptotic model selection in block-diagonal mixture of polynomial experts models
- Many-Speakers Single Channel Speech Separation with Optimal Permutation Training
- Combining a Convolutional Neural Network with Autoencoders to Predict the Survival Chance of COVID-19 Patients
- Failing Conceptually: Concept-Based Explanations of Dataset Shift
- Reference-based Weak Supervision for Answer Sentence Selection using Web Data
- Attention-based Clinical Note Summarization
- A Simulated Experiment to Explore Robotic Dialogue Strategies for People with Dementia
- On the approximation of functions by tanh neural networks
- Knowledge Graph Anchored Information-Extraction for Domain-Specific Insights
- Group-Sparse Matrix Factorization for Transfer Learning of Word Embeddings
- The Preposition Project
- Motion Vector Extrapolation for Video Object Detection
- Towards Open-World Text-Guided Face Image Generation and Manipulation
- SurvNAM: The machine learning survival model explanation
- A Two-branch Neural Network for Non-homogeneous Dehazing via Ensemble Learning
- Texture Based Classification of High Resolution Remotely Sensed Imagery using Weber Local Descriptor
- Provably Safe Tolerance Estimation for Robot Arms via Sum-of-Squares Programming
- The Intrinsic Dimension of Images and Its Impact on Learning
- Modular Procedural Generation for Voxel Maps
- Convolutional Neural Networks in Orthodontics: a review
- A survey of image labelling for computer vision applications
- Perspectives on Machine Learning from Psychology's Reproducibility Crisis
- Language in a (Search) Box: Grounding Language Learning in Real-World Human-Machine Interaction
- Ranking Structured Objects with Graph Neural Networks
- CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval
- Filtering Empty Camera Trap Images in Embedded Systems
- Emotion-Regularized Conditional Variational Autoencoder for Emotional Response Generation
- An Improved Discriminative Optimization for 3D Rigid Point Cloud Registration
- Let's See Clearly: Contaminant Artifact Removal for Moving Cameras
- On Training Sketch Recognizers for New Domains
- Lesion-Inspired Denoising Network: Connecting Medical Image Denoising and Lesion Detection
- A Rank based Adaptive Mutation in Genetic Algorithm
- On the Influence of Masking Policies in Intermediate Pre-training
- Multi-scale Self-calibrated Network for Image Light Source Transfer
- LayoutXLM: Multimodal Pre-training for Multilingual Visually-rich Document Understanding
- CrossFit: A Few-shot Learning Challenge for Cross-task Generalization in NLP
- Modeling Ideological Salience and Framing in Polarized Online Groups with Graph Neural Networks and Structured Sparsity
- GPT3Mix: Leveraging Large-scale Language Models for Text Augmentation
- Flexible Generation of Natural Language Deductions
- SimCSE: Simple Contrastive Learning of Sentence Embeddings
- Classifications of the Summative Assessment for Revised Blooms Taxonomy by using Deep Learning
- Stream-level Latency Evaluation for Simultaneous Machine Translation
- FedNLP: Benchmarking Federated Learning Methods for Natural Language Processing Tasks
- CNN aided Weighted Interpolation for Channel Estimation in Vehicular Communications
- Contrastive Out-of-Distribution Detection for Pretrained Transformers
- Human Schema Curation via Causal Association Rule Mining
- SciCo: Hierarchical Cross-Document Coreference for Scientific Concepts
- Learn Continually, Generalize Rapidly: Lifelong Knowledge Accumulation for Few-shot Learning
- Best Practices for Noise-Based Augmentation to Improve the Performance of Deployable Speech-Based Emotion Recognition Systems
- Low-rank State-action Value-function Approximation
- Multilingual Knowledge Graph Completion with Joint Relation and Entity Alignment
- Consistent Accelerated Inference via Confident Adaptive Transformers
- Back-Training excels Self-Training at Unsupervised Domain Adaptation of Question Generation and Passage Retrieval
- Keyphrase Generation with Fine-Grained Evaluation-Guided Reinforcement Learning
- MonoGRNet: A General Framework for Monocular 3D Object Detection
- Intuitive Physics Guided Exploration for Sample Efficient Sim2real Transfer
- SalKG: Learning From Knowledge Graph Explanations for Commonsense Reasoning
- Human-Imitating Metrics for Training and Evaluating Privacy Preserving Emotion Recognition Models Using Sociolinguistic Knowledge
- Misinfo Reaction Frames: Reasoning about Readers' Reactions to News Headlines
- An Uncertainty-aware Hierarchical Probabilistic Network for Early Prediction, Quantification and Segmentation of Pulmonary Tumour Growth
- Chinese Sentences Similarity via Cross-Attention Based Siamese Network
- Fantastically Ordered Prompts and Where to Find Them: Overcoming Few-Shot Prompt Order Sensitivity
- Gaussian Dynamic Convolution for Efficient Single-Image Segmentation
- On the Sensitivity and Stability of Model Interpretations in NLP
- Variational Weakly Supervised Sentiment Analysis with Posterior Regularization
- Line Segmentation from Unconstrained Handwritten Text Images using Adaptive Approach
- Federated Learning of User Verification Models Without Sharing Embeddings
- Dynamically Addressing Unseen Rumor via Continual Learning
- Cross-Task Generalization via Natural Language Crowdsourcing Instructions
- Cross-Attention is All You Need: Adapting Pretrained Transformers for Machine Translation
- Fair Representation Learning for Heterogeneous Information Networks
- Constrained Language Models Yield Few-Shot Semantic Parsers
- TSGN: Transaction Subgraph Networks for Identifying Ethereum Phishing Accounts
- Making Attention Mechanisms More Robust and Interpretable with Virtual Adversarial Training
- Case-based Reasoning for Natural Language Queries over Knowledge Bases
- Solving Inefficiency of Self-supervised Representation Learning
- Revisiting the Complexity Analysis of Conflict-Based Search: New Computational Techniques and Improved Bounds
- Documenting Large Webtext Corpora: A Case Study on the Colossal Clean Crawled Corpus
- Zero-shot Cross-lingual Transfer of Neural Machine Translation with Multilingual Pretrained Encoders
- DCH-2: A Parallel Customer-Helpdesk Dialogue Corpus with Distributions of Annotators' Labels
- Multi-objective Feature Selection with Missing Data in Classification
- Generative Context Pair Selection for Multi-hop Question Answering
- Go Forth and Prosper: Language Modeling with Ancient Textual History
- CEAR: Cross-Entity Aware Reranker for Knowledge Base Completion
- Continuity-Discrimination Convolutional Neural Network for Visual Object Tracking
- Low-Rank Subspaces for Unsupervised Entity Linking
- Stochastic Optimization of Areas Under Precision-Recall Curves with Provable Convergence
All 142
- Learning with Instance Bundles for Reading Comprehension
- Application of Computer Vision and Machine Learning for Digitized Herbarium Specimens: A Systematic Literature Review
- Can NLI Models Verify QA Systems' Predictions?
- Unsupervised Deep Keyphrase Generation
- Revealing Persona Biases in Dialogue Systems
- GooAQ: Open Question Answering with Diverse Answer Types
- AmericasNLI: Evaluating Zero-shot Natural Language Understanding of Pretrained Multilingual Models in Truly Low-resource Languages
- Extract, Denoise and Enforce: Evaluating and Improving Concept Preservation for Text-to-Text Generation
- News Meets Microblog: Hashtag Annotation via Retriever-Generator
- Embedding-Enhanced Giza++: Improving Alignment in Low- and High- Resource Scenarios Using Embedding Space Geometry
- CLIPScore: A Reference-free Evaluation Metric for Image Captioning
- Do We Really Need Dice? The Hidden Region-Size Biases of Segmentation Losses
- Deep Latent Emotion Network for Multi-Task Learning
- PaCo: Preconditions Attributed to Commonsense Knowledge
- Simple and Efficient ways to Improve REALM
- Complexity Lower Bounds for Nonconvex-Strongly-Concave Min-Max Optimization
- A Token-level Reference-free Hallucination Detection Benchmark for Free-form Text Generation
- Reconsidering CO2 emissions from Computer Vision
- Intent Features for Rich Natural Language Understanding
- Lottery Jackpots Exist in Pre-trained Models
- A Simple and Effective Positional Encoding for Transformers
- OSKDet: Towards Orientation-sensitive Keypoint Localization for Rotated Object Detection
- Knowledge Neurons in Pretrained Transformers
- Model Error Propagation via Learned Contraction Metrics for Safe Feedback Motion Planning of Unknown Systems
- MT6: Multilingual Pretrained Text-to-Text Transformer with Translation Pairs
- The Power of Scale for Parameter-Efficient Prompt Tuning
- Rethinking Image-Scaling Attacks: The Interplay Between Vulnerabilities in Machine Learning Systems
- RPCL: A Framework for Improving Cross-Domain Detection with Auxiliary Tasks
- Signal Processing Challenges and Examples for it in-situ Transmission Electron Microscopy
- Linguistic Dependencies and Statistical Dependence
- Self-Supervised Pillar Motion Learning for Autonomous Driving
- Rethinking Network Pruning -- under the Pre-train and Fine-tune Paradigm
- Guilt by Association: Emotion Intensities in Lexical Representations
- Improving Question Answering Model Robustness with Synthetic Adversarial Data Generation
- From Fully Trained to Fully Random Embeddings: Improving Neural Machine Translation with Compact Word Embedding Tables
- Distributed NLI: Learning to Predict Human Opinion Distributions for Language Reasoning
- Dual-View Distilled BERT for Sentence Embedding
- "Average" Approximates "First Principal Component"? An Empirical Analysis on Representations from Neural Language Models
- When Does Pretraining Help? Assessing Self-Supervised Learning for Law and the CaseHOLD Dataset
- Generating Related Work
- SIMMC 2.0: A Task-oriented Dialog Dataset for Immersive Multimodal Conversations
- Worst of Both Worlds: Biases Compound in Pre-trained Vision-and-Language Models