Papers
Fri 15 Apr 2022
140 papers
- MoEBERT: from BERT to Mixture-of-Experts via Importance-Guided AdaptationMixture-of-experts → MoE large language models
- CILDA: Contrastive Data Augmentation using Intermediate Layer Knowledge DistillationKnowledge distillation → Knowledge distillation for LLMs
- Deep Unlearning via Randomized Conditionally Independent HessiansLLM safety and security → Machine unlearning
- Evaluating the Effectiveness of Corrective Demonstrations and a Low-Cost Sensor for Dexterous ManipulationOffline RL and imitation learning from data → Robot manipulation imitation learning
- Mixture of Experts for Biomedical Question AnsweringMixture-of-experts → Medical and biomedical MoE
- COTS: Collaborative Two-Stream Vision-Language Pre-Training Model for Cross-Modal RetrievalMultimodal LLMs / vision-language models → Document understanding and multimodal RAG
- Towards Fine-grained Causal Reasoning and QALLM reasoning → Causal reasoning in LLMs
- Divide & Conquer Imitation LearningOffline RL and imitation learning from data → Imitation learning methods
- Ensemble diverse hypotheses and knowledge distillation for unsupervised cross-subject adaptationKnowledge distillation → General knowledge distillation methods
- Semantic Structure based Query Graph Prediction for Question Answering over Knowledge Graph
- Simulation of machine learning-based 6G systems in virtual worlds
- Deep learning based closed-loop optimization of geothermal reservoir production
- Intelligent Spatial Interpolation-based Frost Prediction Methodology using Artificial Neural Networks with Limited Local Data
- DialAug: Mixing up Dialogue Contexts in Contrastive Learning for Robust Conversational Modeling
- Self-Similarity Priors: Neural Collages as Differentiable Fractal Representations
- Just Fine-tune Twice: Selective Differential Privacy for Large Language Models
- Designing Creative AI Partners with COFI: A Framework for Modeling Interaction in Human-AI Co-Creative Systems
- Conditional Injective Flows for Bayesian Imaging
- Spanish Abstract Meaning Representation: Annotation of a General Corpus
- Finding Pareto Trade-offs in Fair and Accurate Detection of Toxic Speech
- It is Okay to Not Be Okay: Overcoming Emotional Bias in Affective Image Captioning by Contrastive Data Collection
- Detection of sepsis during emergency department triage using machine learning
- Learning time-dependent PDE solver using Message Passing Graph Neural Networks
- MultiEarth 2022 -- Multimodal Learning for Earth and Environment Workshop and Challenge
- Identifying Ethical Issues in AI Partners in Human-AI Co-Creation
- Investigating Positive and Negative Qualities of Human-in-the-Loop Optimization for Designing Interaction Techniques
- Event-aided Direct Sparse Odometry
- Towards a Stronger Theory for Permutation-based Evolutionary Algorithms
- Lagrangian Motion Magnification with Double Sparse Optical Flow Decomposition
- A generative neural network model for random dot product graphs
- Multi-Frame Self-Supervised Depth with Transformers
- TabNAS: Rejection Sampling for Neural Architecture Search on Tabular Datasets
- DeepCSI: Rethinking Wi-Fi Radio Fingerprinting Through MU-MIMO CSI Feedback Deep Learning
- Y-Net: A Spatiospectral Dual-Encoder Networkfor Medical Image Segmentation
- Contextualizing Artificially Intelligent Morality: A Meta-Ethnography of Top-Down, Bottom-Up, and Hybrid Models for Theoretical and Applied Ethics in Artificial Intelligence
- Sources of Irreproducibility in Machine Learning: A Review
- Learning to Adapt Domain Shifts of Moral Values via Instance Weighting
- In-BoXBART: Get Instructions into Biomedical Multi-Task Learning
- Perfectly Balanced: Improving Transfer and Robustness of Supervised Contrastive Learning
- mGPT: Few-Shot Learners Go Multilingual
- Interpretable Fault Diagnosis of Rolling Element Bearings with Temporal Logic Neural Network
- The Distributed Information Bottleneck reveals the explanatory structure of complex systems
- Evaluation Benchmarks for Spanish Sentence Representations
- Deep Learning-based List Sphere Decoding for Faster-than-Nyquist (FTN) Signaling Detection
- Evaluating Factuality in Text Simplification
- Streaming Align-Refine for Non-autoregressive Deliberation
- Chinese Idiom Paraphrasing
- Efficient Architecture Search for Diverse Tasks
- Improving Rare Word Recognition with LM-aware MWER Training
- Summarization with Graphical Elements
- Human Judgement as a Compass to Navigate Automatic Metrics for Formality Transfer
- Learning Multi-View Aggregation In the Wild for Large-Scale 3D Semantic Segmentation
- Semi-supervised atmospheric component learning in low-light image problem
- CryoRL: Reinforcement Learning Enables Efficient Cryo-EM Data Collection
- Selecting Continuous Life-Like Cellular Automata for Halting Unpredictability: Evolving for Abiogenesis
- Unconditional Image-Text Pair Generation with Multimodal Cross Quantizer
- Accurate ADMET Prediction with XGBoost
- Understanding Game-Playing Agents with Natural Language Annotations
- Statistical-Computational Trade-offs in Tensor PCA and Related Problems via Communication Complexity
- Neural Structured Prediction for Inductive Node Classification
- Resource-Aware Distributed Submodular Maximization: A Paradigm for Multi-Robot Decision-Making
- Synthesizing Informative Training Samples with GAN
- Improving Passage Retrieval with Zero-Shot Question Generation
- A Machine Learning Tutorial for Operational Meteorology, Part I: Traditional Machine Learning
- Patch-wise Contrastive Style Learning for Instagram Filter Removal
- Polling Latent Opinions: A Method for Computational Sociolinguistics Using Transformer Language Models
- Towards PAC Multi-Object Detection and Tracking
- Knowledge Equivalence in Digital Twins of Intelligent Systems
- Guiding Attention using Partial-Order Relationships for Image Captioning
- Kernel similarity matching with Hebbian neural networks
- The Importance of Credo in Multiagent Learning
- Sensitivity of sparse codes to image distortions
- Improving Pre-trained Language Models with Syntactic Dependency Prediction Task for Chinese Semantic Error Recognition
- ORCNet: A context-based network to simultaneously segment the ocular region components
- Stretching Sentence-pair NLI Models to Reason over Long Documents and Clusters
- Detecting Violence in Video Based on Deep Features Fusion Technique
- Scalable and Real-time Multi-Camera Vehicle Detection, Re-Identification, and Tracking
- INSTA-BNN: Binary Neural Network with INSTAnce-aware Threshold
- Transfer Learning for Instance Segmentation of Waste Bottles using Mask R-CNN Algorithm
- Political Communities on Twitter: Case Study of the 2022 French Presidential Election
- ERGO: Event Relational Graph Transformer for Document-level Event Causality Identification
- ML_LTU at SemEval-2022 Task 4: T5 Towards Identifying Patronizing and Condescending Language
- The Importance of Landscape Features for Performance Prediction of Modular CMA-ES Variants
- Experimentally realized memristive memory augmented neural network
- Decision-making with E-admissibility given a finite assessment of choices
- An interpretable machine learning approach for ferroalloys consumptions
- Deep CardioSound-An Ensembled Deep Learning Model for Heart Sound MultiLabelling
- Safe Reinforcement Learning Using Black-Box Reachability Analysis
- Universal approximation property of invertible neural networks
- SOTVerse: A User-defined Task Space of Single Object Tracking
- Super Resolution for Turbulent Flows in 2D: Stabilized Physics Informed Neural Networks
- End-to-End Sensitivity-Based Filter Pruning
- SSR-HEF: Crowd Counting with Multi-Scale Semantic Refining and Hard Example Focusing
- Deep learning model solves change point detection for multiple change types
- FasterVideo: Efficient Online Joint Object Detection And Tracking
- Characterizing metastable states with the help of machine learning
- Email Spam Detection Using Hierarchical Attention Hybrid Deep Learning Method
- Crowd counting with segmentation attention convolutional neural network
- Image Captioning In the Transformer Age
- Revisiting the Adversarial Robustness-Accuracy Tradeoff in Robot Learning
All 140
- A Personalized Dialogue Generator with Implicit User Persona Detection
- 2D Human Pose Estimation: A Survey
- On the Role of Pre-trained Language Models in Word Ordering: A Case Study with BART
- ResT V2: Simpler, Faster and Stronger
- Is Surprisal in Issue Trackers Actionable?
- Spatio-Temporal-Frequency Graph Attention Convolutional Network for Aircraft Recognition Based on Heterogeneous Radar Network
- Text Revision by On-the-Fly Representation Optimization
- Prototype-based Domain Generalization Framework for Subject-Independent Brain-Computer Interfaces
- Vision-and-Language Pretrained Models: A Survey
- Anomalous Sound Detection Based on Machine Activity Detection
- A Differentially Private Probabilistic Framework for Modeling the Variability Across Federated Datasets of Heterogeneous Multi-View Observations
- Condition-Invariant and Compact Visual Place Description by Convolutional Autoencoder
- Crowd counting with crowd attention convolutional neural network
- MVSTER: Epipolar Transformer for Efficient Multi-View Stereo
- CAiD: Context-Aware Instance Discrimination for Self-supervised Learning in Medical Imaging
- LaMemo: Language Modeling with Look-Ahead Memory
- Training Entire-Space Models for Target-oriented Opinion Words Extraction
- A Keypoint-based Global Association Network for Lane Detection
- Knowledgebra: An Algebraic Learning Framework for Knowledge Graph
- Graph Pooling for Graph Neural Networks: Progress, Challenges, and Opportunities
- XDBERT: Distilling Visual Information to BERT from Cross-Modal Systems to Improve Language Understanding
- Feature Compression for Rate Constrained Object Detection on the Edge
- Structural Analysis of Branch-and-Cut and the Learnability of Gomory Mixed Integer Cuts
- MetaSets: Meta-Learning on Point Sets for Generalizable Representations
- Saga: A Platform for Continuous Construction and Serving of Knowledge At Scale
- Pushing the Limits of Simple Pipelines for Few-Shot Learning: External Data and Fine-Tuning Make a Difference
- Improving Cross-Modal Understanding in Visual Dialog via Contrastive Learning
- Dense Learning based Semi-Supervised Object Detection
- Where to Go for the Holidays: Towards Mixed-Type Dialogs for Clarification of User Goals
- Towards a Unified Framework for Uncertainty-aware Nonlinear Variable Selection with Theoretical Guarantees
- Unsupervised Probabilistic Models for Sequential Electronic Health Records
- The training response law explains how deep neural networks learn
- Identifying and Measuring Token-Level Sentiment Bias in Pre-trained Language Models with Prompts
- Characterizing the Efficiency vs. Accuracy Trade-off for Long-Context NLP Models
- Guided Co-Modulated GAN for 360deg Field of View Extrapolation
- Invisible-to-Visible: Privacy-Aware Human Instance Segmentation using Airborne Ultrasound via Collaborative Learning Variational Autoencoder
- auton-survival: an Open-Source Package for Regression, Counterfactual Estimation, Evaluation and Phenotyping with Censored Time-to-Event Data
- Incremental Prompting: Episodic Memory Prompt for Lifelong Event Detection
- Automated speech tools for helping communities process restricted-access corpora for language revival efforts
- Model-agnostic Multi-Domain Learning with Domain-Specific Adapters for Action Recognition