Papers
Wed 15 Dec 2021
196 papers
- Learning Cross-Lingual IR from an English RetrieverKnowledge distillation → Knowledge distillation for LLMs
- Automatic tuning of hyper-parameters of reinforcement learning algorithms using Bayesian optimization with behavioral cloningOffline RL and imitation learning from data → Offline RL algorithms
- Decoupling Zero-Shot Semantic SegmentationMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
- Tracing Text Provenance via Context-Aware Lexical SubstitutionLLM safety and security → Watermarking generated content and models
- Tackling the Generative Learning Trilemma with Denoising Diffusion GANsDiffusion models → Diffusion foundations and sampling
- Do You See What I See? Capabilities and Limits of Automated Multimedia Content Analysis
- DeepScalper: A Risk-Aware Reinforcement Learning Framework to Capture Fleeting Intraday Trading Opportunities
- Selecting the suitable resampling strategy for imbalanced data classification regarding dataset properties
- Overview of the EEG Pilot Subtask at MediaEval 2021: Predicting Media Memorability
- Encoding protein dynamic information in graph representation for functional residue identification
- Automatic Product Copywriting for E-Commerce
- Assisted Text Annotation Using Active Learning to Achieve High Quality with Little Effort
- Interpretable Knowledge Tracing: Simple and Efficient Student Modeling with Causal Relations
- CPPE-5: Medical Personal Protective Equipment Dataset
- LTB curves with Lipschitz turn are par-regular
- Confidence-Aware Subject-to-Subject Transfer Learning for Brain-Computer Interface
- SanMove: Next Location Recommendation via Self-Attention Network
- Advancing Spiking Neural Networks towards Deep Residual Learning
- Responsive parallelized architecture for deploying deep learning models in production environments
- COVID-19 Electrocardiograms Classification using CNN Models
- Deep Generative Models for Geometric Design Under Uncertainty
- Penn-Helsinki Parsed Corpus of Early Modern English: First Parsing Results and Analysis
- Invariance Through Latent Alignment
- FLoRA: Single-shot Hyper-parameter Optimization for Federated Learning
- DocAMR: Multi-Sentence AMR Representation and Evaluation
- ELight: Enabling Efficient Photonic In-Memory Neurocomputing with Life Enhancement
- OptABC: an Optimal Hyperparameter Tuning Approach for Machine Learning Algorithms
- Algorithms for Adaptive Experiments that Trade-off Statistical Analysis with Reward: Combining Uniform Random Assignment and Reward Maximization
- Predicting Levels of Household Electricity Consumption in Low-Access Settings
- StyleMC: Multi-Channel Based Fast Text-Guided Image Generation and Manipulation
- Human Languages with Greater Information Density Increase Communication Speed, but Decrease Conversation Breadth
- Text Mining Through Label Induction Grouping Algorithm Based Method
- Gaining Outlier Resistance with Progressive Quantiles: Fast Algorithms and Theoretical Studies
- Insta-VAX: A Multimodal Benchmark for Anti-Vaccine and Misinformation Posts Detection on Social Media
- ErAConD : Error Annotated Conversational Dialog Dataset for Grammatical Error Correction
- Applying SoftTriple Loss for Supervised Language Model Fine Tuning
- Rethinking Nearest Neighbors for Visual Classification
- Curriculum learning for data-driven modeling of dynamical systems
- Dense Video Captioning Using Unsupervised Semantic Information
- The Need for Ethical, Responsible, and Trustworthy Artificial Intelligence for Environmental Sciences
- Quantum Algorithms for Reinforcement Learning with a Generative Model
- Positional Encoding Augmented GAN for the Assessment of Wind Flow for Pedestrian Comfort in Urban Areas
- Torch.fx: Practical Program Capture and Transformation for Deep Learning in Python
- A White-Box SVM Framework and its Swarm-Based Optimization for Supervision of Toothed Milling Cutter through Characterization of Spindle Vibrations
- Neural Network-based Power Flow Model
- Characterization of causal ancestral graphs for time series with latent confounders
- Real-time Detection of Anomalies in Multivariate Time Series of Astronomical Data
- DSGPT: Domain-Specific Generative Pre-Training of Transformers for Text Generation in E-commerce Title and Review Summarization
- Quantum Model Learning Agent: characterisation of quantum systems through machine learning
- Breeding realistic D-brane models
- Lifelong Generative Modelling Using Dynamic Expansion Graph Model
- Feature-Attending Recurrent Modules for Generalization in Reinforcement Learning
- AGMI: Attention-Guided Multi-omics Integration for Drug Response Prediction with Graph Neural Networks
- Data Valuation for Vertical Federated Learning: A Model-free and Privacy-preserving Method
- 3D Question Answering
- Design Challenges for a Multi-Perspective Search Engine
- Estimating Uncertainty For Vehicle Motion Prediction on Yandex Shifts Dataset
- Textless Speech-to-Speech Translation on Real Data
- Database Search Results Disambiguation for Task-Oriented Dialog Systems
- Prompt Waywardness: The Curious Case of Discretized Interpretation of Continuous Prompts
- Simple Text Detoxification by Identifying a Linear Toxic Subspace in Language Model Embeddings
- Reliable Multi-Object Tracking in the Presence of Unreliable Detections
- DG2: Data Augmentation Through Document Grounded Dialogue Generation
- GenIE: Generative Information Extraction
- AllWOZ: Towards Multilingual Task-Oriented Dialog Systems for All
- Model Stealing Attacks Against Inductive Graph Neural Networks
- Evaluating Pretrained Transformer Models for Entity Linking in Task-Oriented Dialog
- Is "My Favorite New Movie" My Favorite Movie? Probing the Understanding of Recursive Noun Phrases
- ForgeryNet -- Face Forgery Analysis Challenge 2021: Methods and Results
- Know Thy Strengths: Comprehensive Dialogue State Tracking Diagnostics
- Measure and Improve Robustness in NLP Models: A Survey
- On the Convergence and Robustness of Adversarial Training
- Rethinking Influence Functions of Neural Networks in the Over-parameterized Regime
- Decomposing Natural Logic Inferences in Neural NLI
- Improving Both Domain Robustness and Domain Adaptability in Machine Translation
- Detecting Object States vs Detecting Objects: A New Dataset and a Quantitative Experimental Study
- SeqFormer: Sequential Transformer for Video Instance Segmentation
- Putting People in their Place: Monocular Regression of 3D People in Depth
- Prescriptive Machine Learning for Automated Decision Making: Challenges and Opportunities
- KGR^4: Retrieval, Retrospect, Refine and Rethink for Commonsense Generation
- One System to Rule them All: a Universal Intent Recognition System for Customer Service Chatbots
- Est-ce que vous compute? Code-switching, cultural identity, and AI
- Online Feature Selection for Efficient Learning in Networked Systems
- Predicting the utility of search spaces for black-box optimization: a simple, budget-aware approach
- RA V-Net: Deep learning network for automated liver segmentation
- An Experimental Study of the Impact of Pre-training on the Pruning of a Convolutional Neural Network
- Disparities in Social Determinants among Performances of Mortality Prediction with Machine Learning for Sepsis Patients
- Guaranteed Trajectory Tracking under Learned Dynamics with Contraction Metrics and Disturbance Estimation
- Quantitative analysis of visual representation of sign elements in COVID-19 context
- Probabilistic Forecasting with Generative Networks via Scoring Rule Minimization
- Enhancing operations management through smart sensors: measuring and improving well-being, interaction and performance of logistics workers
- TrialGraph: Machine Intelligence Enabled Insight from Graph Modelling of Clinical Trials
- Taming Overconfident Prediction on Unlabeled Data from Hindsight
- N3H-Core: Neuron-designed Neural Network Accelerator via FPGA-based Heterogeneous Computing Cores
- Lesan -- Machine Translation for Low Resource Languages
- Planning with Biological Neurons and Synapses
- Hierarchical Variational Memory for Few-shot Learning Across Domains
- Multi-View Depth Estimation by Fusing Single-View Depth Probability with Multi-View Geometry
- Chimpanzee voice prints? Insights from transfer learning experiments from human voices
- One size does not fit all: Investigating strategies for differentially-private learning across NLP tasks
All 196
- Faster Nearest Neighbor Machine Translation
- Improving Conversational Recommendation Systems' Quality with Context-Aware Item Meta Information
- Characterizing the Program Expressive Power of Existential Rule Languages
- Improving Self-supervised Learning with Automated Unsupervised Outlier Arbitration
- Exponential Convergence of Deep Operator Networks for Elliptic Partial Differential Equations
- Self-Supervised Monocular Depth and Ego-Motion Estimation in Endoscopy: Appearance Flow to the Rescue
- Vision Transformer Based Video Hashing Retrieval for Tracing the Source of Fake Videos
- Robust Neural Network Classification via Double Regularization
- Mask-combine Decoding and Classification Approach for Punctuation Prediction with real-time Inference Constraints
- Towards Controllable Agent in MOBA Games with Generative Modeling
- Ensuring DNN Solution Feasibility for Optimization Problems with Convex Constraints and Its Application to DC Optimal Power Flow Problems
- Image-Adaptive YOLO for Object Detection in Adverse Weather Conditions
- Cognition-aware Cognate Detection
- Joint Demand Prediction for Multimodal Systems: A Multi-task Multi-relational Spatiotemporal Graph Neural Network Approach
- Fast characterization of inducible regions of atrial fibrillation models with multi-fidelity Gaussian process classification
- Depth Refinement for Improved Stereo Reconstruction
- Funnels: Exact maximum likelihood with dimensionality reduction
- Head Matters: Explainable Human-centered Trait Prediction from Head Motion Dynamics
- Leveraging Image-based Generative Adversarial Networks for Time Series Generation
- Building separable approximations for quantum states via neural networks
- Optimal Latent Space Forecasting for Large Collections of Short Time Series Using Temporal Matrix Factorization
- Exploring the Asynchronous of the Frequency Spectra of GAN-generated Facial Images
- Dynamic Human Evaluation for Relative Model Comparisons
- LookinGoodπ: Real-time Person-independent Neural Re-rendering for High-quality Human Performance Capture
- Named entity recognition architecture combining contextual and global features
- TLogic: Temporal Logical Rules for Explainable Link Forecasting on Temporal Knowledge Graphs
- Segmentation-Reconstruction-Guided Facial Image De-occlusion
- MissMarple : A Novel Socio-inspired Feature-transfer Learning Deep Network for Image Splicing Detection
- Consistent Depth Prediction under Various Illuminations using Dilated Cross Attention
- Autoencoder-based background reconstruction and foreground segmentation with background noise estimation
- Self-Ensembling GAN for Cross-Domain Semantic Segmentation
- Multi-modal Networks Reveal Patterns of Operational Similarity of Terrorist Organizations
- Domain-informed neural networks for interaction localization within astroparticle experiments
- Supervised learning of analysis-sparsity priors with automatic differentiation
- Solving the Data Sparsity Problem in Predicting the Success of the Startups with Machine Learning Methods
- Temporal Action Proposal Generation with Background Constraint
- Detail-aware Deep Clothing Animations Infused with Multi-source Attributes
- Predicting Media Memorability: Comparing Visual, Textual and Auditory Features
- Modality-Aware Triplet Hard Mining for Zero-shot Sketch-Based Image Retrieval
- Towards General and Efficient Active Learning
- A learning-based approach to feature recognition of Engineering shapes
- FEAR: Fast, Efficient, Accurate and Robust Visual Tracker
- Channel Parameter Estimation in the Presence of Phase Noise Based on Maximum Correntropy Criterion
- Object Pursuit: Building a Space of Objects via Discriminative Weight Generation
- Transcoded Video Restoration by Temporal Spatial Auxiliary Network
- Efficient Geometry-aware 3D Generative Adversarial Networks
- The exploitation of Multiple Feature Extraction Techniques for Speaker Identification in Emotional States under Disguised Voices
- Analysis and Evaluation of Synchronous and Asynchronous FLchain
- Graph Representation Learning via Contrasting Cluster Assignments
- From Noise to Feature: Exploiting Intensity Distribution as a Novel Soft Biometric Trait for Finger Vein Recognition
- Imagine by Reasoning: A Reasoning-Based Implicit Semantic Data Augmentation for Long-Tailed Classification
- Knowledge-Grounded Dialogue Generation with a Unified Knowledge Representation
- Ten years of image analysis and machine learning competitions in dementia
- Temporal Shuffling for Defending Deep Action Recognition Models against Adversarial Attacks
- M-FasterSeg: An Efficient Semantic Segmentation Network Based on Neural Architecture Search
- SPTS: Single-Point Text Spotting
- LongT5: Efficient Text-To-Text Transformer for Long Sequences
- A Comparative Analysis of Machine Learning Approaches for Automated Face Mask Detection During COVID-19
- Homography Decomposition Networks for Planar Object Tracking
- Energy-Efficient Real-Time Heart Monitoring on Edge-Fog-Cloud Internet-of-Medical-Things
- Large Dual Encoders Are Generalizable Retrievers
- Tight query complexity bounds for learning graph partitions
- Robust Depth Completion with Uncertainty-Driven Loss Functions
- Graph-based Ensemble Machine Learning for Student Performance Prediction
- Zero-shot Audio Source Separation through Query-based Learning from Weakly-labeled Data
- Investigating myocardial infarction and its effects in patients with urgent medical problems using advanced data mining tools
- Event Linking: Grounding Event Mentions to Wikipedia
- Knowledge-Rich Self-Supervision for Biomedical Entity Linking
- Experimental quantum advantage with quantum coupon collector
- Lex Rosetta: Transfer of Predictive Models Across Languages, Jurisdictions, and Legal Domains
- Does a Face Mask Protect my Privacy?: Deep Learning to Predict Protected Attributes from Masked Face Images
- Gaze Estimation with Eye Region Segmentation and Self-Supervised Multistream Learning
- Learning to Transpile AMR into SPARQL
- Linguistic Frameworks Go Toe-to-Toe at Neuro-Symbolic Language Modeling
- Cross-Domain Generalization and Knowledge Transfer in Transformers Trained on Legal Data
- Fine-Tuning Large Neural Language Models for Biomedical Natural Language Processing
- Few-shot Instruction Prompts for Pretrained Language Models to Detect Social Biases
- Interscript: A dataset for interactive learning of scripts through error feedback
- Fast Computation of Generalized Eigenvectors for Manifold Graph Embedding
- Finite-Sample Analysis of Decentralized Q-Learning for Stochastic Games
- EDAssistant: Supporting Exploratory Data Analysis in Computational Notebooks with In-Situ Code Search and Recommendation
- HyObscure: Hybrid Obscuring for Privacy-Preserving Data Publishing
- Probabilistic Logic Gate in Asynchronous Game of Life with Critical Property
- Fix your Models by Fixing your Datasets
- LoSAC: An Efficient Local Stochastic Average Control Method for Federated Optimization
- Central-Smoothing Hypergraph Neural Networks for Predicting Drug-Drug Interactions
- Communication-Efficient Distributed SGD with Compressed Sensing
- Mining Minority-class Examples With Uncertainty Estimates
- TAFA: Design Automation of Analog Mixed-Signal FIR Filters Using Time Approximation Architecture
- Analog/Mixed-Signal Circuit Synthesis Enabled by the Advancements of Circuit Architectures and Machine Learning Algorithms
- Bayesian Graph Contrastive Learning
- Value Retrieval with Arbitrary Queries for Form-like Documents
- Weed Recognition using Deep Learning Techniques on Class-imbalanced Imagery
- Structure-Aware Image Segmentation with Homotopy Warping
- Representation Alignment in Neural Networks
- Network Graph Based Neural Architecture Search