Papers
Wed 15 Sep 2021
190 papers
- DCUR: Data Curriculum for Teaching via Samples with Reinforcement LearningOffline RL and imitation learning from data → Offline RL algorithms
- What Vision-Language Models `See' when they See ScenesMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
- DROMO: Distributionally Robust Offline Model-based Policy OptimizationOffline RL and imitation learning from data → Offline RL algorithms
- EfficientBERT: Progressively Searching Multilayer Perceptron via Warm-up Knowledge DistillationKnowledge distillation → Knowledge distillation for LLMs
- Self-Training with Differentiable TeacherKnowledge distillation → General knowledge distillation methods
- Prefix-to-SQL: Text-to-SQL Generation from Incomplete User Questions
- Forecasting of COVID-19 Cases, Using an Evolutionary Neural Architecture Search Approach
- Automatic Plane Adjustment of Orthopedic Intra-operative Flat Panel Detector CT-Volumes
- Conditionally Parameterized, Discretization-Aware Neural Networks for Mesh-Based Modeling of Physical Systems
- A Computable Piece of Uncomputable Art whose Expansion May Explain the Universe in Software Space
- Karpov's Queen Sacrifices and AI
- Accurately Modeling Biased Random Walks on Weighted Graphs Using textitNode2vec+
- Image Captioning for Effective Use of Language Models in Knowledge-Based Visual Question Answering
- Neural Architecture Search in operational context: a remote sensing case-study
- Behavior of Keyword Spotting Networks Under Noisy Conditions
- FSER: Deep Convolutional Neural Networks for Speech Emotion Recognition
- Proceedings 37th International Conference on Logic Programming (Technical Communications)
- BacHMMachine: An Interpretable and Scalable Model for Algorithmic Harmonization for Four-part Baroque Chorales
- Towards Zero-shot Cross-lingual Image Retrieval and Tagging
- On-the-Fly Ensemble Pruning in Evolving Data Streams
- Partner-Assisted Learning for Few-Shot Image Classification
- Comparing Feature-Engineering and Feature-Learning Approaches for Multilingual Translationese Classification
- Interpretable Additive Recurrent Neural Networks For Multivariate Clinical Time Series
- A Column Streaming-Based Convolution Engine and Mapping Algorithm for CNN-based Edge AI accelerators
- Modern Cybersecurity Solution using Supervised Machine Learning
- UCP-Net: Unstructured Contour Points for Instance Segmentation
- On the Complementarity of Data Selection and Fine Tuning for Domain Adaptation
- CONTaiNER: Few-Shot Named Entity Recognition via Contrastive Learning
- An influencer-based approach to understanding radical right viral tweets
- Multi-Task Learning with Sequence-Conditioned Transporter Networks
- Predicting 3D shapes, masks, and properties of materials, liquids, and objects inside transparent containers, using the TransProteus CGI dataset
- "It doesn't look good for a date": Transforming Critiques into Preferences for Conversational Recommendation Systems
- Estimation of Warfarin Dosage with Reinforcement Learning
- Non-smooth Bayesian Optimization in Tuning Problems
- A Framework for Multisensory Foresight for Embodied Agents
- Hybrid ICP
- CounterNet: End-to-End Training of Prediction Aware Counterfactual Explanations
- Unit Selection with Causal Diagram
- RaWaNet: Enriching Graph Neural Network Input via Random Walks on Graphs
- A Pathology Deep Learning System Capable of Triage of Melanoma Specimens Utilizing Dermatopathologist Consensus as Ground Truth
- Learning the Regularization in DCE-MR Image Reconstruction for Functional Imaging of Kidneys
- RAFT-Stereo: Multilevel Recurrent Field Transforms for Stereo Matching
- Text as Causal Mediators: Research Design for Causal Estimates of Differential Treatment of Social Groups via Language Aspects
- Pose Transformers (POTR): Human Motion Prediction with Non-Autoregressive Transformers
- Discovering Useful Compact Sets of Sequential Rules in a Long Sequence
- DeepMetis: Augmenting a Deep Learning Test Set to Increase its Mutation Score
- Tied & Reduced RNN-T Decoder
- Learning to Aggregate and Refine Noisy Labels for Visual Sentiment Analysis
- Dialogue State Tracking with a Language Model using Schema-Driven Prompting
- Federated Contrastive Learning for Decentralized Unlabeled Medical Images
- Short Quantum Circuits in Reinforcement Learning Policies for the Vehicle Routing Problem
- Sign-MAML: Efficient Model-Agnostic Meta-Learning by SignSGD
- Making Heads and Tails of Models with Marginal Calibration for Sparse Tagsets
- Comparing Euclidean and Hyperbolic Embeddings on the WordNet Nouns Hypernymy Graph
- Cross-Register Projection for Headline Part of Speech Tagging
- Generalized XGBoost Method
- Neural network optimal feedback control with enhanced closed loop stability
- On the Limits of Minimal Pairs in Contrastive Evaluation
- AnnIE: An Annotation Platform for Constructing Complete Open Information Extraction Benchmark
- MPC-Friendly Commitments for Publicly Verifiable Covert Security
- Efficient Domain Adaptation of Language Models via Adaptive Tokenization
- Comparing Text Representations: A Theory-Driven Approach
- Deep Bregman Divergence for Contrastive Learning of Visual Representations
- Can Machines Read Coding Manuals Yet? -- A Benchmark for Building Better Language Models for Code Understanding
- WikiGUM: Exhaustive Entity Linking for Wikification in 12 Genres
- Neural Human Performer: Learning Generalizable Radiance Fields for Human Performance Rendering
- When Does Translation Require Context? A Data-driven, Multilingual Exploration
- Challenges in Detoxifying Language Models
- Is "moby dick" a Whale or a Bird? Named Entities and Terminology in Speech Translation
- CAMul: Calibrated and Accurate Multi-view Time-Series Forecasting
- Should We Be Pre-training? An Argument for End-task Aware Training as an Alternative
- Computing Policies That Account For The Effects Of Human Agent Uncertainty During Execution In Markov Decision Processes
- Discriminative and Generative Transformer-based Models For Situation Entity Classification
- Contact-Aware Retargeting of Skinned Motion
- A Wide-area, Low-latency, and Power-efficient 6-DoF Pose Tracking System for Rigid Objects
- SupCL-Seq: Supervised Contrastive Learning for Downstream Optimized Sequence Representations
- Gaussian Moments as Physically Inspired Molecular Descriptors for Accurate and Scalable Machine Learning Potentials
- Union: A Unified HW-SW Co-Design Ecosystem in MLIR for Evaluating Tensor Operations on Spatial Accelerators
- Semi-supervised Contrastive Learning for Label-efficient Medical Image Segmentation
- BERT is Robust! A Case Against Synonym-Based Adversarial Examples in Text Classification
- Multi View Spatial-Temporal Model for Travel Time Estimation
- Matching with Transformers in MELT
- Disentangling Generative Factors of Physical Fields Using Variational Autoencoders
- Constraint based Knowledge Base Distillation in End-to-End Task Oriented Dialogs
- Can one hear the shape of a neural network?: Snooping the GPU via Magnetic Side Channel
- How to use KL-divergence to construct conjugate priors, with well-defined non-informative limits, for the multivariate Gaussian
- RankNAS: Efficient Neural Architecture Search by Pairwise Ranking
- Topic Transferable Table Question Answering
- A Unified Framework for Biphasic Facial Age Translation with Noisy-Semantic Guided Generative Adversarial Networks
- Self-learn to Explain Siamese Networks Robustly
- Direct and Sparse Deformable Tracking
- Learning When to Translate for Streaming Speech
- Towards Incremental Transformers: An Empirical Analysis of Transformer Models for Incremental NLU
- Modular Neural Ordinary Differential Equations
- Fermion Sampling Made More Efficient
- Learning Dynamical Human-Joint Affinity for 3D Pose Estimation in Videos
- The ELITR ECA Corpus
- Cross-lingual Transfer of Monolingual Models
- Introducing an Abusive Language Classification Framework for Telegram to Investigate the German Hater Community
- The potential of self-supervised networks for random noise suppression in seismic data
All 190
- Midheind's WMT 2021 submission
- Distribution-free Contextual Dynamic Pricing
- S3LAM: Structured Scene SLAM
- Comparing decision mining approaches with regard to the meaningfulness of their results
- PointManifoldCut: Point-wise Augmentation in the Manifold for Point Clouds
- FORTAP: Using Formulas for Numerical-Reasoning-Aware Table Pretraining
- DeFungi: Direct Mycological Examination of Microscopic Fungi Images
- PoWareMatch: a Quality-aware Deep Learning Approach to Improve Human Schema Matching
- MD-CSDNetwork: Multi-Domain Cross Stitched Network for Deepfake Detection
- Allocating Large Vocabulary Capacity for Cross-lingual Language Model Pre-training
- FFAVOD: Feature Fusion Architecture for Video Object Detection
- New Perspective on Progressive GANs Distillation for One-class Novelty Detection
- Unsupervised Keyphrase Extraction by Jointly Modeling Local and Global Context
- Sequence Length is a Domain: Length-based Overfitting in Transformer Models
- NBcoded: network attack classifiers based on Encoder and Naive Bayes model for resource limited devices
- Distract Your Attention: Multi-head Cross Attention Network for Facial Expression Recognition
- Modelling Major Disease Outbreaks in the 21st Century: A Causal Approach
- Scope resolution of predicted negation cues: A two-step neural network-based approach
- End-to-End Learning of Flowchart Grounded Task-Oriented Dialogs
- Modeling the effects of environmental and perceptual uncertainty using deterministic reinforcement learning dynamics with partial observability
- Federated Learning of Molecular Properties with Graph Neural Networks in a Heterogeneous Setting
- Integrating Sensing and Communication in Cellular Networks via NR Sidelink
- Temporal Parameter-free Deep Skinning of Animated Meshes
- Towards Precise Pruning Points Detection using Semantic-Instance-Aware Plant Models for Grapevine Winter Pruning Automation
- RGB-D Saliency Detection via Cascaded Mutual Information Minimization
- Navigation-Oriented Scene Understanding for Robotic Autonomy: Learning to Segment Driveability in Egocentric Images
- Enhancing Clinical Information Extraction with Transferred Contextual Embeddings
- Regressive Ensemble for Machine Translation Quality Evaluation
- Internet of Behavior (IoB) and Explainable AI Systems for Influencing IoT Behavior
- The Unreasonable Effectiveness of the Baseline: Discussing SVMs in Legal Text Classification
- SWEAT: Scoring Polarization of Topics across Different Corpora
- Learning Mathematical Properties of Integers
- Dialog speech sentiment classification for imbalanced datasets
- How Much do Lyrics Matter? Analysing Lyrical Simplicity Preferences for Individuals At Risk of Depression
- Progressive Hard-case Mining across Pyramid Levels for Object Detection
- Optimising Rolling Stock Planning including Maintenance with Constraint Programming and Quantum Annealing
- Risk Measurement, Risk Entropy, and Autonomous Driving Risk Modeling
- Channel Estimation Based on Machine Learning Paradigm for Spatial Modulation OFDM
- A Relation-Oriented Clustering Method for Open Relation Extraction
- Sentiment Analysis in Poems in Misurata Sub-dialect -- A Sentiment Detection in an Arabic Sub-dialect
- Target Languages (vs. Inductive Biases) for Learning to Act and Plan
- Multiagent Multimodal Categorization for Symbol Emergence: Emergent Communication via Interpersonal Cross-modal Inference
- FCA: Learning a 3D Full-coverage Vehicle Camouflage for Multi-view Physical Adversarial Attack
- Transformer-based Language Models for Factoid Question Answering at BioASQ9b
- Back to Basics: Deep Reinforcement Learning in Traffic Signal Control
- Adversarial Mixing Policy for Relaxing Locally Linear Constraints in Mixup
- Balancing detectability and performance of attacks on the control channel of Markov Decision Processes
- Powered Hawkes-Dirichlet Process: Challenging Textual Clustering using a Flexible Temporal Prior
- Disentangling Generative Factors in Natural Language with Discrete Variational Autoencoders
- 3D Annotation Of Arbitrary Objects In The Wild
- MISSFormer: An Effective Medical Image Segmentation Transformer
- Resolution-robust Large Mask Inpainting with Fourier Convolutions
- Learning to Match Job Candidates Using Multilingual Bi-Encoder BERT
- Can Language Models be Biomedical Knowledge Bases?
- Incorporating Residual and Normalization Layers into Analysis of Masked Language Models
- Reconstructing occluded Elevation Information in Terrain Maps with Self-supervised Learning
- Fusion with Hierarchical Graphs for Mulitmodal Emotion Recognition
- Semantics of European poetry is shaped by conservative forces: The relationship between poetic meter and meaning in accentual-syllabic verse
- Spline-PINN: Approaching PDEs without Data using Fast, Physics-Informed Hermite-Spline CNNs
- Universal Adversarial Attack on Deep Learning Based Prognostics
- Beyond Glass-Box Features: Uncertainty Quantification Enhanced Quality Estimation for Neural Machine Translation
- On the Universality of Deep Contextual Language Models
- Patch-based Medical Image Segmentation using Matrix Product State Tensor Networks
- Optimal Cycling of a Heterogenous Battery Bank via Reinforcement Learning
- Co-Embedding: Discovering Communities on Bipartite Graphs through Projection
- Parallel Constraint-Driven Inductive Logic Programming
- What Does The User Want? Information Gain for Hierarchical Dialogue Policy Optimisation
- Low-Resource Named Entity Recognition Based on Multi-hop Dependency Trigger
- Non-Asymptotic Analysis of Stochastic Approximation Algorithms for Streaming Data
- Anchor DETR: Query Design for Transformer-Based Object Detection
- WIP: Medical Incident Prediction Through Analysis of Electronic Medical Records Using Machine Lerning: Fall Prediction
- Automatic Symmetry Discovery with Lie Algebra Convolutional Network
- Can Edge Probing Tasks Reveal Linguistic Knowledge in QA Models?
- Complementary Feature Enhanced Network with Vision Transformer for Image Dehazing
- Towards Document-Level Paraphrase Generation with Sentence Rewriting and Reordering
- Fast Extraction of Word Embedding from Q-contexts
- Transformer-based Lexically Constrained Headline Generation
- DSOR: A Scalable Statistical Filter for Removing Falling Snow from LiDAR Point Clouds in Severe Winter Weather
- F-CAM: Full Resolution Class Activation Maps via Guided Parametric Upscaling
- Improving Text Auto-Completion with Next Phrase Prediction
- Convergence of a Human-in-the-Loop Policy-Gradient Algorithm With Eligibility Trace Under Reward, Policy, and Advantage Feedback
- Image Synthesis via Semantic Composition
- ARCH: Efficient Adversarial Regularized Training with Caching
- Dataflow Accelerator Architecture for Autonomous Machine Computing
- A Conditional Generative Matching Model for Multi-lingual Reply Suggestion
- Uncertainty Quantification in Medical Image Segmentation with Multi-decoder U-Net
- Attention Is Indeed All You Need: Semantically Attention-Guided Decoding for Data-to-Text NLG
- PnP-DETR: Towards Efficient Visual Analysis with Transformers
- Seeking an Optimal Approach for Computer-Aided Pulmonary Embolism Detection
- Avengers Ensemble! Improving Transferability of Authorship Obfuscation