Papers
Thu 11 Mar 2021
154 papers
- Learning Feature Weights using Reward Modeling for Denoising Parallel CorporaLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
- Sample Complexity of Offline Reinforcement Learning with Deep ReLU NetworksOffline RL and imitation learning from data → Offline RL algorithms
- Imitation learning for variable speed motion generation over multiple actionsOffline RL and imitation learning from data → Robot manipulation imitation learning
- Personalizing image enhancement for critical visual tasks: improved legibility of papyri using color processing and visual illusions
- Systematic Mapping Study on the Machine Learning Lifecycle
- Data Mining and Visualization to Understand Accident-prone Areas
- Data-driven method for real-time prediction and uncertainty quantification of fatigue failure under stochastic loading using artificial neural networks and Gaussian process regression
- Decorrelating Adversarial Nets for Clustering Mobile Network Data
- HSCoNAS: Hardware-Software Co-Design of Efficient DNNs via Neural Architecture Search
- Boosted Genetic Algorithm using Machine Learning for traffic control optimization
- Improving Adversarial Robustness via Channel-wise Activation Suppressing
- ReinforceBug: A Framework to Generate Adversarial Textual Examples
- ACTION-Net: Multipath Excitation for Action Recognition
- Integration of Convolutional Neural Networks in Mobile Applications
- Learning by Teaching, with Application to Neural Architecture Search
- An Efficient Hypergraph Approach to Robust Point Cloud Resampling
- The Location of Optimal Object Colors with More Than Two Transitions (Preprint)
- Performance of a Geometric Deep Learning Pipeline for HL-LHC Particle Tracking
- Continuous 3D Multi-Channel Sign Language Production via Progressive Transformers and Mixture Density Networks
- Federated Functional Gradient Boosting
- Adversarial attacks in consensus-based multi-agent reinforcement learning
- Efficient Pairwise Neuroimage Analysis using the Soft Jaccard Index and 3D Keypoint Sets
- Learning Policies for Multilingual Training of Neural Machine Translation Systems
- Characterizing Partisan Political Narrative Frameworks about COVID-19 on Twitter
- The Minecraft Kernel: Modelling correlated Gaussian Processes in the Fourier domain
- Preregistering NLP Research
- Imagined-Trailing-Whitespace-Agnostic Levenshtein Distance For Plaintext Table Detection
- A Reinforcement Learning Based Approach to Play Calling in Football
- The Semi-Supervised iNaturalist-Aves Challenge at FGVC7 Workshop
- Stochastic-HMDs: Adversarial Resilient Hardware Malware Detectors through Voltage Over-scaling
- DefakeHop: A Light-Weight High-Performance Deepfake Detector
- Linnaeus: A highly reusable and adaptable ML based log classification pipeline
- Anaphoric Binding: an integrated overview
- Non-Asymptotic Performance Guarantees for Neural Estimation of mathsff-Divergences
- Towards Interpreting and Mitigating Shortcut Learning Behavior of NLU Models
- On Improving Deep Learning Trace Analysis with System Call Arguments
- CORSAIR: Convolutional Object Retrieval and Symmetry-AIded Registration
- Adaptation to Unknown Situations as the Holy Grail of Learning-Based Self-Adaptive Systems: Research Directions
- HumanGAN: A Generative Model of Humans Images
- Modern Dimension Reduction
- Evaluation of Morphological Embeddings for English and Russian Languages
- CoMoGAN: continuous model-guided image-to-image translation
- Diverse Semantic Image Synthesis via Probability Distribution Modeling
- Fast and Accurate Model Scaling
- For Manifold Learning, Deep Neural Networks can be Locality Sensitive Hash Functions
- CANINE: Pre-training an Efficient Tokenization-Free Encoder for Language Representation
- Tensor networks and efficient descriptions of classical data
- SMPLicit: Topology-aware Generative Model for Clothed People
- Learning with partially separable data
- Scaffold Embeddings: Learning the Structure Spanned by Chemical Fragments, Scaffolds and Compounds
- Understanding the Origin of Information-Seeking Exploration in Probabilistic Objectives for Control
- Should Graph Neural Networks Use Features, Edges, Or Both?
- A conditional, a fuzzy and a probabilistic interpretation of self-organising maps
- Policy Search with Rare Significant Events: Choosing the Right Partner to Cooperate with
- A hierarchical Bayesian model to find brain-behaviour associations in incomplete data sets
- Fast Hyperspectral Image Denoising and Inpainting Based on Low-Rank and Sparse Representations
- Wasserstein Robust Classification with Fairness Constraints
- Coming Down to Earth: Satellite-to-Street View Synthesis for Geo-Localization
- COVID-19 Smart Chatbot Prototype for Patient Monitoring
- Adapting User Interfaces with Model-based Reinforcement Learning
- Improved Coherence Index-Based Bound in Compressive Sensing
- Towards Continual Learning for Multilingual Machine Translation via Vocabulary Substitution
- BODAME: Bilevel Optimization for Defense Against Model Extraction
- Unknown Object Segmentation from Stereo Images
- MERMAID: Metaphor Generation with Symbolism and Discriminative Decoding
- Intelligent behavior depends on the ecological niche: Scaling up AI to human-like intelligence in socio-cultural environments
- Automatic Social Distance Estimation From Images: Performance Evaluation, Test Benchmark, and Algorithm
- ENTRUST: Argument Reframing with Language Models and Entailment
- Auto-COP: Adaptation Generation in Context-Oriented Programming using Reinforcement Learning Options
- Knowledge Graph Question Answering using Graph-Pattern Isomorphism
- ChallenCap: Monocular 3D Capture of Challenging Human Performances using Multi-Modal References
- Intraclass clustering: an implicit learning ability that regularizes DNNs
- Hybrid Physics and Deep Learning Model for Interpretable Vehicle State Prediction
- Duplex Contextual Relation Network for Polyp Segmentation
- Variational inference with a quantum computer
- Learning Word-Level Confidence For Subword End-to-End ASR
- A semi-agnostic ansatz with variable structure for quantum machine learning
- BYOL for Audio: Self-Supervised Learning for General-Purpose Audio Representation
- Unsupervised Transfer Learning in Multilingual Neural Machine Translation with Cross-Lingual Word Embeddings
- Frame-independent vector-cloud neural network for nonlocal constitutive modeling on arbitrary grids
- The Interplay of Variant, Size, and Task Type in Arabic Pre-trained Language Models
- Inference for Generative Capsule Models
- Temporal Action Segmentation from Timestamp Supervision
- Domain State Tracking for a Simplified Dialogue System
- Real-Time Surface Fitting to RGBD Sensor Data
- Deep Graph Matching under Quadratic Constraint
- Differentially Private Query Release Through Adaptive Projection
- Generalized Contrastive Optimization of Siamese Networks for Place Recognition
- Evaluation of Morphological Embeddings for the Russian Language
- MagFace: A Universal Representation for Face Recognition and Quality Assessment
- Beta-CROWN: Efficient Bound Propagation with Per-neuron Split Constraints for Complete and Incomplete Neural Network Robustness Verification
- A Quadratic Actor Network for Model-Free Reinforcement Learning
- Controlled Gaussian Process Dynamical Models with Application to Robotic Cloth Manipulation
- ASAP: A Chinese Review Dataset Towards Aspect Category Sentiment Analysis and Rating Prediction
- Symbolic Reinforcement Learning for Safe RAN Control
- DebIE: A Platform for Implicit and Explicit Debiasing of Word Embedding Spaces
- Bump Hunting in Latent Space
- Privacy-preserving Object Detection
- Preprint: Norm Loss: An efficient yet effective regularization method for deep neural networks
- An unsupervised deep learning framework for medical image denoising
All 154
- PointFlow: Flowing Semantics Through Points for Aerial Image Segmentation
- WenLan: Bridging Vision and Language by Large-Scale Multi-Modal Pre-Training
- PREPRINT: Comparison of deep learning and hand crafted features for mining simulation data
- Integrated Age Estimation Mechanism
- Causal Learner: A Toolbox for Causal Structure and Markov Blanket Learning
- Affect2MM: Affective Analysis of Multimedia Content Using Emotion Causality
- Calibrated and Partially Calibrated Semi-Generalized Homographies
- Triple-cooperative Video Shadow Detection
- DualPoseNet: Category-level 6D Object Pose and Size Estimation Using Dual Pose Network with Refined Learning of Pose Consistency
- Implicit energy regularization of neural ordinary-differential-equation control
- Tracking Air Pollution in China: Near Real-Time PM2.5 Retrievals from Multiple Data Sources
- Data Collection and Utilization Framework for Edge AI Applications
- Drone-as-a-Service Composition Under Uncertainty
- Does the Magic of BERT Apply to Medical Code Assignment? A Quantitative Study
- A learning-based view extrapolation method for axial super-resolution
- Instance Segmentation GNNs for One-Shot Conformal Tracking at the LHC
- Multi-Format Contrastive Learning of Audio Representations
- Memristive Stochastic Computing for Deep Learning Parameter Optimization
- Adversarial Laser Beam: Effective Physical-World Attack to DNNs in a Blink
- Fair Mixup: Fairness via Interpolation
- Density-aware Haze Image Synthesis by Self-Supervised Content-Style Disentanglement
- Conversational Answer Generation and Factuality for Reading Comprehension Question-Answering
- 3D Human Pose, Shape and Texture from Low-Resolution Images and Videos
- Read Like Humans: Autonomous, Bidirectional and Iterative Language Modeling for Scene Text Recognition
- Active2 Learning: Actively reducing redundancies in Active Learning methods for Sequence Tagging and Machine Translation
- DAFAR: Defending against Adversaries by Feedback-Autoencoder Reconstruction
- Robust High-speed Running for Quadruped Robots via Deep Reinforcement Learning
- Time-uniform central limit theory and asymptotic confidence sequences
- Metapaths guided Neighbors aggregated Network for?Heterogeneous Graph Reasoning
- Multi-Task Federated Reinforcement Learning with Adversaries
- Generalizable Episodic Memory for Deep Reinforcement Learning
- Pavement Distress Detection and Segmentation using YOLOv4 and DeepLabv3 on Pavements in the Philippines
- Recent Advances on Neural Network Pruning at Initialization
- Towards Multi-Sense Cross-Lingual Alignment of Contextual Embeddings
- Smartphone Impostor Detection with Behavioral Data Privacy and Minimalist Hardware Support
- Full Page Handwriting Recognition via Image to Sequence Extraction
- Self-Supervised Motion Retargeting with Safety Guarantee
- Where is your place, Visual Place Recognition?
- Hierarchical Bayesian Model for the Transfer of Knowledge on Spatial Concepts based on Multimodal Information
- Topical Language Generation using Transformers
- Robust 2D/3D Vehicle Parsing in CVIS
- Covariate-assisted Sparse Tensor Completion
- XDO: A Double Oracle Algorithm for Extensive-Form Games
- Holistic 3D Scene Understanding from a Single Image with Implicit Representation
- SAR-U-Net: squeeze-and-excitation block and atrous spatial pyramid pooling based residual U-Net for automatic liver segmentation in Computed Tomography
- LightMBERT: A Simple Yet Effective Method for Multilingual BERT Distillation
- 3D Head-Position Prediction in First-Person View by Considering Head Pose for Human-Robot Eye Contact
- FairFil: Contrastive Neural Debiasing Method for Pretrained Text Encoders
- MediaSum: A Large-scale Media Interview Dataset for Dialogue Summarization
- Distributed Principal Subspace Analysis for Partitioned Big Data: Algorithms, Analysis, and Implementation
- A Vision Based Deep Reinforcement Learning Algorithm for UAV Obstacle Avoidance
- Self-supervised Text-to-SQL Learning with Header Alignment Training
- Analyzing the Hidden Activations of Deep Policy Networks: Why Representation Matters
- Interpretable Data-driven Methods for Subgrid-scale Closure in LES for Transcritical LOX/GCH4 Combustion