Papers
Sun 5 Jun 2022
93 papers
- Lip-Listening: Mixing Senses to Understand Lips using Cross Modality Knowledge Distillation for Word-Based ModelsKnowledge distillation → Speech and audio distillation
- Offline RL for Natural Language Generation with Implicit Language Q LearningOffline RL and imitation learning from data → Language-conditioned policies and VLAs
- Zero-Shot Voice Conditioning for Denoising Diffusion TTS ModelsDiffusion models → Audio, speech and music
- Models of human preference for learning reward functionsLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
- Vanilla Feature Distillation for Improving the Accuracy-Robustness Trade-Off in Adversarial TrainingKnowledge distillation → Federated, robust and private distillation
- Interpretable Mixture of ExpertsMixture-of-experts → MoE theory and gating functions
- Point-to-Voxel Knowledge Distillation for LiDAR Semantic SegmentationKnowledge distillation → Detection and dense prediction distillation
- ARC - Actor Residual Critic for Adversarial Imitation LearningOffline RL and imitation learning from data → Imitation learning methods
- DDPG based on multi-scale strokes for financial time series trading strategy
- Dynamically handling task disruptions by composing together behavior modules
- Constrained Mass Optimal Transport
- Chat, Shift and Perform: Bridging the Gap between Task-oriented and Non-task-oriented Dialog Systems
- Searching Similarity Measure for Binarized Neural Networks
- Efficient decentralized multi-agent learning in asymmetric bipartite queueing systems
- GAAF: Searching Activation Functions for Binary Neural Networks through Genetic Algorithm
- Demystifying the Global Convergence Puzzle of Learning Over-parameterized ReLU Nets in Very High Dimensions
- Accurate Virus Identification with Interpretable Raman Signatures by Machine Learning
- (Im)possibility of Collective Intelligence
- A knowledge graph representation learning approach to predict novel kinase-substrate interactions
- ACT: Semi-supervised Domain-adaptive Medical Image Segmentation with Asymmetric Co-training
- AugLoss: A Robust Augmentation-based Fine Tuning Methodology
- Tagged-MRI Sequence to Audio Synthesis via Self Residual Attention Guided Heterogeneous Translator
- E^2VTS: Energy-Efficient Video Text Spotting from Unmanned Aerial Vehicles
- Annotation Error Detection: Analyzing the Past and Present for a More Coherent Future
- Autoregressive Model for Multi-Pass SAR Change Detection Based on Image Stacks
- Sharper Rates and Flexible Framework for Nonconvex SGD with Client and Data Sampling
- Estimating building energy efficiency from street view imagery, aerial imagery, and land surface temperature data
- Information Threshold, Bayesian Inference and Decision-Making
- Diffusion-GAN: Training GANs with Diffusion
- Towards Individual Grevy's Zebra Identification via Deep 3D Fitting and Metric Learning
- SealID: Saimaa ringed seal re-identification dataset
- Efficient Annotation and Learning for 3D Hand Pose Estimation: A Survey
- Use-Case-Grounded Simulations for Explanation Evaluation
- Augmenting Netflix Search with In-Session Adapted Recommendations
- Exploring Cross-lingual Textual Style Transfer with Large Multilingual Language Models
- A Memory System of a Robot Cognitive Architecture and its Implementation in ArmarX
- OntoMerger: An Ontology Integration Library for Deduplicating and Connecting Knowledge Graph Nodes
- Enforcing Group Fairness in Algorithmic Decision Making: Utility Maximization Under Sufficiency
- Two Decades of Bengali Handwritten Digit Recognition: A Survey
- Finetuning a Kalaallisut-English machine translation system using web-crawled data
- Physically Inspired Constraint for Unsupervised Regularized Ultrasound Elastography
- U(1) Symmetry-breaking Observed in Generic CNN Bottleneck Layers
- Statistical Deep Learning for Spatial and Spatio-Temporal Data
- Sequential Counterfactual Decision-Making Under Confounded Reward
- Variable-rate hierarchical CPC leads to acoustic unit discovery in speech
- Stylistic Fingerprints, POS-tags and Inflected Languages: A Case Study in Polish
- Performance Comparison of Simple Transformer and Res-CNN-BiLSTM for Cyberbullying Classification
- 3D Convolutional with Attention for Action Recognition
- GridShift: A Faster Mode-seeking Algorithm for Image Segmentation and Object Tracking
- Machine learning applications for electricity market agent-based models: A systematic literature review
- FOF: Learning Fourier Occupancy Field for Monocular Real-time Human Reconstruction
- M2FNet: Multi-modal Fusion Network for Emotion Recognition in Conversation
- Functional Ensemble Distillation
- Semi-Supervised Learning for Mars Imagery Classification and Segmentation
- A Simple Meta-learning Paradigm for Zero-shot Intent Classification with Mixture Attention Mechanism
- Belief Acquisition as Stochastic Filtering
- Near-Term Advances in Quantum Natural Language Processing
- Formally Verified Solution Methods for Infinite-Horizon Markov Decision Processes
- A Survey on Deep Learning based Channel Estimation in Doubly Dispersive Environments
- Estimating and Mitigating the Congestion Effect of Curbside Pick-ups and Drop-offs: A Causal Inference Approach
- MotionCNN: A Strong Baseline for Motion Prediction in Autonomous Driving
- Sentiment Analysis of Online Travel Reviews Based on Capsule Network and Sentiment Lexicon
- Never mind the metrics -- what about the uncertainty? Visualising confusion matrix metric distributions
- Perspectives of Non-Expert Users on Cyber Security and Privacy: An Analysis of Online Discussions on Twitter
- HPGNN: Using Hierarchical Graph Neural Networks for Outdoor Point Cloud Processing
- Which models are innately best at uncertainty estimation?
- Dict-TTS: Learning to Pronounce with Prior Dictionary Knowledge for Text-to-Speech
- Recurrent Video Restoration Transformer with Guided Deformable Attention
- Product safety idioms: a method for building causal Bayesian networks for product safety and risk assessment
- Early Stage Convergence and Global Convergence of Training Mildly Parameterized Neural Networks
- LDRNet: Enabling Real-time Document Localization on Mobile Devices
- Federated Adversarial Training with Transformers
- DeeprETA: An ETA Post-processing System at Scale
- Learning Dynamics and Generalization in Reinforcement Learning
- MPANet: Multi-Patch Attention For Infrared Small Target object Detection
- A Multimodal Corpus for Emotion Recognition in Sarcasm
- ShapePU: A New PU Learning Framework Regularized by Global Consistency for Scribble Supervised Cardiac Segmentation
- Cannot See the Forest for the Trees: Aggregating Multiple Viewpoints to Better Classify Objects in Videos
- Speech Detection Task Against Asian Hate: BERT the Central, While Data-Centric Studies the Crucial
- Computer Vision-based Characterization of Large-scale Jet Flames using a Synthetic Infrared Image Generation Approach
- ContraCLIP: Interpretable GAN generation driven by pairs of contrasting sentences
- AUTM Flow: Atomic Unrestricted Time Machine for Monotonic Normalizing Flows
- Search Space Adaptation for Differentiable Neural Architecture Search in Image Classification
- PEER: A Comprehensive and Multi-Task Benchmark for Protein Sequence Understanding
- Using Connectome Features to Constrain Echo State Networks
- LAE: Language-Aware Encoder for Monolingual and Multilingual ASR
- Bandit Theory and Thompson Sampling-Guided Directed Evolution for Sequence Optimization
- LOCO Feature Importance Inference without Data Splitting via Minipatch Ensembles
- Accurate Scoliosis Vertebral Landmark Localization on X-ray Images via Shape-constrained Multi-stage Cascaded CNNs
- Towards the Creation of a Nutrition and Food Group Based Image Database
- Towards Fast Adaptation of Pretrained Contrastive Models for Multi-channel Video-Language Retrieval
- Multilingual Neural Machine Translation with Deep Encoder and Multiple Shallow Decoders
- Straggler-Resilient Personalized Federated Learning