Papers
Thu 27 Oct 2022
252 papers
- Accelerating Diffusion Models via Pre-segmentation Diffusion Sampling for Medical Image SegmentationDiffusion models → Medical imaging and segmentation
- Diffiner: A Versatile Diffusion-based Generative Refiner for Speech EnhancementDiffusion models → Audio, speech and music
- Collaborative Multi-Teacher Knowledge Distillation for Learning Low Bit-width Deep Neural NetworksKnowledge distillation → General knowledge distillation methods
- Conditioning and Sampling in Variational Diffusion Models for Speech Super-ResolutionDiffusion models → Audio, speech and music
- Language Control Diffusion: Efficiently Scaling through Space, Time, and TasksDiffusion models → Discrete and text diffusion
- Class Based Thresholding in Early Exit Semantic Segmentation NetworksEfficient LLM inference and serving → Token pruning and merging for ViTs
- GammaE: Gamma Embeddings for Logical Queries on Knowledge GraphsLLM reasoning → Knowledge- and tool-augmented reasoning
- COST-EFF: Collaborative Optimization of Spatial and Temporal Efficiency with Slenderized Multi-exit Language ModelsEfficient LLM inference and serving → Early exit and edge inference
- Improved Feature Distillation via Projector EnsembleKnowledge distillation → General knowledge distillation methods
- ERNIE-ViLG 2.0: Improving Text-to-Image Diffusion Model with Knowledge-Enhanced Mixture-of-Denoising-ExpertsDiffusion models → Image generation, text-to-image and editing
- Solving Audio Inverse Problems with a Diffusion ModelDiffusion models → Audio, speech and music
- Learning on the Job: Self-Rewarding Offline-to-Online Finetuning for Industrial Insertion of Novel Connectors from VisionSynthetic data and self-improvement for LLMs → Self-evolving LLM agents +1
- Too Brittle To Touch: Comparing the Stability of Quantization and Distillation Towards Developing Lightweight Low-Resource MT ModelsKnowledge distillation → Knowledge distillation for LLMs
- Open-vocabulary Semantic Segmentation with Frozen Vision-Language ModelsMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
- Rethinking the Reverse-engineering of Trojan TriggersLLM safety and security → Backdoor and data poisoning attacks
- A Review of Deep Learning Techniques for Protein Function Prediction
- Low Latency Conversion of Artificial Neural Network Models to Rate-encoded Spiking Neural Networks
- On the biological plausibility of orthogonal initialisation for solving gradient instability in deep neural networks
- Trust-Awareness to Secure Swarm Intelligence from Data Injection Attack
- Local learning through propagation delays in spiking neural networks
- Fast DistilBERT on CPUs
- Joint Graph Convolution for Analyzing Brain Structural and Functional Connectome
- Partial Differential Equations Meet Deep Neural Networks: A Survey
- Efficient ECG-based Atrial Fibrillation Detection via Parameterised Hypercomplex Neural Networks
- A Knowledge Distillation Framework For Enhancing Ear-EEG Based Sleep Staging With Scalp-EEG Data
- Fault Diagnosis for Power Electronics Converters based on Deep Feedforward Network and Wavelet Compression
- MAEEG: Masked Auto-encoder for EEG Representation Learning
- HYDRA-HGR: A Hybrid Transformer-based Architecture for Fusion of Macroscopic and Microscopic Neural Drive Information
- Efficient Similarity-based Passive Filter Pruning for Compressing CNNs
- ProbNeRF: Uncertainty-Aware Inference of 3D Shapes from 2D Images
- Synthesizer Preset Interpolation using Transformer Auto-Encoders
- Simultaneous off-the-grid learning of mixtures issued from a continuous dictionary
- Contextual-Utterance Training for Automatic Speech Recognition
- M3FGM:a node masking and multi-granularity message passing-based federated graph model for spatial-temporal data prediction
- Pretraining Respiratory Sound Representations using Metadata and Contrastive Learning
- Deep Learning Object Detection Approaches to Signal Identification
- Vanishing Component Analysis with Contrastive Normalization
- A Generic Shared Attention Mechanism for Various Backbone Neural Networks
- An Empirical Evaluation of Zeroth-Order Optimization Methods on AI-driven Molecule Optimization
- Predicting Protein-Ligand Binding Affinity with Equivariant Line Graph Network
- Towards Reliable Zero Shot Classification in Self-Supervised Models with Conformal Prediction
- Handwashing Action Detection System for an Autonomous Social Robot
- Adaptive physics-informed neural operator for coarse-grained non-equilibrium flows
- Layout Aware Inpainting for Automated Furniture Removal in Indoor Scenes
- BI AVAN: Brain inspired Adversarial Visual Attention Network
- Poisson Reweighted Laplacian Uncertainty Sampling for Graph-based Active Learning
- A Compact End-to-End Model with Local and Global Context for Spoken Language Identification
- Reinforced Question Rewriting for Conversational Question Answering
- Evaluating context-invariance in unsupervised speech representations
- Fully-attentive and interpretable: vision and video vision transformers for pain detection
- Gathering Strength, Gathering Storms: The One Hundred Year Study on Artificial Intelligence (AI100) 2021 Study Panel Report
- An Adversarial Active Sampling-based Data Augmentation Framework for Manufacturable Chip Design
- Noise Injection Node Regularization for Robust Learning
- Nearest Neighbor Language Models for Stylistic Controllable Generation
- Towards Improving Workers' Safety and Progress Monitoring of Construction Sites Through Construction Site Understanding
- Self-supervised language learning from raw audio: Lessons from the Zero Resource Speech Challenge
- Confident Approximate Policy Iteration for Efficient Local Planning in qπ-realizable MDPs
- Planning with Spatial-Temporal Abstraction from Point Clouds for Deformable Object Manipulation
- One-Shot Acoustic Matching Of Audio Signals -- Learning to Hear Music In Any Room/ Concert Hall
- Spatio-temporal predictive tasks for abnormal event detection in videos
- Token-level Sequence Labeling for Spoken Language Understanding using Compositional End-to-End Models
- Beyond Homophily with Graph Echo State Networks
- PatchRot: A Self-Supervised Technique for Training Vision Transformers
- GraphMAD: Graph Mixup for Data Augmentation using Data-Driven Convex Clustering
- QUILL: Query Intent with Large Language Models using Retrieval Augmentation and Multi-stage Distillation
- Simulating realistic speech overlaps improves multi-talker ASR
- Improvement-Focused Causal Recourse (ICR)
- Do Pre-trained Models Benefit Equally in Continual Learning?
- TAD: Transfer Learning-based Multi-Adversarial Detection of Evasion Attacks against Network Intrusion Detection Systems
- COMET-QE and Active Learning for Low-Resource Machine Translation
- Prototype-Based Layered Federated Cross-Modal Hashing
- Deepening Neural Networks Implicitly and Locally via Recurrent Attention Strategy
- Feature Necessity & Relevancy in ML Classifier Explanations
- Reverse Survival Model (RSM): A Pipeline for Explaining Predictions of Deep Survival Models
- State of the Art in Dense Monocular Non-Rigid 3D Reconstruction
- Deep Generative Models on 3D Representations: A Survey
- A Primal-Dual Approach to Solving Variational Inequalities with General Constraints
- All the Feels: A dexterous hand with large-area tactile sensing
- Learning Single-Index Models with Shallow Neural Networks
- LyricJam Sonic: A Generative System for Real-Time Composition and Musical Improvisation
- Towards Correlated Sequential Rules
- Exploring Effective Distillation of Self-Supervised Speech Models for Automatic Speech Recognition
- Neural Networks with Quantization Constraints
- ACES: Translation Accuracy Challenge Sets for Evaluating Machine Translation Metrics
- Private and Reliable Neural Network Inference
- Working Alliance Transformer for Psychotherapy Dialogue Classification
- Provable Sim-to-real Transfer in Continuous Domain with Partial Observations
- Joint Multi-Person Body Detection and Orientation Estimation via One Unified Embedding
- Regret Bounds and Experimental Design for Estimate-then-Optimize
- A Graph Is More Than Its Nodes: Towards Structured Uncertainty-Aware Learning on Graphs
- Multi-task Bias-Variance Trade-off Through Functional Constraints
- Full-scale Deeply Supervised Attention Network for Segmenting COVID-19 Lesions
- Efficient few-shot learning for pixel-precise handwritten document layout analysis
- Training Graph Neural Networks on Growing Stochastic Graphs
- UNet-2022: Exploring Dynamics in Non-isomorphic Architecture
- Bridging the visual gap in VLN via semantically richer instructions
- Multimodal Transformer Distillation for Audio-Visual Synchronization
- Robust Monocular Localization of Drones by Adapting Domain Maps to Depth Prediction Inaccuracies
- Improving abstractive summarization with energy-based re-ranking
- Terminology-aware Medical Dialogue Generation
All 252
- Strategic Geosteering Workflow with Uncertainty Quantification and Deep Learning: A Case Study on the Goliat Field
- Hyperspectral Images Classification and Dimensionality Reduction using spectral interaction and SVM classifier
- Beyond the Return: Off-policy Function Estimation under User-specified Error-measuring Distributions
- Transformers meet Stochastic Block Models: Attention with Data-Adaptive Sparsity and Cost
- Masked Transformer for image Anomaly Localization
- Multi-Target Tracking with Transferable Convolutional Neural Networks
- Source-Filter HiFi-GAN: Fast and Pitch Controllable High-Fidelity Neural Vocoder
- Learning Location from Shared Elevation Profiles in Fitness Apps: A Privacy Perspective
- Exploiting Features and Logits in Heterogeneous Federated Learning
- A Double Machine Learning Trend Model for Citizen Science Data
- LongShortNet: Exploring Temporal and Semantic Features Fusion in Streaming Perception
- Meta-Reinforcement Learning Using Model Parameters
- Point-Voxel Adaptive Feature Abstraction for Robust Point Cloud Classification
- Lifelong Bandit Optimization: No Prior and No Regret
- ProContEXT: Exploring Progressive Context Transformer for Tracking
- Fusion-based Few-Shot Morphing Attack Detection and Fingerprinting
- How To Overcome Richness Axiom Fallacy
- Resource Constrained Vehicular Edge Federated Learning with Highly Mobile Connected Vehicles
- Leveraging Wikidata's edit history in knowledge graph refinement tasks
- Reconstruction of compressed spectral imaging based on global structure and spectral correlation
- GaitMixer: Skeleton-based Gait Representation Learning via Wide-spectrum Multi-axial Mixer
- Circular Pythagorean fuzzy sets and applications to multi-criteria decision making
- A Novel Filter Approach for Band Selection and Classification of Hyperspectral Remotely Sensed Images Using Normalized Mutual Information and Support Vector Machines
- Adaptive Estimation of Graphical Models under Total Positivity
- Learning Failure-Inducing Models for Testing Software-Defined Networks
- He Said, She Said: Style Transfer for Shifting the Perspective of Dialogues
- One-Class Risk Estimation for One-Class Hyperspectral Image Classification
- Virtuoso: Massive Multilingual Speech-Text Joint Semi-Supervised Learning for Text-To-Speech
- Toroidal Probabilistic Spherical Discriminant Analysis
- Multi-layered Discriminative Restricted Boltzmann Machine with Untrained Probabilistic Layer
- Many-Objective Reinforcement Learning for Online Testing of DNN-Enabled Systems
- Student-centric Model of Learning Management System Activity and Academic Performance: from Correlation to Causation
- What Language Model to Train if You Have One Million GPU Hours?
- Supervised classification methods applied to airborne hyperspectral images: Comparative study using mutual information
- FreeVC: Towards High-Quality Text-Free One-Shot Voice Conversion
- Bayesian Inference of Transition Matrices from Incomplete Graph Data with a Topological Prior
- Facial Video-based Remote Physiological Measurement via Self-supervised Learning
- Make More of Your Data: Minimal Effort Data Augmentation for Automatic Speech Recognition and Translation
- Efficient Learning of Decision-Making Models: A Penalty Block Coordinate Descent Algorithm for Data-Driven Inverse Optimization
- LeNo: Adversarial Robust Salient Object Detection Networks with Learnable Noise
- Automatic Severity Classification of Dysarthric speech by using Self-supervised Model with Multi-task Learning
- Opening the Black Box of wav2vec Feature Encoder
- MorphTE: Injecting Morphology in Tensorized Embeddings
- Retrieving Users' Opinions on Social Media with Multimodal Aspect-Based Sentiment Analysis
- Grasping Causality for the Explanation of Criticality for Automated Driving
- 2T-UNET: A Two-Tower UNet with Depth Clues for Robust Stereo Depth Estimation
- Self-consistent Reasoning For Solving Math Word Problems
- Meta-Learning Initializations for Interactive Medical Image Registration
- CasNet: Investigating Channel Robustness for Speech Separation
- A Training and Inference Strategy Using Noisy and Enhanced Speech as Target for Speech Enhancement without Clean Speech
- Li3DeTr: A LiDAR based 3D Detection Transformer
- Explicit Intensity Control for Accented Text-to-speech
- A Novel Approach for Neuromorphic Vision Data Compression based on Deep Belief Network
- FCTalker: Fine and Coarse Grained Context Modeling for Expressive Conversational Speech Synthesis
- Exploiting modality-invariant feature for robust multimodal emotion recognition with missing modalities
- Leveraging knowledge graphs to update scientific word embeddings using latent semantic imputation
- Learning Discrete Directed Acyclic Graphs via Backpropagation
- Sample-Specific Root Causal Inference with Latent Variables
- Dial2vec: Self-Guided Contrastive Learning of Unsupervised Dialogue Embeddings
- Towards Language-driven Scientific AI
- Stochastic Mirror Descent in Average Ensemble Models
- Efficient and Effective Augmentation Strategy for Adversarial Training
- MSF3DDETR: Multi-Sensor Fusion 3D Detection Transformer for Autonomous Driving
- Rigid-Body Sound Synthesis with Differentiable Modal Resonators
- Deformable Temporal Convolutional Networks for Monaural Noisy Reverberant Speech Separation
- Explaining the Explainers in Graph Neural Networks: a Comparative Study
- Can language models handle recursively nested grammatical structures? A case study on comparing models and humans
- Leveraging Computer Vision Application in Visual Arts: A Case Study on the Use of Residual Neural Network to Classify and Analyze Baroque Paintings
- Spatio-Temporal Hybrid Fusion of CAE and SWIn Transformers for Lung Cancer Malignancy Prediction
- Modeling Inter-Dependence Between Time and Mark in Multivariate Temporal Point Processes
- Isometric 3D Adversarial Examples in the Physical World
- On the Efficiency of Ethics as a Governing Tool for Artificial Intelligence
- SAN: a robust end-to-end ASR model architecture
- On Out-of-Distribution Detection for Audio with Deep Nearest Neighbors
- Weight Averaging: A Simple Yet Effective Method to Overcome Catastrophic Forgetting in Automatic Speech Recognition
- The 1st-place Solution for ECCV 2022 Multiple People Tracking in Group Dance Challenge
- On the Approximation and Complexity of Deep Neural Networks to Invariant Functions
- Implications of sparsity and high triangle density for graph representation learning
- Conversation Disentanglement with Bi-Level Contrastive Learning
- A knowledge-driven vowel-based approach of depression classification from speech using data augmentation
- Forecasting Graph Signals with Recursive MIMO Graph Filters
- Unsupervised Knowledge Graph Construction and Event-centric Knowledge Infusion for Scientific NLI
- A few-shot learning approach with domain adaptation for personalized real-life stress detection in close relationships
- Seq2Seq-SC: End-to-End Semantic Communication Systems with Pre-trained Language Model
- Painting the black box white: experimental findings from applying XAI to an ECG reading setting
- SSD: Towards Better Text-Image Consistency Metric in Text-to-Image Generation
- Creating a morphological and syntactic tagged corpus for the Uzbek language
- Unsupervised Boundary-Aware Language Model Pretraining for Chinese Sequence Labeling
- How well can Text-to-Image Generative Models understand Ethical Natural Language Interventions?
- Iterative pseudo-forced alignment by acoustic CTC loss for self-supervised ASR domain adaptation
- BERT-Flow-VAE: A Weakly-supervised Model for Multi-Label Text Classification
- The Effect of Normalization for Bi-directional Amharic-English Neural Machine Translation
- TASA: Deceiving Question Answering Models by Twin Answer Sentences Attack
- End-to-End Pareto Set Prediction with Graph Neural Networks for Multi-objective Facility Location
- Parsing linearizations appreciate PoS tags - but some are fussy about errors
- Trust and Believe -- Should We? Evaluating the Trustworthiness of Twitter Users
- COCO-DR: Combating Distribution Shifts in Zero-Shot Dense Retrieval with Contrastive and Distributionally Robust Learning
- Multi-view Contrastive Learning with Additive Margin for Adaptive Nasopharyngeal Carcinoma Radiotherapy Prediction
- Deep-MDS Framework for Recovering the 3D Shape of 2D Landmarks from a Single Image
- Watermarking for Out-of-distribution Detection
- Masked Autoencoders Are Articulatory Learners
- Few-shot Image Generation via Masked Discrimination
- Truncation Sampling as Language Model Desmoothing
- Partially Oblivious Neural Network Inference
- Learning Joint Representation of Human Motion and Language
- SAM-RL: Sensing-Aware Model-Based Reinforcement Learning via Differentiable Physics-Based Simulation and Rendering
- Outlier-Aware Training for Improving Group Accuracy Disparities
- Text2Model: Text-based Model Induction for Zero-shot Image Classification
- Disentangled and Robust Representation Learning for Bragging Classification in Social Media
- Mean-field neural networks: learning mappings on Wasserstein space
- Anonymized Histograms in Intermediate Privacy Models
- Domain Adaptive Object Detection for Autonomous Driving under Foggy Weather
- Private Isotonic Regression
- Articulation GAN: Unsupervised modeling of articulatory learning
- Dictionary-Assisted Supervised Contrastive Learning
- Improved Projection Learning for Lower Dimensional Feature Maps
- FAS-UNet: A Novel FAS-driven Unet to Learn Variational Image Segmentation
- Global-to-local Expression-aware Embeddings for Facial Action Unit Detection
- Conversing with Copilot: Exploring Prompt Engineering for Solving CS1 Problems Using Natural Language
- Towards Complex Backgrounds: A Unified Difference-Aware Decoder for Binary Segmentation
- AutoAttention: Automatic Field Pair Selection for Attention in User Behavior Modeling
- Fully Automated Deep Learning-enabled Detection for Hepatic Steatosis on Computed Tomography: A Multicenter International Validation Study
- A Curriculum Learning Approach for Multi-domain Text Classification Using Keyword weight Ranking
- Towards Practicality of Sketch-Based Visual Understanding
- Gendered Mental Health Stigma in Masked Language Models
- V-Cloak: Intelligibility-, Naturalness- & Timbre-Preserving Real-Time Voice Anonymization
- ScoreMix: A Scalable Augmentation Strategy for Training GANs with Limited Data
- 3D Shape Knowledge Graph for Cross-domain 3D Shape Retrieval
- Training Autoregressive Speech Recognition Models with Limited in-domain Supervision
- Learning Variational Motion Prior for Video-based Motion Capture
- Retrieval Oriented Masking Pre-training Language Model for Dense Passage Retrieval
- Hybrid Indoor Localization via Reinforcement Learning-based Information Fusion
- Towards High-Quality Neural TTS for Low-Resource Languages by Learning Compact Speech Representations
- MMFL-Net: Multi-scale and Multi-granularity Feature Learning for Cross-domain Fashion Retrieval
- ViT-CAT: Parallel Vision Transformers with Cross Attention Fusion for Popularity Prediction in MEC Networks
- Generalizability of Functional Forms for Interatomic Potential Models Discovered by Symbolic Regression
- Bootstrapping Human Optical Flow and Pose
- Federated Graph Representation Learning using Self-Supervision
- Light-weighted CNN-Attention based architecture for Hand Gesture Recognition via ElectroMyography
- MEET: Mobility-Enhanced Edge inTelligence for Smart and Green 6G Networks
- Masked Vision-Language Transformer in Fashion
- Boosting Point Clouds Rendering via Radiance Mapping
- TRScore: A Novel GPT-based Readability Scorer for ASR Segmentation and Punctuation model evaluation and selection
- Coordination with Humans via Strategy Matching
- Natural Language Syntax Complies with the Free-Energy Principle
- Contrastive Decoding: Open-ended Text Generation as Optimization
- Towards customizable reinforcement learning agents: Enabling preference specification through online vocabulary expansion
- Predicting Visual Attention and Distraction During Visual Search Using Convolutional Neural Networks
- Generalized Laplacian Regularized Framelet Graph Neural Networks
- Segmentation of Multiple Sclerosis Lesions across Hospitals: Learn Continually or Train from Scratch?
- Personalized Dialogue Generation with Persona-Adaptive Attention
- Robot to Human Object Handover using Vision and Joint Torque Sensor Modalities