Papers
Wed 2 Nov 2022
232 papers
- Quantized Compressed Sensing with Score-based Generative ModelsDiffusion models → Diffusion foundations and sampling
- Dormant Neural TrojansLLM safety and security → Backdoor and data poisoning attacks
- Convergence of the Inexact Langevin Algorithm in KL Divergence with Application to Score-based Generative ModelsDiffusion models → Diffusion foundations and sampling
- Dual Generator Offline Reinforcement LearningOffline RL and imitation learning from data → Offline RL algorithms
- An optimal control perspective on diffusion-based generative modelingDiffusion models → Diffusion foundations and sampling
- Chinese CLIP: Contrastive Vision-Language Pretraining in ChineseMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
- eDiff-I: Text-to-Image Diffusion Models with an Ensemble of Expert DenoisersDiffusion models → Image generation, text-to-image and editing
- Generation of Anonymous Chest Radiographs Using Latent Diffusion Models for Training Thoracic Abnormality Classification SystemsDiffusion models → Medical imaging and segmentation
- data2vec-aqc: Search for the right Teaching Assistant in the Teacher-Student training setupKnowledge distillation → Speech and audio distillation
- Multi-level Distillation of Semantic Knowledge for Pre-training Multilingual Language ModelKnowledge distillation → Knowledge distillation for LLMs
- DPM-Solver++: Fast Solver for Guided Sampling of Diffusion Probabilistic ModelsDiffusion models → Diffusion foundations and sampling
- Generative Poisoning Using Random DiscriminatorsLLM safety and security → Backdoor and data poisoning attacks
- Gradient Knowledge Distillation for Pre-trained Language ModelsKnowledge distillation → Knowledge distillation for LLMs
- Offline RL With Realistic Datasets: Heteroskedasticity and Support ConstraintsOffline RL and imitation learning from data → Offline RL algorithms
- Model-based Reinforcement Learning with a Hamiltonian Canonical ODE NetworkWorld models → Latent dynamics models and model-based RL
- Spot the fake lungs: Generating Synthetic Medical Images using Neural Diffusion ModelsDiffusion models → Medical imaging and segmentation
- Behavior Prior Representation learning for Offline Reinforcement LearningOffline RL and imitation learning from data → Offline RL algorithms
- Edge Impulse: An MLOps Platform for Tiny Machine Learning
- Generative Adversarial Training Can Improve Neural Language Models
- Deep Reinforcement Learning for IRS Phase Shift Design in Spatiotemporally Correlated Environments
- Numerical Optimizations for Weighted Low-rank Estimation on Language Model
- SigT: An Efficient End-to-End MIMO-OFDM Receiver Framework Based on Transformer
- Verified Reversible Programming for Verified Lossless Compression
- Supporting the Task-driven Skill Identification in Open Source Project Issue Tracking Systems
- AI Ethics in Smart Healthcare
- A Machine Learning system to monitor student progress in educational institutes
- Untargeted Backdoor Attack against Object Detection
- Backdoor Defense via Suppressing Model Shortcuts
- Causal Counterfactuals for Improving the Robustness of Reinforcement Learning
- Plausibility Verification For 3D Object Detectors Using Energy-Based Optimization
- MuMIC -- Multimodal Embedding for Multi-label Image Classification with Tempered Sigmoid
- Biologically-Inspired Continual Learning of Human Motion Sequences
- Learning to Price Supply Chain Contracts against a Learning Retailer
- Energy System Digitization in the Era of AI: A Three-Layered Approach towards Carbon Neutrality
- How Technology Impacts and Compares to Humans in Socially Consequential Arenas
- Fast and efficient speech enhancement with variational autoencoders
- Deep Distance Sensitivity Oracles
- Wind Power Forecasting Considering Data Privacy Protection: A Federated Deep Reinforcement Learning Approach
- Data-driven design of fault diagnosis for three-phase PWM rectifier using random forests technique with transient synthetic features
- AI enhanced finite element multiscale modelling and structural uncertainty analysis of a functionally graded porous beam
- Ranking-based Group Identification via Factorized Attention on Social Tripartite Graph
- BATT: Backdoor Attack with Transformation-based Triggers
- Beyond Instance Discrimination: Relation-aware Contrastive Self-supervised Learning
- Jump-Diffusion Langevin Dynamics for Multimodal Posterior Sampling
- Losses Can Be Blessings: Routing Self-Supervised Speech Representations Towards Efficient Multilingual and Multitask Speech Processing
- Inferring independent sets of Gaussian variables after thresholding correlations
- SLICER: Learning universal audio representations using low-resource self-supervised pre-training
- Bayesian Counterfactual Mean Embeddings and Off-Policy Evaluation
- MAST: Multiscale Audio Spectrogram Transformers
- Optimizing Fiducial Marker Placement for Improved Visual Localization
- Implicit Neural Representation as a Differentiable Surrogate for Photon Propagation in a Monolithic Neutrino Detector
- Learning to Grasp the Ungraspable with Emergent Extrinsic Dexterity
- On the Safety of Interpretable Machine Learning: A Maximum Deviation Approach
- Max Markov Chain
- Assessing Resource-Performance Trade-off of Natural Language Models using Data Envelopment Analysis
- Data Level Lottery Ticket Hypothesis for Vision Transformers
- RQUGE: Reference-Free Metric for Evaluating Question Generation by Answering the Question
- Over-communicate no more: Situated RL agents learn concise communication protocols
- The Need for Medically Aware Video Compression in Gastroenterology
- Generative Entity-to-Entity Stance Detection with Knowledge Graph Augmentation
- Phoneme Segmentation Using Self-Supervised Speech Models
- Towards Zero-Shot Code-Switched Speech Recognition
- PI is back! Switching Acquisition Functions in Bayesian Optimization
- Speeding up NAS with Adaptive Subset Selection
- MPCFormer: fast, performant and private Transformer inference with MPC
- Privacy-preserving Non-negative Matrix Factorization with Outliers
- Trustworthy Representation Learning via Information Funnels and Bottlenecks
- Improved Inapproximability of VC Dimension and Littlestone's Dimension via (Unbalanced) Biclique
- eXplainable AI for Quantum Machine Learning
- Variable Attention Masking for Configurable Transformer Transducer Speech Recognition
- Cross-stitching Text and Knowledge Graph Encoders for Distantly Supervised Relation Extraction
- Hierarchies over Vector Space: Orienting Word and Graph Embeddings
- CLIP-Sculptor: Zero-Shot Generation of High-Fidelity and Diverse Shapes from Natural Language
- Harnessing the Power of Explanations for Incremental Training: A LIME-Based Approach
- CAMANet: Class Activation Map Guided Attention Network for Radiology Report Generation
- On the Informativeness of Supervision Signals
- End-to-end deep multi-score model for No-reference stereoscopic image quality assessment
- Interpretable Modeling and Reduction of Unknown Errors in Mechanistic Operators
- Investigating the robustness of a learning-based method for quantitative phase retrieval from propagation-based x-ray phase contrast measurements under laboratory conditions
- Two-Stream Network for Sign Language Recognition and Translation
- QuACK: Accelerating Gradient-Based Quantum Optimization with Koopman Operator Learning
- My Face My Choice: Privacy Enhancing Deepfakes for Social Media Anonymization
- Quasi-Newton Steps for Efficient Online Exp-Concave Optimization
- MT-GenEval: A Counterfactual and Contextual Dataset for Evaluating Gender Accuracy in Machine Translation
- Improving Named Entity Recognition in Telephone Conversations via Effective Active Learning with Human in the Loop
- Fourier Disentangled Multimodal Prior Knowledge Fusion for Red Nucleus Segmentation in Brain MRI
- Fine-grained Human Activity Recognition Using Virtual On-body Acceleration Data
- POLICE: Provably Optimal Linear Constraint Enforcement for Deep Neural Networks
- Predicting phoneme-level prosody latents using AR and flow-based Prior Networks for expressive speech synthesis
- Low-Resource Music Genre Classification with Cross-Modal Neural Model Reprogramming
- Addressing Data Distribution Shifts in Online Machine Learning Powered Smart City Applications Using Augmented Test-Time Adaptation
- Distill and Collect for Semi-Supervised Temporal Action Segmentation
- A Joint Framework Towards Class-aware and Class-agnostic Alignment for Few-shot Segmentation
- Properties of the Concrete distribution
- Late Audio-Visual Fusion for In-The-Wild Speaker Diarization
- Machine Learning for Metasurfaces Design and Their Applications
- Driver Digital Twin for Online Prediction of Personalized Lane Change Behavior
- DC-cycleGAN: Bidirectional CT-to-MR Synthesis from Unpaired Data
- Learning an Artificial Language for Knowledge-Sharing in Multilingual Translation
- Boosting word frequencies in authorship attribution
All 232
- Characterizing Intrinsic Compositionality in Transformers with Tree Projections
- An Exponentially Converging Particle Method for the Mixed Nash Equilibrium of Continuous Games
- Multi-Vector Retrieval as Sparse Alignment
- Knowing the Past to Predict the Future: Reinforcement Virtual Learning
- A Quantum Kernel Learning Approach to Acoustic Modeling for Spoken Command Recognition
- Where Do We Go From Here? Guidelines For Offline Recommender Evaluation
- Instance-Dependent Generalization Bounds via Optimal Transport
- An Aggregation of Aggregation Methods in Computational Pathology
- Task-Oriented Over-the-Air Computation for Multi-Device Edge AI
- CircleSnake: Instance Segmentation with Circle Representation
- Fair Visual Recognition via Intervention with Proxy Features
- An efficient algorithm for the ℓp norm based metric nearness problem
- EquiMod: An Equivariance Module to Improve Self-Supervised Learning
- WiserVR: Semantic Communication Enabled Wireless Virtual Reality Delivery
- Isometric Representations in Neural Networks Improve Robustness
- Uncertainty-Aware DNN for Multi-Modal Camera Localization
- Attention-based Neural Cellular Automata
- Interval Markov Decision Processes with Continuous Action-Spaces
- DEArt: Dataset of European Art
- Propensity score models are better when post-calibrated
- Time-aware Random Walk Diffusion to Improve Dynamic Graph Learning
- FiFo: Fishbone Forwarding in Massive IoT Networks
- Bias-Aware Face Mask Detection Dataset
- Human-in-the-Loop Mixup
- Human alignment of neural network representations
- Inference and Denoise: Causal Inference-based Neural Speech Enhancement
- Joint Data and Feature Augmentation for Self-Supervised Representation Learning on Point Clouds
- M-SpeechCLIP: Leveraging Large-Scale, Pre-Trained Models for Multilingual Speech to Image Retrieval
- Neural Systematic Binder
- Hypergraph Convolutional Network based Weakly Supervised Point Cloud Semantic Segmentation with Scene-Level Annotations
- RegCLR: A Self-Supervised Framework for Tabular Representation Learning in the Wild
- Lifted Inference with Linear Order Axiom
- Unsupervised denoising for sparse multi-spectral computed tomography
- Entropic Neural Optimal Transport via Diffusion Processes
- An Easy-to-use and Robust Approach for the Differentially Private De-Identification of Clinical Textual Documents
- DynamicISP: Dynamically Controlled Image Signal Processor for Image Recognition
- OPA-3D: Occlusion-Aware Pixel-Wise Aggregation for Monocular 3D Object Detection
- Faster variational quantum algorithms with quantum kernel-based surrogate models
- Classification of multi-frequency RF signals by extreme learning, using magnetic tunnel junctions as neurons and synapses
- Style Augmentation improves Medical Image Segmentation
- Fast Adaptive Federated Bilevel Optimization
- Variational Hierarchical Mixtures for Probabilistic Learning of Inverse Dynamics
- On the Benefit of Dual-domain Denoising in a Self-supervised Low-dose CT Setting
- AS-PD: An Arbitrary-Size Downsampling Framework for Point Clouds
- Deep Reinforcement Learning for Power Control in Next-Generation WiFi Network Systems
- Nonparametric Involutive Markov Chain Monte Carlo
- Semantic SuperPoint: A Deep Semantic Descriptor
- Recovering Sign Bits of DCT Coefficients in Digital Images as an Optimization Problem
- Improving transferability of 3D adversarial attacks with scale and shear transformations
- I4U System Description for NIST SRE'20 CTS Challenge
- Transformer-based encoder-encoder architecture for Spoken Term Detection
- Spatial Reasoning for Few-Shot Object Detection
- On Correlation Detection and Alignment Recovery of Gaussian Databases
- Stability of clinical prediction models developed using statistical or machine learning methods
- Fantasizing with Dual GPs in Bayesian Optimization and Active Learning
- Monolingual Recognizers Fusion for Code-switching Speech Recognition
- Deep Learning Computer Vision Algorithms for Real-time UAVs On-board Camera Image Processing
- Explainable AI over the Internet of Things (IoT): Overview, State-of-the-Art and Future Directions
- DynamicLight: Two-Stage Dynamic Traffic Signal Timing
- Verifying And Interpreting Neural Networks using Finite Automata
- Data-driven modeling of Landau damping by physics-informed neural networks
- Cluster-Based Autoencoders for Volumetric Point Clouds
- Bayesian sequential design of computer experiments for quantile set inversion
- Spatial-temporal recurrent reinforcement learning for autonomous ships
- Thunderstorm nowcasting with deep learning: a multi-hazard data fusion model
- A weighted-variance variational autoencoder model for speech enhancement
- How Stable is Knowledge Base Knowledge?
- Audio-visual speech enhancement with a deep Kalman filter generative model
- Autoregressive GAN for Semantic Unconditional Head Motion Generation
- Balancing Utility and Fairness in Submodular Maximization (Technical Report)
- Processing Long Legal Documents with Pre-trained Transformers: Modding LegalBERT and Longformer
- Large deviations rates for stochastic gradient descent with strongly convex functions
- Internal Language Model Estimation based Adaptive Language Model Fusion for Domain Adaptation
- Ambiguity-Aware Multi-Object Pose Optimization for Visually-Assisted Robot Manipulation
- Inflexible Multi-Asset Hedging of incomplete market
- Linear Embedding-based High-dimensional Batch Bayesian Optimization without Reconstruction Mappings
- CarDD: A New Dataset for Vision-based Car Damage Detection
- WITT: A Wireless Image Transmission Transformer for Semantic Communications
- Deep Multimodal Fusion for Generalizable Person Re-identification
- Neural Active Learning on Heteroskedastic Distributions
- SyncTalkFace: Talking Face Generation with Precise Lip-Syncing via Audio-Lip Memory
- SpeechBlender: Speech Augmentation Framework for Mispronunciation Data Generation
- Dialect-robust Evaluation of Generated Text
- A Data-driven Case-based Reasoning in Bankruptcy Prediction
- Universal Deep Image Compression via Content-Adaptive Optimization with Adapters
- Passage-Mask: A Learnable Regularization Strategy for Retriever-Reader Models
- Discover Important Paths in the Knowledge Graph Based on Dynamic Relation Confidence
- Bipartite mixed membership distribution-free model. A novel model for community detection in overlapping bipartite weighted networks
- PLATO-K: Internal and External Knowledge Enhanced Dialogue Generation
- A survey on the development status and application prospects of knowledge graph in smart grids
- LightVessel: Exploring Lightweight Coronary Artery Vessel Segmentation via Similarity Knowledge Distillation
- SIMD-size aware weight regularization for fast neural vocoding on CPU
- Pop2Piano : Pop Audio-based Piano Cover Generation
- Rethinking the Metric in Few-shot Learning: From an Adaptive Multi-Distance Perspective
- Accelerating Parallel Stochastic Gradient Descent via Non-blocking Mini-batches
- Certified Robustness of Quantum Classifiers against Adversarial Examples through Quantum Noise
- Alternating Phase Langevin Sampling with Implicit Denoiser Priors for Phase Retrieval
- DyAnNet: A Scene Dynamicity Guided Self-Trained Video Anomaly Detection Network
- Unsupervised Syntactically Controlled Paraphrase Generation with Abstract Meaning Representations
- Neural Fourier Shift for Binaural Speech Rendering
- ADPTriage: Approximate Dynamic Programming for Bug Triage
- Title2Event: Benchmarking Open Event Extraction with a Large-scale Chinese Title Dataset
- tSF: Transformer-based Semantic Filter for Few-Shot Learning
- Gradient Descent and the Power Method: Exploiting their connection to find the leftmost eigen-pair and escape saddle points
- Multi-task Learning for Source Attribution and Field Reconstruction for Methane Monitoring
- Insight into cloud processes from unsupervised classification with a rotationally invariant autoencoder
- Decoupled Cross-Scale Cross-View Interaction for Stereo Image Enhancement in The Dark
- Deep Virtual-to-Real Distillation for Pedestrian Crossing Prediction
- More Speaking or More Speakers?
- Fine-grained Visual-Text Prompt-Driven Self-Training for Open-Vocabulary Object Detection
- Heterogeneous Trajectory Forecasting via Risk and Scene Graph Learning
- RCD-SGD: Resource-Constrained Distributed SGD in Heterogeneous Environment via Submodular Partitioning
- Unsupervised Deraining: Where Asymmetric Contrastive Learning Meets Self-similarity
- Learning a Condensed Frame for Memory-Efficient Video Class-Incremental Learning
- Exploiting Spatial-temporal Correlations for Video Anomaly Detection
- Synthesizing Programs with Continuous Optimization
- TSAA: A Two-Stage Anchor Assignment Method towards Anchor Drift in Crowded Object Detection
- LMD: A Learnable Mask Network to Detect Adversarial Examples for Speaker Verification
- Adversarial Auto-Augment with Label Preservation: A Representation Learning Principle Guided Approach
- A new method for determining Wasserstein 1 optimal transport maps from Kantorovich potentials, with deep learning applications
- Interpretable estimation of the risk of heart failure hospitalization from a 30-second electrocardiogram
- CodePAD: Sequence-based Code Generation with Pushdown Automaton
- An Information-Theoretic Approach for Estimating Scenario Generalization in Crowd Motion Prediction
- Unsupervised Model Adaptation for Source-free Segmentation of Medical Images
- Optical Channel Impulse Response-Based Localization Using An Artificial Neural Network
- Geodesic Sinkhorn for Fast and Accurate Optimal Transport on Manifolds
- Concrete Score Matching: Generalized Score Matching for Discrete Data
- Multi-Agent Reinforcement Learning for Adaptive Mesh Refinement
- Practical Phase Retrieval Using Double Deep Image Priors
- InterMPL: Momentum Pseudo-Labeling with Intermediate CTC Loss
- Impact of annotation modality on label quality and model performance in the automatic assessment of laughter in-the-wild
- BECTRA: Transducer-based End-to-End ASR with BERT-Enhanced Encoder