Papers
Mon 30 May 2022
223 papers
- Few-Shot Diffusion ModelsDiffusion models → Diffusion foundations and sampling
- Causal Explanations for Sequential Decision Making Under UncertaintyLLM reasoning → Causal reasoning in LLMs
- Minimax Optimal Online Imitation Learning via Replay EstimationOffline RL and imitation learning from data → Imitation learning methods
- Guided-TTS 2: A Diffusion Model for High-quality Adaptive Text-to-Speech with Untranscribed DataDiffusion models → Audio, speech and music
- Non-Markovian Reward Modelling from Trajectory Labels via Interpretable Multiple Instance LearningLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
- Multi-Game Decision TransformersOffline RL and imitation learning from data → Decision transformers and sequence modeling
- VLUE: A Multi-Task Benchmark for Evaluating Vision-Language ModelsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
- Backpropagation through Combinatorial Algorithms: Identity with Projection WorksLLM reasoning → Diffusion reasoning and test-time scaling
- Towards Efficient 3D Object Detection with Knowledge DistillationKnowledge distillation → Detection and dense prediction distillation
- A Continuous Time Framework for Discrete Denoising ModelsDiffusion models → Diffusion foundations and sampling
- Knowledge Distillation for 6D Pose Estimation by Aligning Distributions of Local PredictionsKnowledge distillation → Detection and dense prediction distillation
- Guided Diffusion Model for Adversarial PurificationDiffusion models → Robustness, privacy and adversarial aspects
- From Representation to Reasoning: Towards both Evidence and Commonsense Reasoning for Video Question-AnsweringLLM reasoning → Multimodal reasoning
- Time3D: End-to-End Joint Monocular 3D Object Detection and Tracking for Autonomous DrivingEnd-to-end autonomous driving → VLMs for autonomous driving
- Prompt-aligned Gradient for Prompt TuningMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
- Play it by Ear: Learning Skills amidst Occlusion through Audio-Visual Imitation LearningOffline RL and imitation learning from data → Robot manipulation imitation learning
- Excess Risk of Two-Layer ReLU Neural Networks in Teacher-Student Settings and its Superiority to Kernel MethodsKnowledge distillation → General knowledge distillation methods
- TaSIL: Taylor Series Imitation LearningOffline RL and imitation learning from data → Imitation learning methods
- BinauralGrad: A Two-Stage Conditional Diffusion Probabilistic Model for Binaural Audio SynthesisDiffusion models → Audio, speech and music
- Radar Image Reconstruction from Raw ADC Data using Parametric Variational Autoencoder with Domain Adaptation
- Multi-Fault Diagnosis Of Industrial Rotating Machines Using Data-Driven Approach: A Review Of Two Decades Of Research
- Transformer with Tree-order Encoding for Neural Program Generation
- Analysis of Augmentations for Contrastive ECG Representation Learning
- Blind Estimation of a Doubly Selective OFDM Channel: A Deep Learning Algorithm and Theory
- Securing AI-based Healthcare Systems using Blockchain Technology: A State-of-the-Art Systematic Literature Review and Future Research Directions
- White-box Membership Attack Against Machine Learning Based Retinopathy Classification
- Rites de Passage: Elucidating Displacement to Emplacement of Refugees on Twitter
- Towards Fair Federated Recommendation Learning: Characterizing the Inter-Dependence of System and Data Heterogeneity
- Contextualization for the Organization of Text Documents Streams
- Towards retrieving dispersion profiles using quantum-mimic Optical Coherence Tomography and Machine Learnin
- A Comparative Study on Energy Consumption Models for Drones
- PreBit -- A multimodal model with Twitter FinBERT embeddings for extreme price movement prediction of Bitcoin
- DEP-RL: Embodied Exploration for Reinforcement Learning in Overactuated and Musculoskeletal Systems
- Median Pixel Difference Convolutional Network for Robust Face Recognition
- Braille Letter Reading: A Benchmark for Spatio-Temporal Pattern Recognition on Neuromorphic Hardware
- Adversarial synthesis based data-augmentation for code-switched spoken language identification
- GCoNet+: A Stronger Group Collaborative Co-Salient Object Detector
- Data Banzhaf: A Robust Data Valuation Framework for Machine Learning
- Analyzing Modality Robustness in Multimodal Sentiment Analysis
- Critic Sequential Monte Carlo
- Bayesian Active Learning for Scanning Probe Microscopy: from Gaussian Processes to Hypothesis Learning
- Registering Image Volumes using 3D SIFT and Discrete SP-Symmetry
- A Simulation Environment and Reinforcement Learning Method for Waste Reduction
- MVMO: A Multi-Object Dataset for Wide Baseline Multi-View Semantic Segmentation
- Posterior and Computational Uncertainty in Gaussian Processes
- FeatER: An Efficient Network for Human Reconstruction via Feature Map-Based TransformER
- Holistic Generalized Linear Models
- Continual Object Detection: A review of definitions, strategies, and challenges
- Exploring Advances in Transformers and CNN for Skin Lesion Diagnosis on Small Datasets
- StyleTTS: A Style-Based Generative Model for Natural and Diverse Text-to-Speech Synthesis
- AMED: Automatic Mixed-Precision Quantization for Edge Devices
- Uncertainty Quantification for Fairness in Two-Stage Recommender Systems
- A Game-Theoretic Framework for Managing Risk in Multi-Agent Systems
- Segmentation Consistency Training: Out-of-Distribution Generalization for Medical Image Segmentation
- Fitting and recognition of geometric primitives in segmented 3D point clouds using a localized voting procedure
- Connecting adversarial attacks and optimal transport for domain adaptation
- Fool SHAP with Stealthily Biased Sampling
- A portfolio-based analysis method for competition results
- PolypConnect: Image inpainting for generating realistic gastrointestinal tract images with polyps
- LiDAR-aid Inertial Poser: Large-scale Human Motion Capture by Sparse Inertial and LiDAR Sensors
- Grid HTM: Hierarchical Temporal Memory for Anomaly Detection in Videos
- Gator: Customizable Channel Pruning of Neural Networks with Gating
- Neural Optimal Transport with General Cost Functionals
- VoGE: A Differentiable Volume Renderer using Gaussian Ellipsoids for Analysis-by-Synthesis
- Designing Rewards for Fast Learning
- A hybrid approach to seismic deblending: when physics meets self-supervision
- Attention Flows for General Transformers
- Dictionary Learning with Accumulator Neurons
- Truly Deterministic Policy Optimization
- Reinforcement Learning with a Terminator
- Optimistic Whittle Index Policy: Online Learning for Restless Bandits
- Infinite-dimensional optimization and Bayesian nonparametric learning of stochastic differential equations
- TubeFormer-DeepLab: Video Mask Transformer
- AI-enabled Sound Pattern Recognition on Asthma Medication Adherence: Evaluation with the RDA Benchmark Suite
- Searching for the Essence of Adversarial Perturbations
- Superposing Many Tickets into One: A Performance Booster for Sparse Neural Network Training
- Payday loans -- blessing or growth suppressor? Machine Learning Analysis
- AdaProp: Learning Adaptive Propagation for Graph Neural Network based Knowledge Graph Reasoning
- Chefs' Random Tables: Non-Trigonometric Random Features
- Can Transformer be Too Compositional? Analysing Idiom Processing in Neural Machine Translation
- Adapting Rapid Motor Adaptation for Bipedal Robots
- Efficient Phi-Regret Minimization in Extensive-Form Games via Online Mirror Descent
- An Approach to Ordering Objectives and Pareto Efficient Solutions
- Zero-Shot and Few-Shot Learning for Lung Cancer Multi-Label Classification using Vision Transformer
- Self-Supervised Visual Representation Learning with Semantic Grouping
- Fast Dynamic Radiance Fields with Time-Aware Neural Voxels
- Learning Open Domain Multi-hop Search Using Reinforcement Learning
- Testing for Geometric Invariance and Equivariance
- EAMM: One-Shot Emotional Talking Face via Audio-Based Emotion-Aware Motion Model
- MetaSSD: Meta-Learned Self-Supervised Detection
- Kernel Neural Optimal Transport
- Federated X-Armed Bandit
- Going Beyond One-Hot Encoding in Classification: Can Human Uncertainty Improve Model Performance?
- bsnsing: A decision tree induction method based on recursive optimal boolean rule composition
- Pooling Revisited: Your Receptive Field is Suboptimal
- Residual Q-Networks for Value Function Factorizing in Multi-Agent Reinforcement Learning
- Re-parameterizing Your Optimizers rather than Architectures
- Conformal Credal Self-Supervised Learning
- RankSim: Ranking Similarity Regularization for Deep Imbalanced Regression
- Non-convex online learning via algorithmic equivalence
All 223
- Few-Shot Adaptation of Pre-Trained Networks for Domain Shift
- A Survey in Mathematical Language Processing
- Few-shot Class-incremental Learning for 3D Point Cloud Objects
- Prompting ELECTRA: Few-Shot Learning with Discriminative Pre-Trained Models
- Automatic Short Math Answer Grading via In-context Meta-learning
- A Graph and Attentive Multi-Path Convolutional Network for Traffic Prediction
- GraphWalks: Efficient Shape Agnostic Geodesic Shortest Path Estimation
- Support Recovery in Sparse PCA with Incomplete Data
- The Devil is in the Pose: Ambiguity-free 3D Rotation-invariant Learning via Pose-aware Convolution
- Flowification: Everything is a Normalizing Flow
- STN: Scalable Tensorizing Networks via Structure-Aware Training and Adaptive Compression
- PAC Generalization via Invariant Representations
- Do Deep Neural Networks Always Perform Better When Eating More Data?
- A Review and Evaluation of Elastic Distance Functions for Time Series Clustering
- ShuffleMixer: An Efficient ConvNet for Image Super-Resolution
- Self-Supervised Pre-training of Vision Transformers for Dense Prediction Tasks
- Billions of Parameters Are Worth More Than In-domain Training Data: A case study in the Legal Case Entailment Task
- Modular and On-demand Bias Mitigation with Attribute-Removal Subnetworks
- GAN-based Medical Image Small Region Forgery Detection via a Two-Stage Cascade Framework
- Updating belief functions over Belnap--Dunn logic
- Principal Component Analysis based frameworks for efficient missing data imputation algorithms
- Batch Normalization Is Blind to the First and Second Derivatives of the Loss
- Machine Learning Methods for Health-Index Prediction in Coating Chambers
- Special Properties of Gradient Descent with Large Learning Rates
- Theme Aspect Argumentation Model for Handling Fallacies
- Detecting fake news by enhanced text representation with multi-EDU-structure awareness
- Optimal Gradient Sliding and its Application to Distributed Optimization Under Similarity
- Group Probability-Weighted Tree Sums for Interpretable Modeling of Heterogeneous Data
- Why Adversarial Training of ReLU Networks Is Difficult?
- Level Up with ML Vulnerability Identification: Leveraging Domain Constraints in Feature Space for Robust Android Malware Detection
- Universal Deep GNNs: Rethinking Residual Connection in GNNs from a Path Decomposition Perspective for Preventing the Over-smoothing
- Elastic Monte Carlo Tree Search with State Abstraction for Strategy Game Playing
- Mixed-Effect Thompson Sampling
- Towards Supporting Intelligence in 5G/6G Core Networks: NWDAF Implementation and Initial Analysis
- OOD Link Prediction Generalization Capabilities of Message-Passing GNNs in Larger Test Graphs
- Online Agnostic Multiclass Boosting
- A k nearest neighbours classifiers ensemble based on extended neighbourhood rule and features subsets
- FLICU: A Federated Learning Workflow for Intensive Care Unit Mortality Prediction
- Meta Representation Learning with Contextual Linear Bandits
- CHALLENGER: Training with Attribution Maps
- Retrieving and Ranking Relevant JavaScript Technologies from Web Repositories
- CGMN: A Contrastive Graph Matching Network for Self-Supervised Graph Similarity Learning
- Improved Algorithms for Bandit with Graph Feedback via Regret Decomposition
- Align then Fusion: Generalized Large-scale Multi-view Clustering with Anchor Matching Correspondences
- Embedding Graphs on Grassmann Manifold
- SEREN: Knowing When to Explore and When to Exploit
- A Transistor Operations Model for Deep Learning Energy Consumption Scaling Law
- Duplex Conversation: Towards Human-like Interaction in Spoken Dialogue Systems
- Hilbert Curve Projection Distance for Distribution Comparison
- Stock Trading Optimization through Model-based Reinforcement Learning with Resistance Support Relative Strength
- Deblurring Photographs of Characters Using Deep Neural Networks
- X-SCITLDR: Cross-Lingual Extreme Summarization of Scholarly Documents
- Metrizing Fairness
- RLx2: Training a Sparse Deep Reinforcement Learning Model from Scratch
- Learnable Patchmatch and Self-Teaching for Multi-Frame Depth Estimation in Monocular Endoscopy
- An Efficient Modern Baseline for FloodNet VQA
- Agnostic Physics-Driven Deep Learning
- A Fundamental Probabilistic Fuzzy Logic Framework Suitable for Causal Reasoning
- Task-Prior Conditional Variational Auto-Encoder for Few-Shot Image Classification
- Efficient Transformed Gaussian Processes for Non-Stationary Dependent Multi-class Classification
- Running the Dual-PQC GAN on noisy simulators and real quantum hardware
- CompleteDT: Point Cloud Completion with Dense Augment Inference Transformers
- Quantum Multi-Armed Bandits and Stochastic Linear Bandits Enjoy Logarithmic Regrets
- GMML is All you Need
- ZusammenQA: Data Augmentation with Specialized Models for Cross-lingual Open-retrieval Question Answering System
- Fast Nonlinear Vector Quantile Regression
- Rethinking Saliency Map: An Context-aware Perturbation Method to Explain EEG-based Deep Learning Model
- PSNet: Fast Data Structuring for Hierarchical Deep Learning on Point Cloud
- Sampling-free Inference for Ab-Initio Potential Energy Surface Networks
- FedAUXfdp: Differentially Private One-Shot Federated Distillation
- Dataset Condensation via Efficient Synthetic-Data Parameterization
- AttentionCode: Ultra-Reliable Feedback Codes for Short-Packet Communications
- Multi-Agent Reinforcement Learning is a Sequence Modeling Problem
- Benchmarking the Robustness of LiDAR-Camera Fusion for 3D Object Detection
- HiViT: Hierarchical Vision Transformer Meets Masked Image Modeling
- Data-driven Numerical Invariant Synthesis with Automatic Generation of Attributes
- Edge YOLO: Real-Time Intelligent Object Detection System Based on Edge-Cloud Cooperation in Autonomous Vehicles
- Detecting Unknown DGAs without Context Information
- Spectral Maps for Learning on Subgraphs
- Deep Learning Methods for Fingerprint-Based Indoor Positioning: A Review
- Neural Volumetric Object Selection
- CalFAT: Calibrated Federated Adversarial Training with Label Skewness
- Unbalanced CO-Optimal Transport
- ACIL: Analytic Class-Incremental Learning with Absolute Memorization and Privacy Protection
- A Deep Learning Approach for Automatic Detection of Qualitative Features of Lecturing
- Uncertainty Quantification and Resource-Demanding Computer Vision Applications of Deep Learning
- E2S2: Encoding-Enhanced Sequence-to-Sequence Pretraining for Language Understanding and Generation
- Adaptive color transfer from images to terrain visualizations
- Confederated Learning: Federated Learning with Decentralized Edge Servers
- FRAug: Tackling Federated Learning with Non-IID Features via Representation Augmentation
- Daisy Bloom Filters
- Exploring the Open World Using Incremental Extreme Value Machines
- Deep Posterior Distribution-based Embedding for Hyperspectral Image Super-resolution
- Neural Shape Mating: Self-Supervised Object Assembly with Adversarial Shape Priors
- Easter2.0: Improving convolutional models for handwritten text recognition
- You Only Need 90K Parameters to Adapt Light: A Light Weight Transformer for Image Enhancement and Exposure Correction
- Compressible-composable NeRF via Rank-residual Decomposition
- Measuring and mitigating voting access disparities: a study of race and polling locations in Florida and North Carolina
- Leave-one-out Singular Subspace Perturbation Analysis for Spectral Clustering
- Anti-virus Autobots: Predicting More Infectious Virus Variants for Pandemic Prevention through Deep Learning
- Benchmarking Unsupervised Anomaly Detection and Localization
- Exposing Fine-Grained Adversarial Vulnerability of Face Anti-Spoofing Models
- EA2E: Improving Consistency with Event Awareness for Document-Level Argument Extraction
- Precise Learning Curves and Higher-Order Scaling Limits for Dot Product Kernel Regression
- Efficient Reward Poisoning Attacks on Online Deep Reinforcement Learning
- Maximizing Global Model Appeal in Federated Learning
- Adversarial Bandits against Arbitrary Strategies
- Most Equitable Voting Rules
- Enhancing Sequential Recommendation with Graph Contrastive Learning
- GraMeR: Graph Meta Reinforcement Learning for Multi-Objective Influence Maximization
- Walle: An End-to-End, General-Purpose, and Large-Scale Production System for Device-Cloud Collaborative Machine Learning
- Temporal Multiresolution Graph Neural Networks For Epidemic Prediction
- Adaptive Sampling for Discovery
- Lepton Flavour Violation Identification in Tau Decay (τ- rightarrow μ-μ-μ+) Using Artificial Intelligence
- Robust Weight Perturbation for Adversarial Training
- Bayesian Low-Rank Interpolative Decomposition for Complex Datasets
- Universality of Group Convolutional Neural Networks Based on Ridgelet Analysis on Groups
- Mitigating Out-of-Distribution Data Density Overestimation in Energy-Based Models
- Your Contrastive Learning Is Secretly Doing Stochastic Neighbor Embedding
- Last-iterate convergence analysis of stochastic momentum methods for neural networks
- Random Rank: The One and Only Strategyproof and Proportionally Fair Randomized Facility Location Mechanism
- Temporal Latent Bottleneck: Synthesis of Fast and Slow Processing Mechanisms in Sequence Learning
- End-to-End Topology-Aware Machine Learning for Power System Reliability Assessment