mlsanityData to 14 Oct 2026

Papers

New on arXiv

Thu 2 Mar 2023

253 papers

  1. ConTEXTual Net: A Multimodal Vision-Language Model for Segmentation of PneumothoraxMultimodal LLMs / vision-language models → Medical vision-language models
  2. Sparse MoE as the New Dropout: Scaling Dense and Self-Slimmable TransformersMixture-of-experts → Expert routing strategies
  3. Alexa Arena: A User-Centric Interactive Platform for Embodied AIWorld models → World models for navigation
  4. Defending against Adversarial Audio via Diffusion ModelDiffusion models → Robustness, privacy and adversarial aspects
  5. Teach a Robot to FISH: Versatile Imitation from One Minute of DemonstrationsOffline RL and imitation learning from data → Robot manipulation imitation learning
  6. Consistency ModelsDiffusion models → Diffusion foundations and sampling
  7. Programmatic Imitation Learning from Unlabeled and Noisy DemonstrationsOffline RL and imitation learning from data → Imitation learning methods
  8. Human Motion Diffusion as a Generative PriorDiffusion models → Video generation
  9. iART: Learning from Demonstration for Assisted Robotic Therapy Using LSTMOffline RL and imitation learning from data → Robot learning from demonstration
  10. Letz Translate: Low-Resource Machine Translation for LuxembourgishKnowledge distillation → Knowledge distillation for LLMs
  11. MixPHM: Redundancy-Aware Parameter-Efficient Tuning for Low-Resource Visual Question AnsweringMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  12. Grid-Centric Traffic Scenario Perception for Autonomous Driving: A Comprehensive ReviewEnd-to-end autonomous driving → End-to-end system architecture
  13. Learning From Yourself: A Self-Distillation Method for Fake Speech DetectionKnowledge distillation → Speech and audio distillation
  14. Iterative Circuit Repair Against Formal SpecificationsMechanistic interpretability → Circuits and mechanistic analysis
  15. Distillation from Heterogeneous Models for Top-K RecommendationKnowledge distillation → Distillation for recommender systems
  16. Open-World Object Manipulation using Pre-trained Vision-Language ModelsMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  17. Active Reward Learning from Multiple TeachersLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
  18. Distributed Learning Meets 6G: A Communication and Computing Perspective
  19. A Data Augmentation Method and the Embedding Mechanism for Detection and Classification of Pulmonary Nodules on Small Samples
  20. IoT Device Identification Based on Network Communication Analysis Using Deep Learning
  21. EdgeServe: A Streaming System for Decentralized Model Serving
  22. Uniform Pessimistic Risk and its Optimal Portfolio
  23. Practical Statistical Considerations for the Clinical Validation of AI/ML-enabled Medical Diagnostic Devices
  24. Converting the Suggested Upper Merged Ontology to Typed First-order Form
  25. Robust Semi-Supervised Anomaly Detection via Adversarially Learned Continuous Noise Corruption
  26. CoSyn: Detecting Implicit Hate Speech in Online Conversations Using a Context Synergized Hyperbolic Network
  27. Evaluating Parameter-Efficient Transfer Learning Approaches on SURE Benchmark for Speech Understanding
  28. Population-based Evaluation in Repeated Rock-Paper-Scissors as a Benchmark for Multiagent Reinforcement Learning
  29. T-Cell Receptor Optimization with Reinforcement Learning and Mutation Policies for Precesion Immunotherapy
  30. Navigates Like Me: Understanding How People Evaluate Human-Like AI in Video Games
  31. BioImageLoader: Easy Handling of Bioimage Datasets for Machine Learning
  32. ACL-SPC: Adaptive Closed-Loop system for Self-Supervised Point Cloud Completion
  33. Multi-Start Team Orienteering Problem for UAS Mission Re-Planning with Data-Efficient Deep Reinforcement Learning
  34. Less is More: Mitigate Spurious Correlations for Open-Domain Dialogue Response Generation Models by Causal Discovery
  35. Artificial Intelligence for Dementia Research Methods Optimization
  36. Real-Time Tube-Based Non-Gaussian Risk Bounded Motion Planning for Stochastic Nonlinear Systems in Uncertain Environments via Motion Primitives
  37. Learning to Adapt to Online Streams with Distribution Shifts
  38. Non-Gaussian Uncertainty Minimization Based Control of Stochastic Nonlinear Robotic Systems
  39. GlucoSynth: Generating Differentially-Private Synthetic Glucose Traces
  40. Deconstructing deep active inference
  41. Hierarchical discriminative learning improves visual representations of biomedical microscopy
  42. A Meta-Learning Approach to Predicting Performance and Data Requirements
  43. QAID: Question Answering Inspired Few-shot Intent Detection
  44. Joint cortical registration of geometry and function using semi-supervised learning
  45. Technical report: Graph Neural Networks go Grammatical
  46. AZTR: Aerial Video Action Recognition with Auto Zoom and Temporal Reasoning
  47. Evolutionary Augmentation Policy Optimization for Self-supervised Learning
  48. A Few-Shot Attention Recurrent Residual U-Net for Crack Segmentation
  49. Mixture of Soft Prompts for Controllable Data Generation
  50. DeepLens: Interactive Out-of-distribution Data Detection in NLP Models
  51. DeepSeer: Interactive RNN Explanation and Debugging via State Abstraction
  52. DejaVu: Conditional Regenerative Learning to Enhance Dense Prediction
  53. Chemically Transferable Generative Backmapping of Coarse-Grained Proteins
  54. Deep Neural Networks with Efficient Guaranteed Invariances
  55. On the Provable Advantage of Unsupervised Pretraining
  56. Data-efficient, Explainable and Safe Box Manipulation: Illustrating the Advantages of Physical Priors in Model-Predictive Control
  57. Active Learning and Bayesian Optimization: a Unified Perspective to Learn with a Goal
  58. Improving GAN Training via Feature Space Shrinkage
  59. BenchDirect: A Directed Language Model for Compiler Benchmarks
  60. Counterfactual Edits for Generative Evaluation
  61. Simultaneous prediction of hand gestures, handedness, and hand keypoints using thermal images
  62. MiShape: 3D Shape Modelling of Mitochondria in Microscopy
  63. Decision-Oriented Learning with Differentiable Submodular Maximization for Vehicle Routing Problem
  64. Self-attention in Vision Transformers Performs Perceptual Grouping, Not Attention
  65. Variational EP with Probabilistic Backpropagation for Bayesian Neural Networks
  66. Feature Perturbation Augmentation for Reliable Evaluation of Importance Estimators in Neural Networks
  67. Semantic Attention Flow Fields for Monocular Dynamic Scene Decomposition
  68. Optimization-Based Deep learning methods for Magnetic Resonance Imaging Reconstruction and Synthesis
  69. Safe AI for health and beyond -- Monitoring to transform a health service
  70. Bayesian Posterior Perturbation Analysis with Integral Probability Metrics
  71. INO at Factify 2: Structure Coherence based Multi-Modal Fact Verification
  72. EPAM: A Predictive Energy Model for Mobile AI
  73. Fine-grained Emotional Control of Text-To-Speech: Learning To Rank Inter- And Intra-Class Emotion Intensities
  74. Understanding and Unifying Fourteen Attribution Methods with Taylor Interactions
  75. Ternary Quantization: A Survey
  76. FeatAug-DETR: Enriching One-to-Many Matching for DETRs with Feature Augmentation
  77. Computational Language Acquisition with Theory of Mind
  78. Stability and Machine Learning Applications of Persistent Homology Using the Delaunay-Rips Complex
  79. Dropout Reduces Underfitting
  80. ABAW: Valence-Arousal Estimation, Expression Recognition, Action Unit Detection & Emotional Reaction Intensity Estimation Challenges
  81. Image as Set of Points
  82. Transferring Models Trained on Natural Images to 3D MRI via Position Encoded Slice Models
  83. Language Variety Identification with True Labels
  84. Self-Improving Robots: End-to-End Autonomous Visuomotor Reinforcement Learning
  85. Understanding plasticity in neural networks
  86. Predicting Motion Plans for Articulating Everyday Objects
  87. Auxiliary Functions as Koopman Observables: Data-Driven Analysis of Dynamical Systems via Polynomial Optimization
  88. Delivering Arbitrary-Modal Semantic Segmentation
  89. Over-training with Mixup May Hurt Generalization
  90. Quantum Hamiltonian Descent
  91. Dataset Creation Pipeline for Camera-Based Heart Rate Estimation
  92. MoSFPAD: An end-to-end Ensemble of MobileNet and Support Vector Classifier for Fingerprint Presentation Attack Detection
  93. Efficient Rate Optimal Regret for Adversarial Contextual MDPs Using Online Function Approximation
  94. Benign Overfitting in Linear Classifiers and Leaky ReLU Networks from KKT Conditions for Margin Maximization
  95. The Double-Edged Sword of Implicit Bias: Generalization vs. Robustness in ReLU Networks
  96. Learning Contact-based Navigation in Crowds
  97. Improved Space Bounds for Learning with Experts
  98. Do Machine Learning Models Learn Statistical Rules Inferred from Data?
  99. WiCE: Real-World Entailment for Claims in Wikipedia
  100. Optimal transfer protocol by incremental layer defrosting
All 253
  1. Design-based conformal prediction
  2. Learn to Memorize: Scalable Continual Learning in Semiparametric Models with Mixture-of-Neighbors Induction Memory
  3. 3D generation on ImageNet
  4. The Challenges of Hyperparameter Tuning for Accurate Causal Effect Estimation
  5. NLP Workbench: Efficient and Extensible Integration of State-of-the-art Text Mining Tools
  6. Sparse-penalized deep neural networks estimator under weak dependence
  7. MLANet: Multi-Level Attention Network with Sub-instruction for Continuous Vision-and-Language Navigation
  8. The Ladder in Chaos: A Simple and Effective Improvement to General DRL Algorithms by Policy Path Trimming and Boosting
  9. Machine Learning-Based Detection of Parkinson's Disease From Resting-State EEG: A Multi-Center Study
  10. Reinforced Labels: Multi-Agent Deep Reinforcement Learning for Point-Feature Label Placement
  11. DAVA: Disentangling Adversarial Variational Autoencoder
  12. A Vision for Semantically Enriched Data Science
  13. BEL: A Bag Embedding Loss for Transformer enhances Multiple Instance Whole Slide Image Classification
  14. High-dimensional analysis of double descent for linear regression with random projections
  15. Deep-NFA: a Deep textita contrario Framework for Small Object Detection
  16. Penalising the biases in norm regularisation enforces sparsity
  17. APARATE: Adaptive Adversarial Patch for CNN-based Monocular Depth Estimation for Autonomous Navigation
  18. Co-learning Planning and Control Policies Constrained by Differentiable Logic Specifications
  19. PlaNet-ClothPick: Effective Fabric Flattening Based on Latent Dynamic Planning
  20. Active Learning Enhances Classification of Histopathology Whole Slide Images with Attention-based Multiple Instance Learning
  21. Matching-based Term Semantics Pre-training for Spoken Patient Query Understanding
  22. AdvRain: Adversarial Raindrops to Attack Camera-based Smart Vision Systems
  23. First-order ANIL provably learns representations despite overparametrization
  24. Self-Supervised Few-Shot Learning for Ischemic Stroke Lesion Segmentation
  25. Canonical mapping as a general-purpose object descriptor for robotic manipulation
  26. A Pathway Towards Responsible AI Generated Content
  27. Weakly-supervised HOI Detection via Prior-guided Bi-level Representation Learning
  28. Zero-Shot Text-to-Parameter Translation for Game Character Auto-Creation
  29. BIFRNet: A Brain-Inspired Feature Restoration DNN for Partially Occluded Image Recognition
  30. Reasoning-Based Software Testing
  31. Compensating for Sensing Failures via Delegation in Human-AI Hybrid Systems
  32. Creating Synthetic Datasets for Collaborative Filtering Recommender Systems using Generative Adversarial Networks
  33. Iterative Assessment and Improvement of DNN Operational Accuracy
  34. Rethinking the Effect of Data Augmentation in Adversarial Contrastive Learning
  35. Cluster-Guided Semi-Supervised Domain Adaptation for Imbalanced Medical Image Classification
  36. Boosting Distributed Full-graph GNN Training with Asynchronous One-bit Communication
  37. Conflict-Based Cross-View Consistency for Semi-Supervised Semantic Segmentation
  38. Measuring axiomatic soundness of counterfactual image models
  39. Navigating the Metric Maze: A Taxonomy of Evaluation Metrics for Anomaly Detection in Time Series
  40. Analyzing Effects of Fake Training Data on the Performance of Deep Learning Systems
  41. Token Contrast for Weakly-Supervised Semantic Segmentation
  42. Steering Graph Neural Networks with Pinning Control
  43. Choosing Public Datasets for Private Machine Learning via Gradient Subspace Distance
  44. FlowFormer++: Masked Cost Volume Autoencoding for Pretraining Optical Flow Estimation
  45. Evaluation of drain, a deep-learning approach to rain retrieval from gpm passive microwave radiometer
  46. A Coarse to Fine Framework for Object Detection in High Resolution Image
  47. Synthetic Misinformers: Generating and Combating Multimodal Misinformation
  48. Why (and When) does Local SGD Generalize Better than SGD?
  49. DSD2: Can We Dodge Sparse Double Descent and Compress the Neural Network Worry-Free?
  50. Average of Pruning: Improving Performance and Stability of Out-of-Distribution Detection
  51. Document Provenance and Authentication through Authorship Classification
  52. STDepthFormer: Predicting Spatio-temporal Depth from Video with a Self-supervised Transformer Model
  53. UZH_CLyp at SemEval-2023 Task 9: Head-First Fine-Tuning and ChatGPT Data Generation for Cross-Lingual Learning in Tweet Intimacy Prediction
  54. Interpretable System Identification and Long-term Prediction on Time-Series Data
  55. Denoising-based UNMT is more robust to word-order divergence than MASS-based UNMT
  56. Discrete-time Competing-Risks Regression with or without Penalization
  57. iSAGE: An Incremental Version of SAGE for Online Explanation on Data Streams
  58. SHAP-IQ: Unified Approximation of any-order Shapley Interactions
  59. Augmenting Medical Imaging: A Comprehensive Catalogue of 65 Techniques for Enhanced Data Analysis
  60. Resource-Constrained Station-Keeping for Helium Balloons using Reinforcement Learning
  61. Expert-Free Online Transfer Learning in Multi-Agent Reinforcement Learning
  62. Risk-aware Path Planning via Probabilistic Fusion of Traversability Prediction for Planetary Rovers on Heterogeneous Terrains
  63. BPT: Binary Point Cloud Transformer for Place Recognition
  64. A Notion of Feature Importance by Decorrelation and Detection of Trends by Random Forest Regression
  65. GeoLab: Geometry-based Tractography Parcellation of Superficial White Matter
  66. DeepSaDe: Learning Neural Networks that Guarantee Domain Constraint Satisfaction
  67. Cardinality Estimation over Knowledge Graphs with Embeddings and Graph Neural Networks
  68. Tight Risk Bounds for Gradient Descent on Separable Data
  69. Error mitigation of entangled states using brainbox quantum autoencoders
  70. Distilling Multi-Level X-vector Knowledge for Small-footprint Speaker Verification
  71. In all LikelihoodS: How to Reliably Select Pseudo-Labeled Data for Self-Training in Semi-Supervised Learning
  72. Visual Atoms: Pre-training Vision Transformers with Sinusoidal Waves
  73. Predicting Stock Price Movement as an Image Classification Problem
  74. Evidence-empowered Transfer Learning for Alzheimer's Disease
  75. Multi-Head Multi-Loss Model Calibration
  76. CTRLStruct: Dialogue Structure Learning for Open-Domain Response Generation
  77. ArCL: Enhancing Contrastive Learning with Augmentation-Robust Representations
  78. OPE-SR: Orthogonal Position Encoding for Designing a Parameter-free Upsampling Module in Arbitrary-scale Image Super-Resolution
  79. LiteG2P: A fast, light and high accuracy model for grapheme-to-phoneme conversion
  80. GBMST: An Efficient Minimum Spanning Tree Clustering Based on Granular-Ball Computing
  81. Can BERT Refrain from Forgetting on Sequential Tasks? A Probing Study
  82. LANDMARK: Language-guided Representation Enhancement Framework for Scene Graph Generation
  83. Hallucinated Adversarial Control for Conservative Offline Policy Evaluation
  84. Learning not to Regret
  85. GHQ: Grouped Hybrid Q Learning for Heterogeneous Cooperative Multi-agent Reinforcement Learning
  86. Implicit Neural Representations for Modeling of Abdominal Aortic Aneurysm Progression
  87. Targeted Adversarial Attacks against Neural Machine Translation
  88. AI and the FCI: Can ChatGPT Project an Understanding of Introductory Physics?
  89. Adopting the Multi-answer Questioning Task with an Auxiliary Metric for Extreme Multi-label Text Classification Utilizing the Label Hierarchy
  90. Physics-informed neural networks for solving forward and inverse problems in complex beam systems
  91. Deep Learning based Segmentation of Optical Coherence Tomographic Images of Human Saphenous Varicose Vein
  92. Demystifying Causal Features on Adversarial Examples and Causal Inoculation for Robust Network by Adversarial Instrumental Variable Regression
  93. Model-based Constrained MDP for Budget Allocation in Sequential Incentive Marketing
  94. Task-Specific Context Decoupling for Object Detection
  95. Jointly Visual- and Semantic-Aware Graph Memory Networks for Temporal Sentence Localization in Videos
  96. I2P-Rec: Recognizing Images on Large-scale Point Cloud Maps through Bird's Eye View Projections
  97. Reinforcement Learning Guided Multi-Objective Exam Paper Generation
  98. Neural Intrinsic Embedding for Non-rigid Point Cloud Matching
  99. Google USM: Scaling Automatic Speech Recognition Beyond 100 Languages
  100. Validated respiratory drug deposition predictions from 2D and 3D medical images with statistical shape models and convolutional neural networks
  101. Multi-Task Self-Supervised Time-Series Representation Learning
  102. ESceme: Vision-and-Language Navigation with Episodic Scene Memory
  103. Node Embedding from Hamiltonian Information Propagation in Graph Neural Networks
  104. Specformer: Spectral Graph Neural Networks Meet Transformers
  105. CADeSH: Collaborative Anomaly Detection for Smart Homes
  106. Domain Adaptation of Reinforcement Learning Agents based on Network Service Proximity
  107. Target Domain Data induces Negative Transfer in Mixed Domain Training with Disjoint Classes
  108. X&Fuse: Fusing Visual Information in Text-to-Image Generation
  109. Unsupervised Meta-Learning via Few-shot Pseudo-supervised Contrastive Learning
  110. Pay Less But Get More: A Dual-Attention-based Channel Estimation Network for Massive MIMO Systems with Low-Density Pilots
  111. Encoding of data sets and algorithms
  112. Using simulation to quantify the performance of automotive perception systems
  113. Learning to Grow Pretrained Models for Efficient Transformer Training
  114. Multi-Source Soft Pseudo-Label Learning with Domain Similarity-based Weighting for Semantic Segmentation
  115. Leveraging Large Text Corpora for End-to-End Speech Summarization
  116. Ego-Vehicle Action Recognition based on Semi-Supervised Contrastive Learning
  117. Image Labels Are All You Need for Coarse Seagrass Segmentation
  118. Practical Network Acceleration with Tiny Sets: Hypothesis, Theory, and Algorithm
  119. Disentangling Orthogonal Planes for Indoor Panoramic Room Layout Estimation with Cross-Scale Distortion Awareness
  120. PAPAL: A Provable PArticle-based Primal-Dual ALgorithm for Mixed Nash Equilibrium
  121. Rethinking the Reasonability of the Test Set for Simultaneous Machine Translation
  122. Dynamic fairness-aware recommendation through multi-agent social choice
  123. Customer Churn Prediction Model using Explainable Machine Learning
  124. Preference Transformer: Modeling Human Preferences using Transformers for RL
  125. Large Deviations for Accelerating Neural Networks Training
  126. Towards Activated Muscle Group Estimation in the Wild
  127. Open Problem: Optimal Best Arm Identification with Fixed Budget
  128. Attention-based Graph Convolution Fusing Latent Structures and Multiple Features for Graph Neural Networks
  129. Evolutionary Computation in Action: Feature Selection for Deep Embedding Spaces of Gigapixel Pathology Images
  130. Meta-information-aware Dual-path Transformer for Differential Diagnosis of Multi-type Pancreatic Lesions in Multi-phase CT
  131. ParaFormer: Parallel Attention Transformer for Efficient Feature Matching
  132. Spatial Layout Consistency for 3D Semantic Segmentation
  133. UniDexGrasp: Universal Robotic Dexterous Grasping via Learning Diverse Proposal Generation and Goal-Conditioned Policy
  134. Learning to Detect Slip through Tactile Estimation of the Contact Force Field and its Entropy
  135. Helpful, Misleading or Confusing: How Humans Perceive Fundamental Building Blocks of Artificial Intelligence Explanations
  136. QuickCent: a fast and frugal heuristic for harmonic centrality estimation on scale-free networks
  137. STUNT: Few-shot Tabular Learning with Self-generated Tasks from Unlabeled Tables
  138. Enhancing General Face Forgery Detection via Vision Transformer with Low-Rank Adaptation
  139. BiomedCLIP: a multimodal biomedical foundation model pretrained from fifteen million scientific image-text pairs
  140. Neuro-Modulated Hebbian Learning for Fully Test-Time Adaptation
  141. Parameter Sharing with Network Pruning for Scalable Multi-Agent Deep Reinforcement Learning
  142. Interactive Text Generation
  143. Transmission-Guided Bayesian Generative Model for Smoke Segmentation
  144. StoCFL: A Stochastically Clustered Federated Learning Framework for Non-IID Data with Dynamic Client Participation
  145. Predicting IPv4 Services Across All Ports
  146. MoSS: Monocular Shape Sensing for Continuum Robots
  147. Comparison of High-Dimensional Bayesian Optimization Algorithms on BBOB
  148. Photovoltaic Panel Defect Detection Based on Ghost Convolution with BottleneckCSP and Tiny Target Prediction Head Incorporating YOLOv5
  149. Towards Trustable Skin Cancer Diagnosis via Rewriting Model's Decision
  150. Variance-reduced Clipping for Non-convex Optimization
  151. X-Ray2EM: Uncertainty-Aware Cross-Modality Image Reconstruction from X-Ray to Electron Microscopy in Connectomics
  152. Geometric Visual Similarity Learning in 3D Medical Image Self-supervised Pre-training
  153. Bayesian Deep Learning for Affordance Segmentation in images