mlsanityData to 14 Oct 2026

Papers

New on arXiv

Mon 10 Oct 2022

206 papers

  1. Improving Retrieval Augmented Neural Machine Translation by Controlling Source and Fuzzy-Match InteractionsRetrieval-augmented generation → Generation and context integration
  2. FEAMOE: Fair, Explainable and Adaptive Mixture of ExpertsMixture-of-experts → MoE theory and gating functions
  3. f-DM: A Multi-stage Diffusion Model via Progressive Signal TransformationDiffusion models → Diffusion foundations and sampling
  4. What the DAAM: Interpreting Stable Diffusion Using Cross AttentionDiffusion models → Image generation, text-to-image and editing
  5. Sequential Neural Score Estimation: Likelihood-Free Inference with Conditional Score Based Diffusion ModelsDiffusion models → Diffusion foundations and sampling
  6. Knowledge Distillation Transfer Sets and their Impact on Downstream NLU TasksKnowledge distillation → Knowledge distillation for LLMs
  7. CLIP-Diffusion-LM: Apply Diffusion Model on Image CaptioningDiffusion models → Image generation, text-to-image and editing
  8. Bridging CLIP and StyleGAN through Latent Alignment for Image EditingMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  9. Distill the Image to Nowhere: Inversion Knowledge Distillation for Multimodal Machine TranslationKnowledge distillation → Multimodal distillation
  10. Asymmetric Temperature Scaling Makes Larger Networks Teach Well AgainKnowledge distillation → General knowledge distillation methods
  11. Montague semantics and modifier consistency measurement in neural language models
  12. Deep Reinforcement Learning Based Joint Downlink Beamforming and RIS Configuration in RIS-aided MU-MISO Systems Under Hardware Impairments and Imperfect CSI
  13. Region2Vec: Community Detection on Spatial Networks Using Graph Embedding with Node Attributes and Spatial Interactions
  14. Reducing Action Space: Reference-Model-Assisted Deep Reinforcement Learning for Inverter-based Volt-Var Control
  15. Denoising Masked AutoEncoders Help Robust Classification
  16. Towards an Efficient ML System: Unveiling a Trade-off between Task Accuracy and Engineering Efficiency in a Large-scale Car Sharing Platform
  17. Subject-specific quantitative susceptibility mapping using patch based deep image priors
  18. fAux: Testing Individual Fairness via Gradient Alignment
  19. Self-supervised Learning for Label-Efficient Sleep Stage Classification: A Comprehensive Evaluation
  20. Pose-Guided Graph Convolutional Networks for Skeleton-Based Action Recognition
  21. Exploring Efficient-tuning Methods in Self-supervised Speech Models
  22. DEPTWEET: A Typology for Social Media Texts to Detect Depression Severities
  23. On skip connections and normalisation layers in deep optimisation
  24. DeepPerform: An Efficient Approach for Performance Testing of Resource-Constrained Neural Networks
  25. Learning Explicit Credit Assignment for Cooperative Multi-Agent Reinforcement Learning via Polarization Policy Gradient
  26. Risk Automatic Prediction for Social Economy Companies using Camels
  27. Neurosymbolic Programming for Science
  28. Multi-CLS BERT: An Efficient Alternative to Traditional Ensembling
  29. Contrastive Video-Language Learning with Fine-grained Frame Sampling
  30. Fighting FIRe with FIRE: Assessing the Validity of Text-to-Video Retrieval Benchmarks
  31. Automated Audio Captioning via Fusion of Low- and High- Dimensional Features
  32. Not All Errors are Equal: Learning Text Generation Metrics using Stratified Error Synthesis
  33. Multilingual Representation Distillation with Contrastive Learning
  34. Unit Selection: Case Study and Comparison with A/B Test Heuristic
  35. Probabilities of Causation: Adequate Size of Experimental and Observational Samples
  36. Using Deep Learning to Improve Early Diagnosis of Pneumonia in Underdeveloped Countries
  37. The good, the bad and the ugly sides of data augmentation: An implicit spectral regularization perspective
  38. LidarNAS: Unifying and Searching Neural Architectures for 3D Point Clouds
  39. Optimality Guarantees for Particle Belief Approximation of POMDPs
  40. Exploring Adaptive MCTS with TD Learning in miniXCOM
  41. Fast Hierarchical Learning for Few-Shot Object Detection
  42. Energy-Efficient Deployment of Machine Learning Workloads on Neuromorphic Hardware
  43. Social Media Personal Event Notifier Using NLP and Machine Learning
  44. Graph2Vid: Flow graph to Video Grounding for Weakly-supervised Multi-Step Localization
  45. Sampling-based inference for large linear models, with application to linearised Laplace
  46. Continual Learning with Evolving Class Ontologies
  47. Extracting or Guessing? Improving Faithfulness of Event Temporal Relation Extraction
  48. On Designing Day Ahead and Same Day Ridership Level Prediction Models for City-Scale Transit Networks Using Noisy APC Data
  49. Simulating Coverage Path Planning with Roomba
  50. Loop Unrolled Shallow Equilibrium Regularizer (LUSER) -- A Memory-Efficient Inverse Problem Solver
  51. REV: Information-Theoretic Evaluation of Free-Text Rationales
  52. Label-free segmentation from cardiac ultrasound using self-supervised learning
  53. Domain-guided data augmentation for deep learning on medical imaging
  54. Function-space regularized R'enyi divergences
  55. Multi-step Planning for Automated Hyperparameter Optimization with OptFormer
  56. Generating Executable Action Plans with Environmentally-Aware Language Models
  57. Characterization of anomalous diffusion through convolutional transformers
  58. Mining Causality from Continuous-time Dynamics Models: An Application to Tsunami Forecasting
  59. A Hybrid Active-Passive Approach to Imbalanced Nonstationary Data Stream Classification
  60. Reaching Goals is Hard: Settling the Sample Complexity of the Stochastic Shortest Path
  61. Masked Autoencoders for Low dose CT denoising
  62. EarthNets: Empowering AI in Earth Observation
  63. Deep Insights of Learning based Micro Expression Recognition: A Perspective on Promises, Challenges and Research Needs
  64. An Action Is Worth Multiple Words: Handling Ambiguity in Action Recognition
  65. NeRF2Real: Sim2real Transfer of Vision-guided Bipedal Motion Skills using Neural Radiance Fields
  66. Meta-Principled Family of Hyperparameter Scaling Strategies
  67. Improving The Reconstruction Quality by Overfitted Decoder Bias in Neural Image Compression
  68. Turbo Training with Token Dropout
  69. EVA3D: Compositional 3D Human Generation from 2D Image Collections
  70. In-Hand Object Rotation via Rapid Motor Adaptation
  71. Revisiting adapters with adversarial training
  72. SCAM! Transferring humans between images with Semantic Cross Attention Modulation
  73. Layer Ensembles
  74. Translate First Reorder Later: Leveraging Monotonicity in Semantic Parsing
  75. CORE: A Retrieve-then-Edit Framework for Counterfactual Data Generation
  76. Certified Training: Small Boxes are All You Need
  77. SMiLE: Schema-augmented Multi-level Contrastive Learning for Knowledge Graph Link Prediction
  78. A copula-based boosting model for time-to-event prediction with dependent censoring
  79. Deep object detection for waterbird monitoring using aerial imagery
  80. PoGaIN: Poisson-Gaussian Image Noise Modeling from Paired Samples
  81. Tracking changes using Kullback-Leibler divergence for the continual learning
  82. Transformer-based Localization from Embodied Dialog with Large-scale Pre-training
  83. Second-order regression models exhibit progressive sharpening to the edge of stability
  84. NerfAcc: A General NeRF Acceleration Toolbox
  85. FS-DETR: Few-Shot DEtection TRansformer with prompting and without re-training
  86. Multi-Modal Fusion by Meta-Initialization
  87. Rieoptax: Riemannian Optimization in JAX
  88. Benchmarking Reinforcement Learning Techniques for Autonomous Navigation
  89. Visual Prompt Tuning for Test-time Domain Adaptation
  90. Hierarchical3D Adapters for Long Video-to-text Summarization
  91. Assessing Neural Referential Form Selectors on a Realistic Multilingual Dataset
  92. Data types as a more ergonomic frontend for Grammar-Guided Genetic Programming
  93. Long N-step Surrogate Stage Reward to Reduce Variances of Deep Reinforcement Learning in Complex Problems
  94. Efficient Learning of Locomotion Skills through the Discovery of Diverse Environmental Trajectory Generator Priors
  95. Do you pay for Privacy in Online learning?
  96. Ensemble Learning using Transformers and Convolutional Networks for Masked Face Recognition
  97. Truncated proposals for scalable and hassle-free simulation-based inference
  98. Bayesian Sparse Regression for Mixed Multi-Responses with Application to Runtime Metrics Prediction in Fog Manufacturing
  99. Towards a Theoretical Foundation of Policy Optimization for Learning Control Policies
  100. Efficient NTK using Dimensionality Reduction
All 206
  1. Generating image captions with external encyclopedic knowledge
  2. Using Whole Slide Image Representations from Self-Supervised Contrastive Learning for Melanoma Concordance Regression
  3. SimSCOOD: Systematic Analysis of Out-of-Distribution Generalization in Fine-tuned Source Code Models
  4. 4D Unsupervised Object Discovery
  5. LMQFormer: A Laplace-Prior-Guided Mask Query Transformer for Lightweight Snow Removal
  6. On the Importance of Calibration in Semi-supervised Learning
  7. Robustification of Multilingual Language Models to Real-world Noise in Crosslingual Zero-shot Settings with Robust Contrastive Pretraining
  8. CONSS: Contrastive Learning Approach for Semi-Supervised Seismic Facies Classification
  9. Hierarchical Learning in Euclidean Neural Networks
  10. On the Forward Invariance of Neural ODEs
  11. On the Performance of Gradient Tracking with Local Updates
  12. Metaphorical Paraphrase Generation: Feeding Metaphorical Language Models with Literal Texts
  13. Improving Visual-Semantic Embeddings by Learning Semantically-Enhanced Hard Negatives for Cross-modal Information Retrieval
  14. Low-power multi-mode fiber projector overcomes shallow neural networks classifiers
  15. A dynamic programming algorithm for span-based nested named-entity recognition in O(n^2)
  16. Edge Device Deployment of Multi-Tasking Network for Self-Driving Operations
  17. PyHopper -- Hyperparameter optimization
  18. Knowledge Prompts: Injecting World Knowledge into Language Models through Soft Prompts
  19. Experiential Explanations for Reinforcement Learning
  20. Semantics-Consistent Cross-domain Summarization via Optimal Transport Alignment
  21. Uncertainty Quantification with Pre-trained Language Models: A Large-Scale Empirical Analysis
  22. Empowering the Fact-checkers! Automatic Identification of Claim Spans on Twitter
  23. GTAV-NightRain: Photometric Realistic Large-scale Dataset for Night-time Rain Streak Removal
  24. Readability Controllable Biomedical Document Summarization
  25. FedBA: Non-IID Federated Learning Framework in UAV Networks
  26. Language Models Are Poor Learners of Directional Inference
  27. Language Prior Is Not the Only Shortcut: A Benchmark for Shortcut Learning in VQA
  28. Learning "O" Helps for Learning More: Handling the Concealed Entity Problem for Class-incremental NER
  29. A Survey of Methods for Addressing Class Imbalance in Deep-Learning Based Natural Language Processing
  30. Exploiting map information for self-supervised learning in motion forecasting
  31. TCDM: Transformational Complexity Based Distortion Metric for Perceptual Point Cloud Quality Assessment
  32. A CNN Based Approach for the Point-Light Photometric Stereo Problem
  33. Rejecting noise in Baikal-GVD data with neural networks
  34. Association Graph Learning for Multi-Task Classification with Category Shifts
  35. FaDIn: Fast Discretized Inference for Hawkes Processes with General Parametric Kernels
  36. Investigation of inverse design of multilayer thin-films with conditional invertible Neural Networks
  37. FLamby: Datasets and Benchmarks for Cross-Silo Federated Learning in Realistic Healthcare Settings
  38. YFACC: A Yor`ub'a speech-image dataset for cross-lingual keyword localisation through visual grounding
  39. Universal Adversarial Perturbations: Efficiency on a small image dataset
  40. The Small Solution Hypothesis for MAPF on Strongly Connected Directed Graphs Is True
  41. ParaDime: A Framework for Parametric Dimensionality Reduction
  42. Is your noise correction noisy? PLS: Robustness to label noise with two stage detection
  43. ARUBA: An Architecture-Agnostic Balanced Loss for Aerial Object Detection
  44. HumSet: Dataset of Multilingual Information Extraction and Classification for Humanitarian Crisis Response
  45. Floorplan-Aware Camera Poses Refinement
  46. The Eyecandies Dataset for Unsupervised Multimodal Anomaly Detection and Localization
  47. BoundaryFace: A mining framework with noise label self-correction for Face Recognition
  48. Towards Robust Visual Question Answering: Making the Most of Biased Samples via Contrastive Learning
  49. Using Detection, Tracking and Prediction in Visual SLAM to Achieve Real-time Semantic Mapping of Dynamic Scenarios
  50. A Comprehensive Survey of Data Augmentation in Visual Reinforcement Learning
  51. Visually Similar Products Retrieval for Shopsy
  52. Everything is Varied: The Surprising Impact of Individual Variation on ML Robustness in Medicine
  53. Comparing the carbon costs and benefits of low-resource solar nowcasting
  54. SiNeRF: Sinusoidal Neural Radiance Fields for Joint Pose Estimation and Scene Reconstruction
  55. Automatic Evaluation and Analysis of Idioms in Neural Machine Translation
  56. Sparse Semantic Map-Based Monocular Localization in Traffic Scenes Using Learned 2D-3D Point-Line Correspondences
  57. DALE: Differential Accumulated Local Effects for efficient and accurate global explanations
  58. Towards an efficient and risk aware strategy for guiding farmers in identifying best crop management
  59. Belief functions on ordered frames of discernment
  60. Local Interpretable Model Agnostic Shap Explanations for machine learning models
  61. Do Children Texts Hold The Key To Commonsense Knowledge?
  62. A policy gradient approach for Finite Horizon Constrained Markov Decision Processes
  63. SelfMix: Robust Learning Against Textual Label Noise with Self-Mixup Training
  64. Margin-Based Few-Shot Class-Incremental Learning with Class-Level Overfitting Mitigation
  65. HORIZON: High-Resolution Semantically Controlled Panorama Synthesis
  66. Continual task learning in natural and artificial agents
  67. Self-Supervised 3D Human Pose Estimation in Static Video Via Neural Rendering
  68. Multi-Modal Fusion Transformer for Visual Question Answering in Remote Sensing
  69. Scale Equivariant U-Net
  70. A Survey on Heterogeneous Federated Learning
  71. Learning Robust Representations for Continual Relation Extraction via Adversarial Class Augmentation
  72. Unified Detoxifying and Debiasing in Language Generation via Inference-time Adaptive Optimization
  73. A survey of Identification and mitigation of Machine Learning algorithmic biases in Image Analysis
  74. Semantic Framework based Query Generation for Temporal Question Answering over Knowledge Graphs
  75. A Memory Transformer Network for Incremental Learning
  76. HiCo: Hierarchical Contrastive Learning for Ultrasound Video Model Pretraining
  77. Using Both Demonstrations and Language Instructions to Efficiently Learn Robotic Tasks
  78. Leveraging Key Information Modeling to Improve Less-Data Constrained News Headline Generation via Duality Fine-Tuning
  79. Uncertainty-aware LiDAR Panoptic Segmentation
  80. Actor-Critic or Critic-Actor? A Tale of Two Time Scales
  81. Identifying patterns of main causes of death in the young EU population
  82. Investigating the Failure Modes of the AUC metric and Exploring Alternatives for Evaluating Systems in Safety Critical Applications
  83. OGC: Unsupervised 3D Object Segmentation from Rigid Dynamics of Point Clouds
  84. XPrompt: Exploring the Extreme of Prompt Tuning
  85. Self-move and Other-move: Quantum Categorical Foundations of Japanese
  86. CrowdChecked: Detecting Previously Fact-Checked Claims in Social Media
  87. Don't Copy the Teacher: Data and Model Challenges in Embodied Dialogue
  88. DPAR: Decoupled Graph Neural Networks with Node-Level Differential Privacy
  89. Creating a Dynamic Quadrupedal Robotic Goalkeeper with Reinforcement Learning
  90. Spectral Geometric Verification: Re-Ranking Point Cloud Retrieval for Metric Localization
  91. Scientific Machine Learning for Modeling and Simulating Complex Fluids
  92. DeepHS-HDRVideo: Deep High Speed High Dynamic Range Video Reconstruction
  93. A Simple Baseline that Questions the Use of Pretrained-Models in Continual Learning
  94. Self-explaining Hierarchical Model for Intraoperative Time Series
  95. Predicting Blossom Date of Cherry Tree With Support Vector Machine and Recurrent Neural Network
  96. Modeling and Mining Multi-Aspect Graphs With Scalable Streaming Tensor Decomposition
  97. Contrastive Bayesian Analysis for Deep Metric Learning
  98. Focus Plus: Detect Learner's Distraction by Web Camera in Distance Teaching
  99. Deep Learning for Logo Detection: A Survey
  100. Scaling Up Probabilistic Circuits by Latent Variable Distillation
  101. LAPFormer: A Light and Accurate Polyp Segmentation Transformer
  102. DeepMed: Semiparametric Causal Mediation Analysis with Debiased Deep Learning
  103. Semi-supervised Semantic Segmentation with Prototype-based Consistency Regularization
  104. Parameter-Efficient Tuning with Special Token Adaptation
  105. Unsupervised Domain Adaptive Fundus Image Segmentation with Few Labeled Source Data
  106. DCVQE: A Hierarchical Transformer for Video Quality Assessment