mlsanityData to 14 Oct 2026

Papers

New on arXiv

Thu 16 Jun 2022

221 papers

  1. Backdoor Attacks on Vision TransformersLLM safety and security → Backdoor and data poisoning attacks
  2. DialogueScript: Using Dialogue Agents to Produce a ScriptLLM agents and tool use → Social simulation and multi-agent debate
  3. Maximum Likelihood Training for Score-Based Diffusion ODEs by High-Order Denoising Score MatchingDiffusion models → Diffusion foundations and sampling
  4. Multi scale Feature Extraction and Fusion for Online Knowledge DistillationKnowledge distillation → General knowledge distillation methods
  5. Level 2 Autonomous Driving on a Single Device: Diving into the Devils of OpenpilotEnd-to-end autonomous driving → End-to-end system architecture
  6. Trajectory-guided Control Prediction for End-to-end Autonomous Driving: A Simple yet Strong BaselineEnd-to-end autonomous driving → End-to-end system architecture
  7. Self-Generated In-Context Learning: Leveraging Auto-regressive Language Models as a Demonstration GeneratorSynthetic data and self-improvement for LLMs → Self-training for few-shot NLP
  8. Double Check Your State Before Trusting It: Confidence-Aware Bidirectional Offline Model-Based ImaginationOffline RL and imitation learning from data → Offline RL algorithms
  9. Planning Courses for Student Success at the American College of Greece
  10. Is Power-Seeking AI an Existential Risk?
  11. Multi-Frequency Joint Community Detection and Phase Synchronization
  12. Identifying Electrocardiogram Abnormalities Using a Handcrafted-Rule-Enhanced Neural Network
  13. Simultaneous Bone and Shadow Segmentation Network using Task Correspondence Consistency
  14. Reinforcement Learning for Economic Policy: A New Frontier?
  15. Controllable Image Enhancement
  16. High-Speed Accurate Robot Control using Learned Forward Kinodynamics and Non-linear Least Squares Optimization
  17. Interpretable AMR-Based Question Decomposition for Multi-hop Question Answering
  18. Orientation-guided Graph Convolutional Network for Bone Surface Segmentation
  19. Classification of datasets with imputed missing values: does imputation quality matter?
  20. Zero-Shot AutoML with Pretrained Models
  21. XLCoST: A Benchmark Dataset for Cross-lingual Code Intelligence
  22. A Robust Stacking Framework for Training Deep Graph Models with Multifaceted Node Features
  23. Belief-Desire-Intention (BDI) Multi-agent System for Cloud Marketplace Negotiation
  24. Variational Estimators of the Degree-corrected Latent Block Model for Bipartite Networks
  25. PRANC: Pseudo RAndom Networks for Compacting deep models
  26. Recursive Neural Programs: Variational Learning of Image Grammars and Part-Whole Hierarchies
  27. TUSK: Task-Agnostic Unsupervised Keypoints
  28. Local overlap reduction procedure for dynamic ensemble selection
  29. Quantifying Feature Contributions to Overall Disparity Using Information Theory
  30. GOOD: A Graph Out-of-Distribution Benchmark
  31. I Know What You Trained Last Summer: A Survey on Stealing Machine Learning Models and Defences
  32. Active Fairness Auditing
  33. Empirical Bayesian Approaches for Robust Constraint-based Causal Discovery under Insufficient Data
  34. Methods for Estimating and Improving Robustness of Language Models
  35. Enriching Abusive Language Detection with Community Context
  36. A Look at Value-Based Decision-Time vs. Background Planning Methods Across Different Settings
  37. GAAMA 2.0: An Integrated System that Answers Boolean and Extractive Questions
  38. OpenSRH: optimizing brain tumor surgery using intraoperative stimulated Raman histology
  39. The Case for a Wholistic Serverless Programming Paradigm and Full Stack Automation for AI and Beyond -- The Philosophy of Jaseci and Jac
  40. Scalable Temporal Localization of Sensitive Activities in Movies and TV Episodes
  41. EyeNeRF: A Hybrid Representation for Photorealistic Synthesis, Animation and Relighting of Human Eyes
  42. SATBench: Benchmarking the speed-accuracy tradeoff in object recognition by humans and dynamic neural networks
  43. IRISformer: Dense Vision Transformers for Single-Image Inverse Rendering in Indoor Scenes
  44. Real-time motion amplification on mobile devices
  45. Generalised Bayesian Inference for Discrete Intractable Likelihood
  46. CS-UM6P at SemEval-2022 Task 6: Transformer-based Models for Intended Sarcasm Detection in English and Arabic
  47. Deep Multi-Task Models for Misogyny Identification and Categorization on Arabic Social Media
  48. Predicting Hate Intensity of Twitter Conversation Threads
  49. Going Deeper than Tracking: a Survey of Computer-Vision Based Recognition of Animal Pain and Affective States
  50. Learning to Teach Fairness-aware Deep Multi-task Learning
  51. Learning Generic Lung Ultrasound Biomarkers for Decoupling Feature Extraction from Downstream Tasks
  52. Powershap: A Power-full Shapley Feature Selection Method
  53. Unbiased 4D: Monocular 4D Reconstruction with a Neural Deformation Model
  54. SHIFT: A Synthetic Driving Dataset for Continuous Multi-Task Domain Adaptation
  55. Scalable First-Order Bayesian Optimization via Structured Automatic Differentiation
  56. Virtual Correspondence: Humans as a Cue for Extreme-View Geometry
  57. Interaction-Grounded Learning with Action-inclusive Feedback
  58. Benchmarking Heterogeneous Treatment Effect Models through the Lens of Interpretability
  59. Unified Fourier-based Kernel and Nonlinearity Design for Equivariant Networks on Homogeneous Spaces
  60. Controllable 3D Face Synthesis with Conditional Generative Occupancy Fields
  61. MixGen: A New Multi-Modal Data Augmentation
  62. Spatially-Adaptive Multilayer Selection for GAN Inversion and Editing
  63. OmniMAE: Single Model Masked Pretraining on Images and Videos
  64. FWD: Real-time Novel View Synthesis with Forward Warping and Depth
  65. Towards Understanding How Machines Can Learn Causal Overhypotheses
  66. Know your audience: specializing grounded language models with listener subtraction
  67. Beyond Supervised vs. Unsupervised: Representative Benchmarking and Analysis of Image Representation Learning
  68. Real-World Single Image Super-Resolution Under Rainy Condition
  69. Realistic One-shot Mesh-based Head Avatars
  70. iBoot: Image-bootstrapped Self-Supervised Video Representation Learning
  71. Constrained Submodular Optimization for Vaccine Design
  72. BYOL-Explore: Exploration by Bootstrapped Prediction
  73. Compressed-VFL: Communication-Efficient Learning with Vertically Partitioned Data
  74. Characteristics of Harmful Text: Towards Rigorous Benchmarking of Language Models
  75. Equivariant Descriptor Fields: SE(3)-Equivariant Energy-Based Models for End-to-End Visual Robotic Manipulation Learning
  76. Paraformer: Fast and Accurate Parallel Transformer for Non-autoregressive End-to-End Speech Recognition
  77. Boosting the Adversarial Transferability of Surrogate Models with Dark Knowledge
  78. SoundSpaces 2.0: A Simulation Platform for Visual-Acoustic Learning
  79. Continuous-Time Modeling of Counterfactual Outcomes Using Neural Controlled Differential Equations
  80. Pythae: Unifying Generative Autoencoders in Python -- A Benchmarking Use Case
  81. Deepfake histological images for enhancing digital pathology
  82. Sharper Convergence Guarantees for Asynchronous SGD for Distributed and Federated Learning
  83. Adversarial Patch Attacks and Defences in Vision-Based Tasks: A Survey
  84. On Scaled Methods for Saddle Point Problems
  85. Video Capsule Endoscopy Classification using Focal Modulation Guided Convolutional Neural Network
  86. A Language Model With Million Context Length For Raw Audio
  87. Switchable Representation Learning Framework with Self-compatibility
  88. Balancing Cost and Quality: An Exploration of Human-in-the-loop Frameworks for Automated Short Answer Scoring
  89. Definition drives design: Disability models and mechanisms of bias in AI technologies
  90. A machine-generated catalogue of Charon's craters and implications for the Kuiper belt
  91. Rank the triplets: A ranking-based multiple instance learning framework for detecting HPV infection in head and neck cancers using routine H&E images
  92. Concentration of Data Encoding in Parameterized Quantum Circuits
  93. Longitudinal detection of new MS lesions using Deep Learning
  94. Learning with little mixing
  95. 'John ate 5 apples' != 'John ate some apples': Self-Supervised Paraphrase Quality Detection for Algebraic Word Problems
  96. ProGNNosis: A Data-driven Model to Predict GNN Computation Time Using Graph Metrics
  97. Gradient Descent for Low-Rank Functions
  98. Gradient-Based Adversarial and Out-of-Distribution Detection
  99. On the Surprising Behaviour of node2vec
  100. Catastrophic overfitting can be induced with discriminative non-robust features
All 221
  1. Noisy Learning for Neural ODEs Acts as a Robustness Locus Widening
  2. Simple and Efficient Architectures for Semantic Segmentation
  3. Deep Learning Architecture for Automatic Essay Scoring
  4. Open-Set Recognition with Gradient-Based Representations
  5. Delving into the Scale Variance Problem in Object Detection
  6. All the World's a (Hyper)Graph: A Data Drama
  7. Adapting Self-Supervised Vision Transformers by Probing Attention-Conditioned Masking Consistency
  8. Functional Output Regression with Infimal Convolution: Exploring the Huber and ε-insensitive Losses
  9. HaGRID - HAnd Gesture Recognition Image Dataset
  10. A Closer Look at Smoothness in Domain Adversarial Training
  11. Selective Multi-Scale Learning for Object Detection
  12. Inherent Inconsistencies of Feature Importance
  13. Learning Physics between Digital Twins with Low-Fidelity Models and Physics-Informed Gaussian Processes
  14. MAGIC: Microlensing Analysis Guided by Intelligent Computation
  15. Online Segmentation of LiDAR Sequences: Dataset and Algorithm
  16. Asymptotic Soft Cluster Pruning for Deep Neural Networks
  17. UAVs Beneath the Surface: Cooperative Autonomy for Subterranean Search and Rescue in DARPA SubT
  18. Nucleus Segmentation and Analysis in Breast Cancer with the MIScnn Framework
  19. ResNorm: Tackling Long-tailed Degree Distribution Issue in Graph Neural Networks via Normalization
  20. User Engagement in Mobile Health Applications
  21. Not All Lotteries Are Made Equal
  22. RefCrowd: Grounding the Target in Crowd with Referring Expressions
  23. K-Radar: 4D Radar Object Detection for Autonomous Driving in Various Weather Conditions
  24. Adversarial Privacy Protection on Speech Enhancement
  25. Long Range Graph Benchmark
  26. Volumetric Supervised Contrastive Learning for Seismic Semantic Segmentation
  27. Zero-Shot Video Question Answering via Frozen Bidirectional Language Models
  28. Fault-Tolerant Collaborative Inference through the Edge-PRUNE Framework
  29. Self-Adaptive Label Augmentation for Semi-supervised Few-shot Classification
  30. A Contextual Combinatorial Semi-Bandit Approach to Network Bottleneck Identification
  31. Channel Importance Matters in Few-Shot Image Classification
  32. Using adversarial images to improve outcomes of federated learning for non-IID data
  33. Learning to Infer Structures of Network Games
  34. On Private Online Convex Optimization: Optimal Algorithms in ℓp-Geometry and High Dimensional Contextual Bandits
  35. Closed-Form Diffeomorphic Transformations for Time Series Alignment
  36. A Simple Baseline for Adversarial Domain Adaptation-based Unsupervised Flood Forecasting
  37. Towards Diverse Evaluation of Class Incremental Learning: A Representation Learning Perspective
  38. DeepJSCC-Q: Constellation Constrained Deep Joint Source-Channel Coding
  39. Deep Neural Imputation: A Framework for Recovering Incomplete Brain Recordings
  40. Applications of Machine Learning to the Identification of Anomalous ER Claims
  41. On the well-spread property and its relation to linear regression
  42. Unsupervised Space Partitioning for Nearest Neighbor Search
  43. Reinforcement Learning-enhanced Shared-account Cross-domain Sequential Recommendation
  44. An Improved Normed-Deformable Convolution for Crowd Counting
  45. CARLANE: A Lane Detection Benchmark for Unsupervised Domain Adaptation from Simulation to multiple Real-World Domains
  46. TransDrift: Modeling Word-Embedding Drift using Transformer
  47. A Machine Learning-based Digital Twin for Electric Vehicle Battery Modeling
  48. U-PET: MRI-based Dementia Detection with Joint Generation of Synthetic FDG-PET Images
  49. Neural Scene Representation for Locomotion on Structured Terrain
  50. Learning Effect of Lay People in Gesture-Based Locomotion in Virtual Reality
  51. Large-width asymptotics for ReLU neural networks with α-Stable initializations
  52. Towards Robust Ranker for Text Retrieval
  53. Active Nearest Neighbor Regression Through Delaunay Refinement
  54. Nonwords Pronunciation Classification in Language Development Tests for Preschool Children
  55. Generalized Leverage Scores: Geometric Interpretation and Applications
  56. JU_NLP at HinglishEval: Quality Evaluation of the Low-Resource Code-Mixed Hinglish Text
  57. Time Interval-enhanced Graph Neural Network for Shared-account Cross-domain Sequential Recommendation
  58. Automated analysis of continuum fields from atomistic simulations using statistical machine learning
  59. An Open-Domain QA System for e-Governance
  60. Acoustic Modeling for End-to-End Empathetic Dialogue Speech Synthesis Using Linguistic and Prosodic Contexts of Dialogue History
  61. DIALOG-22 RuATD Generated Text Detection
  62. DeepFormableTag: End-to-end Generation and Recognition of Deformable Fiducial Markers
  63. AMOS: A Large-Scale Abdominal Multi-Organ Benchmark for Versatile Medical Image Segmentation
  64. Partial Identifiability for Nonnegative Matrix Factorization
  65. Exploiting Global Semantic Similarities in Knowledge Graphs by Relational Prototype Entities
  66. Multi-View Imputation and Cross-Attention Network Based on Incomplete Longitudinal and Multimodal Data for Conversion Prediction of Mild Cognitive Impairment
  67. Backbones-Review: Feature Extraction Networks for Deep Learning and Deep Reinforcement Learning Approaches
  68. On Error and Compression Rates for Prototype Rules
  69. Hardness prediction of age-hardening aluminum alloy based on ensemble learning
  70. MoDi: Unconditional Motion Synthesis from Diverse Data
  71. Balancing Discriminability and Transferability for Source-Free Domain Adaptation
  72. DCASE 2022: Comparative Analysis Of CNNs For Acoustic Scene Classification Under Low-Complexity Considerations
  73. Evaluating Self-Supervised Learning for Molecular Graph Embeddings
  74. When a RF Beats a CNN and GRU, Together -- A Comparison of Deep Learning and Classical Machine Learning Approaches for Encrypted Malware Traffic Classification
  75. The convergent Indian buffet process
  76. Differentially Private Multi-Party Data Release for Linear Regression
  77. Continual Learning with Guarantees via Weight Interval Constraints
  78. Joint Class-Affinity Loss Correction for Robust Medical Image Segmentation with Noisy Labels
  79. Patch-level Representation Learning for Self-supervised Vision Transformers
  80. PreCogIIITH at HinglishEval : Leveraging Code-Mixing Metrics & Language Model Embeddings To Estimate Code-Mix Quality
  81. Image Captioning based on Feature Refinement and Reflective Decoding
  82. Multi-scale Cooperative Multimodal Transformers for Multimodal Sentiment Analysis in Videos
  83. Research Topic Flows in Co-Authorship Networks
  84. Personalized Federated Learning via Variational Bayesian Inference
  85. Cyclocopula Technique to Study the Relationship Between Two Cyclostationary Time Series with Fractional Brownian Motion Errors
  86. BlindFL: Vertical Federated Machine Learning without Peeking into Your Data
  87. DreamNet: A Deep Riemannian Network based on SPD Manifold Learning for Visual Classification
  88. Towards Better Understanding with Uniformity and Explicit Regularization of Embeddings in Embedding-based Neural Topic Models
  89. Simple-BEV: What Really Matters for Multi-Sensor BEV Perception?
  90. Automatic Prosody Annotation with Pre-Trained Text-Speech Model
  91. Analysis and Extensions of Adversarial Training for Video Classification
  92. Forming Effective Human-AI Teams: Building Machine Learning Models that Complement the Capabilities of Multiple Experts
  93. Distributed Online Private Learning of Convex Nondecomposable Objectives
  94. When Rigidity Hurts: Soft Consistency Regularization for Probabilistic Hierarchical Time Series Forecasting
  95. BANet: Motion Forecasting with Boundary Aware Network
  96. Lifelong Wandering: A realistic few-shot online continual learning setting
  97. Challenges and Opportunities in Deep Reinforcement Learning with Graph Neural Networks: A Comprehensive review of Algorithms and Applications
  98. PInKS: Preconditioned Commonsense Inference with Minimal Supervision
  99. "Understanding Robustness Lottery": A Geometric Visual Comparative Analysis of Neural Network Pruning Approaches
  100. Barrier Certified Safety Learning Control: When Sum-of-Square Programming Meets Reinforcement Learning
  101. Double Sampling Randomized Smoothing
  102. Introducing the Huber mechanism for differentially private low-rank matrix completion
  103. Simultaneously Learning Stochastic and Adversarial Bandits with General Graph Feedback
  104. Explainable Models via Compression of Tree Ensembles
  105. On Privacy and Personalization in Cross-Silo Federated Learning
  106. Multimodal Dialogue State Tracking
  107. NCAGC: A Neighborhood Contrast Framework for Attributed Graph Clustering
  108. PeQuENet: Perceptual Quality Enhancement of Compressed Video with Adaptation- and Attention-based Network
  109. Max-Margin Works while Large Margin Fails: Generalization without Uniform Convergence
  110. Generalization Bounds for Data-Driven Numerical Linear Algebra
  111. Combinatorial Pure Exploration of Causal Bandits
  112. Accelerating Inference and Language Model Fusion of Recurrent Neural Network Transducers via End-to-End 4-bit Quantization
  113. Domain Generalization via Selective Consistency Regularization for Time Series Classification
  114. Optimization-Derived Learning with Essential Convergence Analysis of Training and Hyper-training
  115. How to talk so AI will learn: Instructions, descriptions, and autonomy
  116. Let Invariant Rationale Discovery Inspire Graph Contrastive Learning
  117. Unifying Framework for Optimizations in non-boolean Formalisms
  118. Text normalization for low-resource languages: the case of Ligurian
  119. EPG2S: Speech Generation and Speech Enhancement based on Electropalatography and Audio Signals using Multimodal Learning
  120. The Scattering Transform Network with Generalized Morse Wavelets and Its Application to Music Genre Classification
  121. Performance analysis of coreset selection for quantum implementation of K-Means clustering algorithm