mlsanityData to 14 Oct 2026

Papers

New on arXiv

Fri 10 Nov 2023

188 papers

  1. How to Bridge the Gap between Modalities: Survey on Multimodal Large Language ModelMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  2. Follow-Up Differential Descriptions: Language Models Resolve Ambiguities for Image ClassificationMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  3. Knowledge Graphs are not Created Equal: Exploring the Properties and Structure of Real KGsLLM reasoning → Knowledge- and tool-augmented reasoning
  4. Towards A Unified Neural Architecture for Visual Recognition and ReasoningLLM reasoning → Multimodal reasoning
  5. Distilling Large Language Models using Skill-Occupation Graph Context for HR-Related TasksKnowledge distillation → Knowledge distillation for LLMs
  6. Relation Extraction in underexplored biomedical domains: A diversity-optimised sampling and synthetic data generation approachSynthetic data and self-improvement for LLMs → Medical synthetic data and agents
  7. Smart Agent-Based Modeling: On the Use of Large Language Models in Computer SimulationsLLM agents and tool use → General LLM agent frameworks and benchmarks
  8. Post-training Quantization for Text-to-Image Diffusion Models with Progressive Calibration and Activation RelaxingDiffusion models → Diffusion foundations and sampling
  9. Summon a Demon and Bind it: A Grounded Theory of LLM Red TeamingLLM safety and security → Prompt injection and agent security
  10. Diffusion Models for Earth Observation Use-cases: from cloud removal to urban change detectionDiffusion models → Inverse problems and image restoration
  11. Instant3D: Fast Text-to-3D with Sparse-View Generation and Large Reconstruction ModelDiffusion models → 3D, point cloud and scene generation
  12. Language Models can be Logical SolversLLM reasoning → Reasoning benchmarks and evaluation
  13. Turbulence Scaling from Deep Learning Diffusion Generative ModelsDiffusion models → Flow matching, time series and science
  14. Enhancing Rock Image Segmentation in Digital Rock Physics: A Fusion of Generative AI and State-of-the-Art Neural NetworksDiffusion models → Flow matching, time series and science
  15. Practical Membership Inference Attacks against Fine-tuned Large Language Models via Self-prompt CalibrationLLM safety and security → Membership inference attacks
  16. Learning Contrastive Self-Distillation for Ultra-Fine-Grained Visual Categorization Targeting Limited SamplesKnowledge distillation → General knowledge distillation methods
  17. ChiMed-GPT: A Chinese Medical Large Language Model with Full Training Regime and Better Alignment to Human PreferencesLLM alignment / RLHF / preference optimisation → Medical LLM alignment
  18. JARVIS-1: Open-World Multi-task Agents with Memory-Augmented Multimodal Language ModelsLLM agents and tool use → Reinforcement learning for LLM agents
  19. Quantized Distillation: Optimizing Driver Activity Recognition Models for Resource-Constrained EnvironmentsKnowledge distillation → Detection and dense prediction distillation
  20. Chain of Thought with Explicit Evidence Reasoning for Few-shot Relation ExtractionLLM reasoning → Prompting and chain-of-thought reasoning
  21. Establishing Performance Baselines in Fine-Tuning, Retrieval-Augmented Generation and Soft-Prompting for Non-Specialist LLM UsersRetrieval-augmented generation → RAG pipeline design and evaluation
  22. Semantic Map Guided Synthesis of Wireless Capsule Endoscopy Images using Diffusion ModelsDiffusion models → Medical imaging and segmentation
  23. Watermarking Vision-Language Pre-trained Models for Multi-modal Embedding as a ServiceMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness +1
  24. Diffusion Shape Prior for Wrinkle-Accurate Cloth RegistrationDiffusion models → 3D, point cloud and scene generation
  25. Honest Score Client Selection Scheme: Preventing Federated Learning Label Flipping Attacks in Non-IID ScenariosLLM safety and security → Federated unlearning and poisoning
  26. Let's Reinforce Step by StepLLM alignment / RLHF / preference optimisation → Process reward models for reasoning
  27. Improved Pothole Detection Using YOLOv7 and ESRGAN
  28. Automatic extraction and 3D reconstruction of split wire from point cloud data based on improved DPC algorithm
  29. CloudEval-YAML: A Practical Benchmark for Cloud Configuration Generation
  30. 5G Positioning Advancements with AI/ML
  31. Pioneering EEG Motor Imagery Classification Through Counterfactual Analysis
  32. A Distributed Inference System for Detecting Task-wise Single Trial Event-Related Potential in Stream of Satellite Images
  33. Decoding EEG-based Workload Levels Using Spatio-temporal Features Under Flight Environment
  34. Holistic Evaluation of GPT-4V for Biomedical Imaging
  35. IODeep: an IOD for the introduction of deep learning in the DICOM standard
  36. ChatGPT Exhibits Gender and Racial Biases in Acute Coronary Syndrome Management
  37. Transdisciplinary AI Education: The Confluence of Curricular and Community Needs in the Instruction of Artificial Intelligence
  38. ChatGPT as Co-Advisor in Scientific Initiation: Action Research with Project-Based Learning in Elementary Education
  39. Towards a Feminist Metaethics of AI
  40. Ontology Learning Using Formal Concept Analysis and WordNet
  41. Business Policy Experiments using Fractional Factorial Designs: Consumer Retention on DoorDash
  42. Earnings Prediction Using Recurrent Neural Networks
  43. k-Parameter Approach for False In-Season Anomaly Suppression in Daily Time Series Anomaly Detection
  44. Surrogate Neural Networks to Estimate Parametric Sensitivity of Ocean Models
  45. TransformCode: A Contrastive Learning Framework for Code Embedding via Subtree Transformation
  46. Testing LLMs on Code Generation with Varying Levels of Prompt Specificity
  47. Multi-Label Topic Model for Financial Textual Data
  48. Enhancing Actuarial Non-Life Pricing Models via Transformers
  49. Graph GOSPA metric: a metric to measure the discrepancy between graphs of different sizes
  50. A Diagnosis and Treatment of Liver Diseases: Integrating Batch Processing, Rule-Based Event Detection and Explainable Artificial Intelligence
  51. A Trichotomy for Transductive Online Learning
  52. ChatGPT Prompting Cannot Estimate Predictive Uncertainty in High-Resource Languages
  53. Transferability Bound Theory: Exploring Relationship between Adversarial Transferability and Flatness
  54. Resolving uncertainty on the fly: Modeling adaptive driving behavior as active inference
  55. Forte: An Interactive Visual Analytic Tool for Trust-Augmented Net Load Forecasting
  56. Online multiple testing with e-values
  57. Analyzing Modular Approaches for Visual Question Decomposition
  58. Autoregressive Language Models For Estimating the Entropy of Epic EHR Audit Logs
  59. EviPrompt: A Training-Free Evidential Prompt Generation Method for Segment Anything Model in Medical Images
  60. A comprehensive analysis of concept drift locality in data streams
  61. A statistical perspective on algorithm unrolling models for inverse problems
  62. A design of Convolutional Neural Network model for the Diagnosis of the COVID-19
  63. ChatGPT in the context of precision agriculture data analytics
  64. Transfer Learning for Structured Pruning under Limited Task Data
  65. Theory and implementation of inelastic Constitutive Artificial Neural Networks
  66. DeMuX: Data-efficient Multilingual Learning
  67. Heaps' Law in GPT-Neo Large Language Model Emulated Corpora
  68. Image Classification using Combination of Topological Features and Neural Networks
  69. Higher-Order Newton Methods with Polynomial Work per Iteration
  70. Blockchain-Enabled Federated Learning Approach for Vehicular Networks
  71. The AeroSonicDB (YPAD-0523) Dataset for Acoustic Detection and Classification of Aircraft
  72. Word Definitions from Large Language Models
  73. CALLOC: Curriculum Adversarial Learning for Secure and Robust Indoor Localization
  74. Compact Matrix Quantum Group Equivariant Neural Networks
  75. Schema Graph-Guided Prompt for Multi-Domain Dialogue State Tracking
  76. A Survey of AI Text-to-Image and AI Text-to-Video Generators
  77. Reviewing Developments of Graph Convolutional Network Techniques for Recommendation Systems
  78. Can Machine Learning Uncover Insights into Vehicle Travel Demand from Our Built Environment?
  79. Knowledge-Augmented Large Language Models for Personalized Contextual Query Suggestion
  80. Parameter-Efficient Orthogonal Finetuning via Butterfly Factorization
  81. Florence-2: Advancing a Unified Representation for a Variety of Vision Tasks
  82. Argumentation Element Annotation Modeling using XLNet
  83. EVORA: Deep Evidential Traversability Learning for Risk-Aware Off-Road Autonomy
  84. Data Contamination Quiz: A Tool to Detect and Estimate Contamination in Large Language Models
  85. Learning Human Action Recognition Representations Without Real Humans
  86. Learning material synthesis-process-structure-property relationship by data fusion: Bayesian Coregionalization N-Dimensional Piecewise Function Learning
  87. Does Differential Privacy Prevent Backdoor Attacks in Practice?
  88. Harnessing Synthetic Datasets: The Role of Shape Bias in Deep Neural Network Generalization
  89. A Comparison of Lexicon-Based and ML-Based Sentiment Analysis: Are There Outlier Words?
  90. Semantic-aware Video Representation for Few-shot Action Recognition
  91. MultiIoT: Benchmarking Machine Learning for the Internet of Things
  92. Differentiable VQ-VAE's for Robust White Matter Streamline Encodings
  93. ASSIST: Interactive Scene Nodes for Scalable and Realistic Indoor Simulation
  94. Optimal Cooperative Multiplayer Learning Bandits with Noisy Rewards and No Communication
  95. BanglaBait: Semi-Supervised Adversarial Approach for Clickbait Detection on Bangla Clickbait Dataset
  96. Greedy PIG: Adaptive Integrated Gradients
  97. FourierGNN: Rethinking Multivariate Time Series Forecasting from a Pure Graph Perspective
  98. Syntax-semantics interface: an algebraic model
  99. An Automated Pipeline for Tumour-Infiltrating Lymphocyte Scoring in Breast Cancer
  100. Frequency-domain MLPs are More Effective Learners in Time Series Forecasting
All 188
  1. Automatic Report Generation for Histopathology images using pre-trained Vision Transformers
  2. Search-Based Fairness Testing: An Overview
  3. Time Scale Network: A Shallow Neural Network For Time Series Data
  4. Deep Fast Vision: A Python Library for Accelerated Deep Transfer Learning Vision Prototyping
  5. GRAM: An Interpretable Approach for Graph Anomaly Detection using Gradient Attention Maps
  6. Going beyond persistent homology using persistent homology
  7. Dense Visual Odometry Using Genetic Algorithm
  8. Incorporating sufficient physical information into artificial neural networks: a guaranteed improvement via physics-based Rao-Blackwellization
  9. An Evaluation of Forensic Facial Recognition
  10. Federated Learning Across Decentralized and Unshared Archives for Remote Sensing Image Classification
  11. Minimum norm interpolation by perceptra: Explicit regularization and implicit bias
  12. MonoProb: Self-Supervised Monocular Depth Estimation with Interpretable Uncertainty
  13. High-dimensional mixed-categorical Gaussian processes with application to multidisciplinary design optimization for a green aircraft
  14. Fight Fire with Fire: Combating Adversarial Patch Attacks using Pattern-randomized Defensive Patches
  15. Multilingual and Multi-topical Benchmark of Fine-tuned Language models and Large Language Models for Check-Worthy Claim Detection
  16. Exploring the Efficacy of Base Data Augmentation Methods in Deep Learning-Based Radiograph Classification of Knee Joint Osteoarthritis
  17. Distributionally Robust Skeleton Learning of Discrete Bayesian Networks
  18. An Interpretable Machine Learning Framework to Understand Bikeshare Demand before and during the COVID-19 Pandemic in New York City
  19. Consistency for constrained maximum likelihood estimation and clustering based on mixtures of elliptically-symmetric distributions under general data generating processes
  20. 1-Lipschitz Neural Networks are more expressive with N-Activations
  21. Making LLMs Worth Every Penny: Resource-Limited Text Classification in Banking
  22. In-Context Learning for MIMO Equalization Using Transformer-Based Sequence Models
  23. Dual input stream transformer for vertical drift correction in eye-tracking reading data
  24. Learning-Based Biharmonic Augmentation for Point Cloud Classification
  25. Attributes Grouping and Mining Hashing for Fine-Grained Image Retrieval
  26. Lidar-based Norwegian tree species detection using deep learning
  27. RIGA: A Regret-Based Interactive Genetic Algorithm
  28. Improved Positional Encoding for Implicit Neural Representation based Compact Data Representation
  29. Ulcerative Colitis Mayo Endoscopic Scoring Classification with Active Learning and Generative Data Augmentation
  30. Refining the ONCE Benchmark with Hyperparameter Tuning
  31. Deep learning for 3D Object Detection and Tracking in Autonomous Driving: A Brief Survey
  32. 2D Image head pose estimation via latent space regression under occlusion settings
  33. Diagonal Hierarchical Consistency Learning for Semi-supervised Medical Image Segmentation
  34. Symbolic Regression as Feature Engineering Method for Machine and Deep Learning Regression Tasks
  35. U3DS3: Unsupervised 3D Semantic Scene Segmentation
  36. Unlock Reliable Skill Inference for Quadruped Adaptive Behavior by Skill Graph
  37. Double Machine Learning Based Structure Identification from Temporal Data
  38. Polar-Net: A Clinical-Friendly Model for Alzheimer's Disease Detection in OCTA Images
  39. Keystroke Verification Challenge (KVC): Biometric and Fairness Benchmark Evaluation
  40. Robust Adversarial Attacks Detection for Deep Learning based Relative Pose Estimation for Space Rendezvous
  41. Vision Big Bird: Random Sparsification for Full Attention
  42. Comparing Male Nyala and Male Kudu Classification using Transfer Learning with ResNet-50 and VGG-16
  43. Sum-max Submodular Bandits
  44. Plasma Surrogate Modelling using Fourier Neural Operators
  45. Large Language Models are Zero Shot Hypothesis Proposers
  46. Multiscale Neural Operators for Solving Time-Independent PDEs
  47. Hierarchical deep learning-based adaptive time-stepping scheme for multiscale simulations
  48. A Neural Height-Map Approach for the Binocular Photometric Stereo Problem
  49. ID Embedding as Subtle Features of Content and Structure for Multimodal Recommendation
  50. Out-of-Distribution-Aware Electric Vehicle Charging
  51. Genetic Algorithm enhanced by Deep Reinforcement Learning in parent selection mechanism and mutation : Minimizing makespan in permutation flow shop scheduling problems
  52. Aggregation Weighting of Federated Learning via Generalization Bound Estimation
  53. Early-Exit Neural Networks with Nested Prediction Sets
  54. Efficient Segmentation with Texture in Ore Images Based on Box-supervised Approach
  55. The Shape of Learning: Anisotropy and Intrinsic Dimensions in Transformer-Based Models
  56. Automated Sperm Assessment Framework and Neural Network Specialized for Sperm Video Recognition
  57. Federated Learning with Manifold Regularization and Normalized Update Reaggregation
  58. Inter-object Discriminative Graph Modeling for Indoor Scene Recognition
  59. Fake Alignment: Are LLMs Really Aligned Well?
  60. An alternative for one-hot encoding in neural network models
  61. FlashFFTConv: Efficient Convolutions for Long Sequences with Tensor Cores
  62. Citation Recommendation on Scholarly Legal Articles
  63. Low-Multi-Rank High-Order Bayesian Robust Tensor Factorization
  64. Hiformer: Heterogeneous Feature Interactions Learning with Transformers for Recommender Systems
  65. Central Angle Optimization for 360-degree Holographic 3D Content
  66. A Performance-Driven Benchmark for Feature Selection in Tabular Deep Learning
  67. Trends in Integration of Knowledge and Large Language Models: A Survey and Taxonomy of Methods, Benchmarks, and Applications
  68. Testing Dependency of Unlabeled Databases
  69. Automated Heterogeneous Low-Bit Quantization of Multi-Model Deep Learning Inference Pipeline
  70. Fair Supervised Learning with A Simple Random Sampler of Sensitive Attributes
  71. DPR: An Algorithm Mitigate Bias Accumulation in Recommendation feedback loops
  72. Domain Generalization by Learning from Privileged Medical Imaging Information
  73. Layer-wise Auto-Weighting for Non-Stationary Test-Time Adaptation
  74. Reframing Audience Expansion through the Lens of Probability Density Estimation
  75. Cognitive Architecture Toward Common Ground Sharing Among Humans and Generative AIs: Trial on Model-Model Interactions in Tangram Naming Task
  76. Clipped-Objective Policy Gradients for Pessimistic Policy Optimization
  77. Tamil-Llama: A New Tamil Language Model Based on Llama 2
  78. AI-native Interconnect Framework for Integration of Large Language Model Technologies in 6G Systems
  79. UMedNeRF: Uncertainty-aware Single View Volumetric Rendering for Medical Neural Radiance Fields
  80. AccEPT: An Acceleration Scheme for Speeding Up Edge Pipeline-parallel Training
  81. Machine Learning-powered Compact Modeling of Stochastic Electronic Devices using Mixture Density Networks
  82. CFBenchmark: Chinese Financial Assistant Benchmark for Large Language Model
  83. Scale-MIA: A Scalable Model Inversion Attack against Secure Federated Learning via Latent Space Reconstruction
  84. Model-as-a-Service (MaaS): A Survey
  85. Leveraging LLMs for Synthesizing Training Data Across Many Languages in Multilingual Dense Retrieval
  86. Adaptive Variance Thresholding: A Novel Approach to Improve Existing Deep Transfer Vision Models and Advance Automatic Knee-Joint Osteoarthritis Classification
  87. Synthesizing Bidirectional Temporal States of Knee Osteoarthritis Radiographs with Cycle-Consistent Generative Adversarial Neural Networks
  88. Improvements on Uncertainty Quantification for Node Classification via Distance-Based Regularization