mlsanityData to 14 Oct 2026

Papers

New on arXiv

Fri 24 Nov 2023

168 papers

  1. Synthetic Shifts to Initial Seed Vector Exposes the Brittle Nature of Latent-Based Diffusion ModelsDiffusion models → Diffusion foundations and sampling
  2. GeoChat: Grounded Large Vision-Language Model for Remote SensingMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  3. Unified Medical Image Pre-training in Language-Guided Common Semantic SpaceMultimodal LLMs / vision-language models → Medical vision-language models
  4. TrojanedCM: A Repository of Trojaned Large Language Models of CodeLLM safety and security → Backdoor and data poisoning attacks
  5. AdaDiff: Adaptive Step Selection for Fast Diffusion ModelsDiffusion models → Diffusion foundations and sampling
  6. Reinforcement Learning from Statistical Feedback: the Journey from AB Testing to ANT TestingLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
  7. Charting New Territories: Exploring the Geographic and Geospatial Capabilities of Multimodal LLMsMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  8. CatVersion: Concatenating Embeddings for Diffusion-Based Text-to-Image PersonalizationDiffusion models → Image generation, text-to-image and editing
  9. Animate124: Animating One Image to 4D Dynamic SceneDiffusion models → 3D, point cloud and scene generation
  10. Large Language Models as Automated Aligners for benchmarking Vision-Language ModelsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  11. Griffon: Spelling out All Object Locations at Any Granularity with Large Language ModelsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  12. Data-Efficient Alignment of Large Language Models with Human Feedback Through Natural LanguageLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  13. ToddlerDiffusion: Interactive Structured Image Generation with Cascaded Schr"odinger BridgeDiffusion models → Image generation, text-to-image and editing
  14. MVControl: Adding Conditional Control to Multi-view Diffusion for Controllable Text-to-3D GenerationDiffusion models → Image generation, text-to-image and editing
  15. Joint Diffusion: Mutual Consistency-Driven Diffusion Model for PET-MRI Co-ReconstructionDiffusion models → Medical imaging and segmentation
  16. Universal Jailbreak Backdoors from Poisoned Human FeedbackLLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks
  17. Towards Concept-based Interpretability of Skin Lesion Diagnosis using Vision-Language ModelsMultimodal LLMs / vision-language models → Medical vision-language models
  18. TVT: Training-Free Vision Transformer Search on Tiny DatasetsKnowledge distillation → General knowledge distillation methods
  19. Maximizing Discrimination Capability of Knowledge Distillation with Energy FunctionKnowledge distillation → General knowledge distillation methods
  20. Offline Skill Generalization via Task and Motion PlanningOffline RL and imitation learning from data → Real-world robot offline RL
  21. Cosine Similarity Knowledge Distillation for Individual Class Information TransferKnowledge distillation → General knowledge distillation methods
  22. Paragraph-to-Image Generation with Information-Enriched Diffusion ModelDiffusion models → Image generation, text-to-image and editing
  23. Latent Diffusion Prior Enhanced Deep Unfolding for Snapshot Spectral Compressive ImagingDiffusion models → Inverse problems and image restoration
  24. Efficient Open-world Reinforcement Learning via Knowledge Distillation and Autonomous Rule DiscoveryKnowledge distillation → On-policy and self-distillation for LLMs
  25. Pseudo-label Correction for Instance-dependent Noise Using Teacher-student FrameworkKnowledge distillation → General knowledge distillation methods
  26. Deep Learning-Enabled Swallowing Monitoring and Postoperative Recovery Biosensing System
  27. Automated Small Kidney Cancer Detection in Non-Contrast Computed Tomography
  28. Hierarchical ML Codebook Design for Extreme MIMO Beam Management
  29. Gender inference: can chatGPT outperform common commercial tools?
  30. Automatic detection of problem-gambling signs from online texts using large language models
  31. InceptionCaps: A Performant Glaucoma Classification Model for Data-scarce Environment
  32. Who is leading in AI? An analysis of industry AI research
  33. DeepTreeGANv2: Iterative Pooling of Point Clouds
  34. Deep encoder-decoder hierarchical convolutional neural networks for conjugate heat transfer surrogate modeling
  35. DemoFusion: Democratising High-Resolution Image Generation With No
  36. UniHPE: Towards Unified Human Pose Estimation via Contrastive Learning
  37. Next-gen traffic surveillance: AI-assisted mobile traffic violation detection system
  38. Bayesian Neural Networks for 2D MRI Segmentation
  39. Advancing Fluid-Based Thermal Management Systems Design: Leveraging Graph Neural Networks for Graph Regression and Efficient Enumeration Reduction
  40. Tracing Influence at Scale: A Contrastive Learning Approach to Linking Public Comments and Regulator Responses
  41. Improving Cross-Domain Hate Speech Generalizability with Emotion Knowledge
  42. Effective Structural Encodings via Local Curvature Profiles
  43. An Empirical Investigation into Benchmarking Model Multiplicity for Trustworthy Machine Learning: A Case Study on Image Classification
  44. Disruption Prediction in Fusion Devices through Feature Extraction and Logistic Regression
  45. OpusCleaner and OpusTrainer, open source toolkits for training Machine Translation and Large language models
  46. Benchmarking Robustness of Text-Image Composed Retrieval
  47. Custom Data Augmentation for low resource ASR using Bark and Retrieval-Based Voice Conversion
  48. Weak Alignment Supervision from Hybrid Model Improves End-to-end ASR
  49. Proximal Algorithms for Accelerated Langevin Dynamics
  50. Deep Latent Force Models: ODE-based Process Convolutions for Bayesian Deep Learning
  51. A Reusable AI-Enabled Defect Detection System for Railway Using Ensembled CNN
  52. Revisiting Quantum Algorithms for Linear Regressions: Quadratic Speedups without Data-Dependent Parameters
  53. Text and Click inputs for unambiguous open vocabulary instance segmentation
  54. Data-to-Text Bilingual Generation
  55. Evaluating Large Language Models through Gender and Racial Stereotypes
  56. GPT-4V Takes the Wheel: Promises and Challenges for Pedestrian Behavior Prediction
  57. Understanding the Role of Textual Prompts in LLM for Time Series Forecasting: an Adapter View
  58. From Text to Image: Exploring GPT-4Vision's Potential in Advanced Radiological Analysis across Subspecialties
  59. VSViG: Real-time Video-based Seizure Detection via Skeleton-based Spatiotemporal ViG
  60. Set Features for Anomaly Detection
  61. Trainwreck: A damaging adversarial attack on image classifiers
  62. Learning to Cooperate and Communicate Over Imperfect Channels
  63. Low-Cost HEM with Arduino and Zigbee Technologies in the Energy Sector in Colombia
  64. SafeSea: Synthetic Data Generation for Adverse & Low Probability Maritime Conditions
  65. SEGIC: Unleashing the Emergent Correspondence for In-Context Segmentation
  66. Differentiable and accelerated spherical harmonic and Wigner transforms
  67. Understanding Self-Supervised Features for Learning Unsupervised Instance Segmentation
  68. Convergence Analysis for Learning Orthonormal Deep Linear Neural Networks
  69. JetLOV: Enhancing Jet Tree Tagging through Neural Network Learning of Optimal LundNet Variables
  70. Data-driven Prior Learning for Bayesian Optimisation
  71. One Pass Streaming Algorithm for Super Long Token Attention Approximation in Sublinear Space
  72. History Filtering in Imperfect Information Games: Algorithms and Complexity
  73. Learning in Deep Factor Graphs with Gaussian Belief Propagation
  74. Calibrated Language Models Must Hallucinate
  75. More is Better in Modern Machine Learning: when Infinite Overparameterization is Optimal and Overfitting is Obligatory
  76. A General Framework for User-Guided Bayesian Optimization
  77. Continuous football player tracking from discrete broadcast data
  78. Unsupervised high-throughput segmentation of cells and cell nuclei in quantitative phase images
  79. Automated Detection and Counting of Windows using UAV Imagery based Remote Sensing
  80. One Strike, You're Out: Detecting Markush Structures in Low Signal-to-Noise Ratio Images
  81. Differentially Private SGD Without Clipping Bias: An Error-Feedback Approach
  82. ARIA: On the Interaction Between Architectures, Initialization and Aggregation Methods for Federated Visual Classification
  83. Eliciting Honest Information From Authors Using Sequential Review
  84. Neural Style Transfer for Computer Games
  85. Analysis of the expected L2 error of an over-parametrized deep neural network estimate learned by gradient descent without regularization
  86. A Metalearned Neural Circuit for Nonparametric Bayesian Inference
  87. A Survey and Analysis of Evolutionary Operators for Permutations
  88. GPT Struct Me: Probing GPT Models on Narrative Entity Extraction
  89. Example-Based Explanations of Random Forest Predictions
  90. Counting Solutions to Conjunctive Queries: Structural and Hybrid Tractability
  91. Predicting Failure of P2P Lending Platforms through Machine Learning: The Case in China
  92. RAISE -- Radiology AI Safety, an End-to-end lifecycle approach
  93. Electric Vehicles coordination for grid balancing using multi-objective Harris Hawks Optimization
  94. FRUITS: Feature Extraction Using Iterated Sums for Time Series Classification
  95. Inferring Latent Class Statistics from Text for Robust Visual Few-Shot Learning
  96. RDF Stream Taxonomy: Systematizing RDF Stream Types in Research and Practice
  97. CMed-GPT: Prompt Tuning for Entity-Aware Chinese Medical Dialogue Generation
  98. Finding Foundation Models for Time Series Classification with a PreText Task
  99. Introducing 3DCNN ResNets for ASD full-body kinematic assessment: a comparison with hand-crafted features
  100. Digital Twin-Native AI-Driven Service Architecture for Industrial Networks
All 168
  1. Machine Translation for Ge'ez Language
  2. GaussianEditor: Swift and Controllable 3D Editing with Gaussian Splatting
  3. tinyCLAP: Distilling Constrastive Language-Audio Pretrained Models
  4. FRAD: Front-Running Attacks Detection on Ethereum using Ternary Classification Model
  5. Multi-Class Anomaly Detection based on Regularized Discriminative Coupled hypersphere-based Feature Adaptation
  6. Analysing the Impact of Removing Infrequent Words on Topic Quality in LDA Models
  7. StableSSM: Alleviating the Curse of Memory in State-space Models through Stable Reparameterization
  8. Towards Interpretable Classification of Leukocytes based on Deep Learning
  9. SER_AMPEL: a multi-source dataset for speech emotion recognition of Italian older adults
  10. Sliding Window FastEdit: A Framework for Lesion Annotation in Whole-body PET Images
  11. Evolutionary game theory: the mathematics of evolution and collective behaviours
  12. Controlled Text Generation via Language Model Arithmetic
  13. MRxaI: Black-Box Explainability for Image Classifiers in a Medical Setting
  14. Fault Detection in Telecom Networks using Bi-level Federated Graph Neural Networks
  15. Online Importance Sampling for Stochastic Gradient Optimization
  16. DP-NMT: Scalable Differentially-Private Machine Translation
  17. Finite Volume Features, Global Geometry Representations, and Residual Training for Deep Learning-based CFD Simulation
  18. CT-xCOV: a CT-scan based Explainable Framework for COVid-19 diagnosis
  19. IDD-AW: A Benchmark for Safe and Robust Segmentation of Drive Scenes in Unstructured Traffic and Adverse Weather
  20. How to ensure a safe control strategy? Towards a SRL for urban transit autonomous operation
  21. Segment (Almost) Nothing: Prompt-Agnostic Adversarial Attacks on Segmentation Models
  22. Deep Learning for Automatic Strain Quantification in Arrhythmogenic Right Ventricular Cardiomyopathy
  23. Local Concept Embeddings for Analysis of Concept Distributions in Vision DNN Feature Spaces
  24. Disentangling the Spectral Properties of the Hodge Laplacian: Not All Small Eigenvalues Are Equal
  25. Human-Machine Cooperative Multimodal Learning Method for Cross-subject Olfactory Preference Recognition
  26. Approximation of Convex Envelope Using Reinforcement Learning
  27. Deformable multi-modal image registration for the correlation between optical measurements and histology images
  28. A Comparison of PDF Projection with Normalizing Flows and SurVAE
  29. Unveiling The Factors of Aesthetic Preferences with Explainable AI
  30. LLamol: A Dynamic Multi-Conditional Generative Transformer for De Novo Molecular Design
  31. OneFormer3D: One Transformer for Unified Point Cloud Segmentation
  32. BHGNN-RT: Network embedding for directed heterogeneous graphs
  33. TEA: Test-time Energy Adaptation
  34. Prototype of deployment of Federated Learning with IoT devices
  35. MSCMNet: Multi-scale Semantic Correlation Mining for Visible-Infrared Person Re-Identification
  36. 'UFAL CorPipe at CRAC 2023: Larger Context Improves Multilingual Coreference Resolution
  37. Directly Attention Loss Adjusted Prioritized Experience Replay
  38. A Parameterized Generative Adversarial Network Using Cyclic Projection for Explainable Medical Image Classification
  39. Achieving Margin Maximization Exponentially Fast via Progressive Norm Rescaling
  40. Potential Societal Biases of ChatGPT in Higher Education: A Scoping Review
  41. Ethical Implications of ChatGPT in Higher Education: A Scoping Review
  42. Federated Transformed Learning for a Circular, Secure, and Tiny AI
  43. Deciphering and integrating invariants for neural operator learning with various physical mechanisms
  44. Thompson sampling for zero-inflated count outcomes with an application to the Drink Less mobile health study
  45. Average Token Delay: A Duration-aware Latency Metric for Simultaneous Translation
  46. Highly Detailed and Temporal Consistent Video Stylization via Synchronized Multi-Frame Diffusion
  47. Comparative Analysis of Transformers for Modeling Tabular Data: A Casestudy using Industry Scale Dataset
  48. Cycle Invariant Positional Encoding for Graph Representation Learning
  49. GATGPT: A Pre-trained Large Language Model with Graph Attention Network for Spatiotemporal Imputation
  50. Large Language Models as Topological Structure Enhancers for Text-Attributed Graphs
  51. BinaryHPE: 3D Human Pose and Shape Estimation via Binarization
  52. Windformer:Bi-Directional Long-Distance Spatio-Temporal Network For Wind Speed Prediction
  53. Robust Domain Misinformation Detection via Multi-modal Feature Alignment
  54. Stable Cluster Discrimination for Deep Clustering
  55. New Epochs in AI Supervision: Design and Implementation of an Autonomous Radiology AI Monitoring System
  56. AdaMedGraph: Adaboosting Graph Neural Networks for Personalized Medicine
  57. GeoViT: A Versatile Vision Transformer Architecture for Geospatial Image Analysis
  58. Decouple Content and Motion for Conditional Image-to-Video Generation
  59. Image Super-Resolution with Text Prompt Diffusion
  60. Multi-modal Instance Refinement for Cross-domain Action Recognition
  61. Racing With ROS 2 A Navigation System for an Autonomous Formula Student Race Car
  62. Cooperative Dual Attention for Audio-Visual Speech Enhancement with Facial Cues
  63. CRISP: Hybrid Structured Sparsity for Class-aware Model Pruning
  64. Segmentation-Based Parametric Painting
  65. Adaptive Calibration: A Unified Conversion Framework of Spiking Neural Networks
  66. ZeroPS: High-quality Cross-modal Knowledge Transfer for Zero-Shot 3D Part Segmentation
  67. Out-of-Distribution Generalized Dynamic Graph Neural Network with Disentangled Intervention and Invariance Promotion
  68. RSB-Pose: Robust Short-Baseline Binocular 3D Human Pose Estimation with Occlusion Handling