mlsanityData to 14 Oct 2026

Papers

New on arXiv

Wed 6 Sep 2023

195 papers

  1. Distribution-Aware Prompt Tuning for Vision-Language ModelsMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  2. Efficient Baselines for Motion Prediction in Autonomous DrivingEnd-to-end autonomous driving → Generative simulation for driving
  3. SADIR: Shape-Aware Diffusion Models for 3D Image ReconstructionDiffusion models → Medical imaging and segmentation
  4. REBOOT: Reuse Data for Bootstrapping Efficient Real-World Dexterous ManipulationOffline RL and imitation learning from data → Real-world robot offline RL
  5. Matcha-TTS: A fast TTS architecture with conditional flow matchingDiffusion models → Audio, speech and music
  6. My Art My Choice: Adversarial Protection Against Unruly AIDiffusion models → Robustness, privacy and adversarial aspects
  7. SLiMe: Segment Like MeMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP +1
  8. Everyone Deserves A Reward: Learning Customized Human PreferencesLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
  9. ORL-AUDITOR: Dataset Auditing in Offline Deep Reinforcement LearningOffline RL and imitation learning from data → Offline RL algorithms +1
  10. MCM: Multi-condition Motion Synthesis Framework for Multi-scenarioDiffusion models → Video generation
  11. Leveraging ASR Pretrained Conformers for Speaker Verification through Transfer Learning and Knowledge DistillationKnowledge distillation → Speech and audio distillation
  12. A deep Natural Language Inference predictor without language-specific training dataKnowledge distillation → Knowledge distillation for LLMs
  13. Aligning Large Language Models for Clinical TasksLLM alignment / RLHF / preference optimisation → Medical LLM alignment
  14. Rethinking Momentum Knowledge Distillation in Online Continual LearningKnowledge distillation → Distillation for continual learning
  15. Knowledge Distillation Layer that Lets the Student DecideKnowledge distillation → General knowledge distillation methods
  16. Diffusion Model is Secretly a Training-free Open Vocabulary Semantic SegmenterDiffusion models → Medical imaging and segmentation
  17. DMKD: Improving Feature-based Knowledge Distillation for Object Detection Via Dual Masking AugmentationKnowledge distillation → Detection and dense prediction distillation
  18. Certifying LLM Safety against Adversarial PromptingLLM safety and security → Jailbreaking
  19. Diffusion-EDFs: Bi-equivariant Denoising Generative Modeling on SE(3) for Visual Robotic ManipulationDiffusion models → Diffusion and flow policies for robotics
  20. AI for Investment: A Platform Disruption
  21. Students Success Modeling: Most Important Factors
  22. A Contextual Topic Modeling and Content Analysis of Iranian laws and Regulations
  23. Decoding the Alphabet Soup of Degrees in the United States Postsecondary Education System Through Hybrid Method: Database and Text Mining
  24. AI-Driven Personalised Offloading Device Prescriptions: A Cutting-Edge Approach to Preventing Diabetes-Related Plantar Forefoot Ulcers and Complications
  25. Investigating Online Financial Misinformation and Its Consequences: A Computational Perspective
  26. ETP: Learning Transferable ECG Representations via ECG-Text Pre-training
  27. Narrative as a Dynamical System
  28. Addressing the Blind Spots in Spoken Language Processing
  29. Synthetic Text Generation using Hypergraph Representations
  30. Framework-Based Qualitative Analysis of Free Responses of Large Language Models: Algorithmic Fidelity
  31. Safe Neural Control for Non-Affine Control Systems with Differentiable Control Barrier Functions
  32. C-CLIP: Contrastive Image-Text Encoders to Close the Descriptive-Commentative Gap
  33. A hybrid quantum-classical fusion neural network to improve protein-ligand binding affinity predictions for drug discovery
  34. A recommender for the management of chronic pain in patients undergoing spinal cord stimulation
  35. The Role of Communication and Reference Songs in the Mixing Process: Insights from Professional Mix Engineers
  36. Reasonable Anomaly Detection in Long Sequences
  37. A novel method for iris recognition using BP neural network and parallel computing by the aid of GPUs (Graphics Processing Units)
  38. Community-Based Hierarchical Positive-Unlabeled (PU) Model Fusion for Chronic Disease Prediction
  39. Kidney abnormality segmentation in thorax-abdomen CT scans
  40. Active shooter detection and robust tracking utilizing supplemental synthetic data
  41. RoDia: A New Dataset for Romanian Dialect Identification from Speech
  42. Self-Supervised Masked Digital Elevation Models Encoding for Low-Resource Downstream Tasks
  43. ViewMix: Augmentation for Robust Representation in Self-Supervised Learning
  44. Ensemble linear interpolators: The role of ensembling
  45. Source Camera Identification and Detection in Digital Videos through Blind Forensics
  46. Using Neural Networks for Fast SAR Roughness Estimation of High Resolution Images
  47. Parameter Efficient Audio Captioning With Faithful Guidance Using Audio-text Shared Latent Representation
  48. Expert Uncertainty and Severity Aware Chest X-Ray Classification by Multi-Relationship Graph Learning
  49. MEGANet: Multi-Scale Edge-Guided Attention Network for Weak Boundary Polyp Segmentation
  50. CoNeS: Conditional neural fields with shift modulation for multi-sequence MRI translation
  51. Fitness Approximation through Machine Learning
  52. Robotic Table Tennis: A Case Study into a High Speed Learning System
  53. Comparative Analysis of Deep-Fake Algorithms
  54. Scalable Learning of Intrusion Responses through Recursive Decomposition
  55. CLEANing Cygnus A deep and fast with R2D2
  56. Let Quantum Neural Networks Choose Their Own Frequencies
  57. Temporal Inductive Path Neural Network for Temporal Knowledge Graph Reasoning
  58. Graph Theory Applications in Advanced Geospatial Research
  59. Robust Visual Tracking by Motion Analyzing
  60. EvoCLINICAL: Evolving Cyber-Cyber Digital Twin with Active Transfer Learning for Automated Cancer Registry System
  61. Testing properties of distributions in the streaming model
  62. EGIC: Enhanced Low-Bit-Rate Generative Image Compression Guided by Semantic Segmentation
  63. Automated Bioinformatics Analysis via AutoBA
  64. GPT Can Solve Mathematical Problems Without a Calculator
  65. RepSGG: Novel Representations of Entities and Relationships for Scene Graph Generation
  66. Spatio-Temporal Contrastive Self-Supervised Learning for POI-level Crowd Flow Inference
  67. Implicit Design Choices and Their Impact on Emotion Recognition Model Development and Evaluation
  68. Federated Learning Over Images: Vertical Decompositions and Pre-Trained Backbones Are Difficult to Beat
  69. Blink: Link Local Differential Privacy in Graph Neural Networks via Bayesian Estimation
  70. Bayes' Rays: Uncertainty Quantification for Neural Radiance Fields
  71. 3D Transformer based on deformable patch location for differential diagnosis between Alzheimer's disease and Frontotemporal dementia
  72. 3D Object Positioning Using Differentiable Multimodal Learning
  73. Gender-specific Machine Translation with Large Language Models
  74. PDiscoNet: Semantically consistent part discovery for fine-grained recognition
  75. Impression-Informed Multi-Behavior Recommender System: A Hierarchical Graph Attention Approach
  76. Split-Boost Neural Networks
  77. J-Guard: Journalism Guided Adversarially Robust Detection of AI-generated News
  78. ResFields: Residual Neural Fields for Spatiotemporal Signals
  79. Learning to Recharge: UAV Coverage Path Planning through Deep Reinforcement Learning
  80. Data-Driven Neural Polar Codes for Unknown Channels With and Without Memory
  81. The Best Arm Evades: Near-optimal Multi-pass Streaming Lower Bounds for Pure Exploration in Multi-armed Bandits
  82. Using Multiple Vector Channels Improves E(n)-Equivariant Graph Neural Networks
  83. On strategies for risk management and decision making under uncertainty shared across multiple fields
  84. MyoDex: A Generalizable Prior for Dexterous Manipulation
  85. Knowledge Solver: Teaching LLMs to Search for Domain Knowledge from Knowledge Graphs
  86. Detecting Manufacturing Defects in PCBs via Data-Centric Machine Learning on Solder Paste Inspection Features
  87. Do We Still Need Non-Maximum Suppression? Accurate Confidence Estimates and Implicit Duplication Modeling with IoU-Aware Calibration
  88. ContrastWSD: Enhancing Metaphor Detection with Word Sense Disambiguation Following the Metaphor Identification Procedure
  89. FArMARe: a Furniture-Aware Multi-task methodology for Recommending Apartments based on the user interests
  90. GPT-InvestAR: Enhancing Stock Investment Strategies through Annual Report Analysis with Large Language Models
  91. Parameterizing pressure-temperature profiles of exoplanet atmospheres with neural networks
  92. Character Queries: A Transformer-based Approach to On-Line Handwritten Character Segmentation
  93. A Multimodal Analysis of Influencer Content on Twitter
  94. Prompt-based Ingredient-Oriented All-in-One Image Restoration
  95. Learning Active Subspaces for Effective and Scalable Uncertainty Quantification in Deep Neural Networks
  96. CoLA: Exploiting Compositional Structure for Automatic and Efficient Numerical Linear Algebra
  97. Hide and Seek (HaS): A Lightweight Framework for Prompt Privacy Protection
  98. Adaptive Growth: Real-time CNN Layer Expansion
  99. Exploring Semantic Consistency in Unpaired Image Translation to Generate Data for Surgical Applications
  100. Combining pre-trained Vision Transformers and CIDER for Out Of Domain Detection
All 195
  1. A Refutation of Shapley Values for Explainability
  2. Automated CVE Analysis for Threat Prioritization and Impact Prediction
  3. An Efficient Temporary Deepfake Location Approach Based Embeddings for Partially Spoofed Audio Detection
  4. Deep Learning for Polycystic Kidney Disease: Utilizing Neural Networks for Accurate and Early Detection through Gene Expression Analysis
  5. Universal Preprocessing Operators for Embedding Knowledge Graphs with Literals
  6. SEAL: A Framework for Systematic Evaluation of Real-World Super-Resolution
  7. Amortised Inference in Bayesian Neural Networks
  8. SymED: Adaptive and Online Symbolic Representation of Data on the Edge
  9. Sparse 3D Reconstruction via Object-Centric Ray Sampling
  10. A Theoretical Explanation of Activation Sparsity through Flat Minima and Adversarial Robustness
  11. Vote2Cap-DETR++: Decoupling Localization and Describing for End-to-End 3D Dense Captioning
  12. Continual Evidential Deep Learning for Out-of-Distribution Detection
  13. An Offline Learning Approach to Propagator Models
  14. Natural and Robust Walking using Reinforcement Learning without Demonstrations in High-Dimensional Musculoskeletal Models
  15. FishMOT: A Simple and Effective Method for Fish Tracking Based on IoU Matching
  16. On the Impact of Feeding Cost Risk in Aquaculture Valuation and Decision Making
  17. CR-VAE: Contrastive Regularization on Variational Autoencoders for Preventing Posterior Collapse
  18. Dynamic Hyperbolic Attention Network for Fine Hand-object Reconstruction
  19. Hierarchical-level rain image generative model based on GAN
  20. LuViRA Dataset Validation and Discussion: Comparing Vision, Radio, and Audio Sensors for Indoor Localization
  21. A Non-Invasive Interpretable NAFLD Diagnostic Method Combining TCM Tongue Features
  22. M3D-NCA: Robust 3D Segmentation with Built-in Quality Control
  23. The case for and against fixed step-size: Stochastic approximation algorithms in optimization and machine learning
  24. EdgeFL: A Lightweight Decentralized Federated Learning Framework
  25. Estimating irregular water demands with physics-informed machine learning to inform leakage detection
  26. Patched Line Segment Learning for Vector Road Mapping
  27. GroupEnc: encoder with group loss for global structure preservation
  28. Persona-aware Generative Model for Code-mixed Language
  29. Leave no Place Behind: Improved Geolocation in Humanitarian Documents
  30. Ensemble DNN for Age-of-Information Minimization in UAV-assisted Networks
  31. On the Challenges of Building Datasets for Hate Speech Detection
  32. A Multimodal Learning Framework for Comprehensive 3D Mineral Prospectivity Modeling with Jointly Learned Structure-Fluid Relationships
  33. DECODE: Data-driven Energy Consumption Prediction leveraging Historical Data and Environmental Factors in Buildings
  34. Towards Efficient Training with Negative Samples in Visual Tracking
  35. ViCGCN: Graph Convolutional Network with Contextualized Language Models for Social Media Mining in Vietnamese
  36. A Unified Framework for Discovering Discrete Symmetries
  37. Non-Clashing Teaching Maps for Balls in Graphs
  38. MAD: Modality Agnostic Distance Measure for Image Registration
  39. Learning Hybrid Dynamics Models With Simulator-Informed Latent States
  40. On Reducing Undesirable Behavior in Deep Reinforcement Learning Models
  41. Enhancing Asynchronous Time Series Forecasting with Contrastive Relational Inference
  42. Image Aesthetics Assessment via Learnable Queries
  43. Generalised Mutual Information: a Framework for Discriminative Clustering
  44. Getting too personal(ized): The importance of feature choice in online adaptive algorithms
  45. Bandwidth-efficient Inference for Neural Image Compression
  46. A Critical Review of Common Log Data Sets Used for Evaluation of Sequence-based Anomaly Detection Techniques
  47. Random Postprocessing for Combinatorial Bayesian Optimization
  48. Adjacency-hopping de Bruijn Sequences for Non-repetitive Coding
  49. BigVSAN: Enhancing GAN-based Neural Vocoders with Slicing Adversarial Network
  50. Image-Object-Specific Prompt Learning for Few-Shot Class-Incremental Learning
  51. Promoting Open-domain Dialogue Generation through Learning Pattern Information between Contexts and Responses
  52. Roulette: A Semantic Privacy-Preserving Device-Edge Collaborative Inference Framework for Deep Learning Classification Tasks
  53. Combining Thermodynamics-based Model of the Centrifugal Compressors and Active Machine Learning for Enhanced Industrial Design Optimization
  54. Near-continuous time Reinforcement Learning for continuous state-action spaces
  55. Agent-based simulation of pedestrians' earthquake evacuation; application to Beirut, Lebanon
  56. Introducing Thermodynamics-Informed Symbolic Regression -- A Tool for Thermodynamic Equations of State Development
  57. 3D Trajectory Reconstruction of Drones using a Single Camera
  58. Dynamic Encoding and Decoding of Information for Split Learning in Mobile-Edge Computing: Leveraging Information Bottleneck Theory
  59. CVE-driven Attack Technique Prediction with Semantic Information Extraction and a Domain-specific Language Model
  60. Norm Tweaking: High-performance Low-bit Quantization of Large Language Models
  61. Improving diagnosis and prognosis of lung cancer using vision transformers: A scoping review
  62. GRASS: Unified Generation Model for Speech-to-Semantic Tasks
  63. LightNeuS: Neural Surface Reconstruction in Endoscopy using Illumination Decline
  64. Hot or Cold? Adaptive Temperature Sampling for Code Generation with Large Language Models
  65. On the Effects of Heterogeneous Errors on Multi-fidelity Bayesian Optimization
  66. Unifying over-smoothing and over-squashing in graph neural networks: A physics informed approach and beyond
  67. Towards Unsupervised Graph Completion Learning on Graphs with Features and Structure Missing
  68. SWAP: Exploiting Second-Ranked Logits for Adversarial Attacks on Time Series
  69. MLN-net: A multi-source medical image segmentation method for clustered microcalcifications using multiple layer normalization
  70. Rubric-Specific Approach to Automated Essay Scoring with Augmentation Training
  71. HC3 Plus: A Semantic-Invariant Human ChatGPT Comparison Corpus
  72. Stylebook: Content-Dependent Speaking Style Modeling for Any-to-Any Voice Conversion using Only Speech Data
  73. Large Language Models for Automated Open-domain Scientific Hypotheses Discovery
  74. Offensive Hebrew Corpus and Detection using BERT
  75. SlAction: Non-intrusive, Lightweight Obstructive Sleep Apnea Detection using Infrared Video
  76. Unveiling the frontiers of deep learning: innovations shaping diverse domains
  77. Addressing imperfect symmetry: A novel symmetry-learning actor-critic extension
  78. Improved Outlier Robust Seeding for k-means
  79. HAE-RAE Bench: Evaluation of Korean Knowledge in Language Models
  80. Gene-induced Multimodal Pre-training for Image-omic Classification
  81. A Joint Study of Phrase Grounding and Task Performance in Vision and Language Models
  82. Improving Image Classification of Knee Radiographs: An Automated Image Labeling Approach
  83. Efficient Training for Visual Tracking with Deformable Transformer
  84. RLSynC: Offline-Online Reinforcement Learning for Synthon Completion
  85. Progressive Attention Guidance for Whole Slide Vulvovaginal Candidiasis Screening
  86. Marketing Budget Allocation with Offline Constrained Deep Reinforcement Learning
  87. Fast and Resource-Efficient Object Tracking on Edge Devices: A Measurement Study
  88. Subsethood Measures of Spatial Granules
  89. Zero-Resource Hallucination Prevention for Large Language Models
  90. Contrastive Learning as Kernel Approximation
  91. TFBEST: Dual-Aspect Transformer with Learnable Positional Encoding for Failure Prediction
  92. Epi-Curriculum: Episodic Curriculum Learning for Low-Resource Domain Adaptation in Neural Machine Translation
  93. Multiclass Alignment of Confidence and Certainty for Network Calibration
  94. Deep Reinforcement Learning from Hierarchical Preference Design
  95. Adaptive Consensus: A network pruning approach for decentralized optimization