mlsanityData to 14 Oct 2026

Papers

New on arXiv

Thu 23 Nov 2023

177 papers

  1. SinSR: Diffusion-Based Image Super-Resolution in a Single StepDiffusion models → Inverse problems and image restoration
  2. HOPE: A Memory-Based and Composition-Aware Framework for Zero-Shot Learning with Hopfield Network and Soft Mixture of ExpertsMixture-of-experts → Vision mixture-of-experts
  3. Efficient and Robust Jet Tagging at the LHC with Knowledge DistillationKnowledge distillation → General knowledge distillation methods
  4. Tube-NeRF: Efficient Imitation Learning of Visuomotor Policies from MPC using Tube-Guided Data Augmentation and NeRFsOffline RL and imitation learning from data → Robot manipulation imitation learning
  5. A density estimation perspective on learning from pairwise human preferencesLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
  6. When is Off-Policy Evaluation (Reward Modeling) Useful in Contextual Bandits? A Data-Centric PerspectiveLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
  7. Boosting the Power of Small Multimodal Reasoning Models to Match Larger Models with Self-Consistency TrainingLLM reasoning → Multimodal reasoning
  8. ACT-Diffusion: Efficient Adversarial Consistency Training for One-step Diffusion ModelsDiffusion models → Diffusion foundations and sampling
  9. Cultural Bias and Cultural Alignment of Large Language ModelsLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
  10. HGCLIP: Exploring Vision-Language Models with Graph Representations for Hierarchical UnderstandingMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  11. DPSUR: Accelerating Differentially Private Stochastic Gradient Descent Using Selective Update and ReleaseLLM safety and security → Membership inference attacks
  12. Understanding the Vulnerability of CLIP to Image CompressionMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  13. Continual Learning of Diffusion Models with Generative DistillationDiffusion models → Robustness, privacy and adversarial aspects
  14. Probabilistic Tree-of-thought Reasoning for Answering Knowledge-intensive Complex QuestionsLLM reasoning → Knowledge- and tool-augmented reasoning
  15. Efficient Trigger Word InsertionLLM safety and security → Backdoor and data poisoning attacks
  16. MLLM-Bench: Evaluating Multimodal LLMs with Per-sample CriteriaMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  17. Robustness-Reinforced Knowledge Distillation with Correlation Distance and Network PruningKnowledge distillation → General knowledge distillation methods
  18. Periodically Exchange Teacher-Student for Source-Free Object DetectionKnowledge distillation → Detection and dense prediction distillation
  19. Controlling Large Language Model-based Agents for Large-Scale Decision-Making: An Actor-Critic ApproachLLM agents and tool use → General LLM agent frameworks and benchmarks
  20. Multi-intention Inverse Q-learning for Interpretable Behavior RepresentationOffline RL and imitation learning from data → Inverse reinforcement learning
  21. Adversarial defense based on distribution transferDiffusion models → Robustness, privacy and adversarial aspects
  22. Lego: Learning to Disentangle and Invert Personalized Concepts Beyond Object Appearance in Text-to-Image Diffusion ModelsDiffusion models → Image generation, text-to-image and editing
  23. Posterior Distillation SamplingDiffusion models → Image generation, text-to-image and editing
  24. Education distillation:getting student models to learn in shcoolsKnowledge distillation → General knowledge distillation methods
  25. Bridging Classical and Quantum Machine Learning: Knowledge Transfer From Classical to Quantum Neural Networks Using Knowledge DistillationKnowledge distillation → Graph neural network distillation
  26. Knowledge Distillation Based Semantic Communications For Multiple UsersKnowledge distillation → General knowledge distillation methods
  27. Improved Sample Complexity Bounds for Diffusion Model TrainingDiffusion models → Diffusion foundations and sampling
  28. FinMem: A Performance-Enhanced LLM Trading Agent with Layered Memory and Character DesignLLM agents and tool use → Financial trading and forecasting agents
  29. Stockformer: A Price-Volume Factor Stock Selection Model Based on Wavelet Transform and Multi-Task Self-Attention Networks
  30. Rediscovering Ranganathan: A Prismatic View of His Life through the Knowledge Graph Spectrum
  31. Classifying cow stall numbers using YOLO
  32. Federated Learning for Short Text Clustering
  33. Continuous Authentication Using Mouse Clickstream Data Analysis
  34. Presentation Attack Detection using Convolutional Neural Networks and Local Binary Patterns
  35. Presentation Attack detection using Wavelet Transform and Deep Residual Neural Net
  36. Acoustic Cybersecurity: Exploiting Voice-Activated Systems
  37. Cluster trajectory of SOFA score in predicting mortality in sepsis
  38. Mitigating Shortcut Learning with Diffusion Counterfactuals and Diverse Ensembles
  39. The 2nd Workshop on Maritime Computer Vision (MaCVi) 2024
  40. Deep Learning and NLP in Cryptocurrency Forecasting: Integrating Financial, Blockchain, and Social Media Data
  41. Point2RBox: Combine Knowledge from Synthetic Visual Patterns for End-to-end Oriented Object Detection with Single Point Supervision
  42. PointOBB: Learning Oriented Object Detection via Single Point Supervision
  43. Task-Distributionally Robust Data-Free Meta-Learning
  44. ExCeL : Combined Extreme and Collective Logit Information for Enhancing Out-of-Distribution Detection
  45. Attribute-Aware Representation Rectification for Generalized Zero-Shot Learning
  46. Compositional Zero-shot Learning via Progressive Language-based Observations
  47. All in One: RGB, RGB-D, and RGB-T Salient Object Detection
  48. Robust and Interpretable COVID-19 Diagnosis on Chest X-ray Images using Adversarial Training
  49. Risk Bounds of Accelerated SGD for Overparameterized Linear Regression
  50. Assumption-Lean and Data-Adaptive Post-Prediction Inference
  51. A New Benchmark and Model for Challenging Image Manipulation Detection
  52. Extending Variability-Aware Model Selection with Bias Detection in Machine Learning Projects
  53. Annotation Sensitivity: Training Data Collection Methods Affect Model Performance
  54. ECRF: Entropy-Constrained Neural Radiance Fields Compression with Frequency Domain Optimization
  55. Data-Driven Risk Modeling for Infrastructure Projects Using Artificial Intelligence Techniques
  56. A Systematic Review of Deep Learning-based Research on Radiology Report Generation
  57. Enhancing mTBI Diagnosis with Residual Triplet Convolutional Neural Network Using 3D CT
  58. Touch Analysis: An Empirical Evaluation of Machine Learning Classification Algorithms on Touch Data
  59. D-SCo: Dual-Stream Conditional Diffusion for Monocular Hand-Held Object Reconstruction
  60. Gradient-based bilevel optimization for multi-penalty Ridge regression through matrix differential calculus
  61. TCuPGAN: A novel framework developed for optimizing human-machine interactions in citizen science
  62. Appearance-based gaze estimation enhanced with synthetic images using deep neural networks
  63. Evaluating GPT-4's Vision Capabilities on Brazilian University Admission Exams
  64. Fast Policy Learning for Linear Quadratic Control with Entropy Regularization
  65. Variational Annealing on Graphs for Combinatorial Optimization
  66. GigaPose: Fast and Robust Novel Object Pose Estimation via One Correspondence
  67. Automated 3D Tumor Segmentation using Temporal Cubic PatchGAN (TCuP-GAN)
  68. Class Balanced Dynamic Acquisition for Domain Adaptive Semantic Segmentation using Active Learning
  69. Machine Learning For An Explainable Cost Prediction of Medical Insurance
  70. Privacy-Preserving Algorithmic Recourse
  71. A Blockchain Solution for Collaborative Machine Learning over IoT
  72. Exactly conservative physics-informed neural networks and deep operator networks for dynamical systems
  73. Byzantine Robustness and Partial Participation Can Be Achieved at Once: Just Clip Gradient Differences
  74. Towards Auditing Large Language Models: Improving Text-based Stereotype Detection
  75. Scalable AI Safety via Doubly-Efficient Debate
  76. Weight fluctuations in (deep) linear neural networks and a derivation of the inverse-variance flatness relation
  77. SONIQ: System-Optimized Noise-Injected Ultra-Low-Precision Quantization with Full-Precision Parity
  78. MINTY: Rule-based Models that Minimize the Need for Imputing Features with Missing Values
  79. Neural Subnetwork Ensembles
  80. Video Anomaly Detection using GAN
  81. Robust Decision Aggregation with Second-order Information
  82. PortfolioMentor: Multimodal Generative AI Companion for Learning and Crafting Interactive Digital Art Portfolios
  83. Class Uncertainty: A Measure to Mitigate Class Imbalance
  84. Question Answering in Natural Language: the Special Case of Temporal Expressions
  85. Brain MRI Screening Tool with Federated Learning
  86. Invisible Relevance Bias: Text-Image Retrieval Models Prefer AI-Generated Images
  87. You Only Explain Once
  88. Empirical Comparison between Cross-Validation and Mutation-Validation in Model Selection
  89. Machine learning-based decentralized TDMA for VLC IoT networks
  90. RetroDiff: Retrosynthesis as Multi-stage Distribution Interpolation
  91. Searching for Snippets of Open-Domain Dialogue in Task-Oriented Dialogue Datasets
  92. Learning Saliency From Fixations
  93. Enhancing Task-Oriented Dialogues with Chitchat: a Comparative Study Based on Lexical Diversity and Divergence
  94. Do VSR Models Generalize Beyond LRS3?
  95. Hardware Resilience Properties of Text-Guided Image Classifiers
  96. Towards Explainable Strategy Templates using NLP Transformers
  97. Identification for Tree-shaped Structural Causal Models in Polynomial Time
  98. Assessing the Impact of Noise on Quantum Neural Networks: An Experimental Analysis
  99. Assessment of Deep Learning Segmentation for Real-Time Free-Breathing Cardiac Magnetic Resonance Imaging at Rest and Under Exercise Stress
  100. AdapterFL: Adaptive Heterogeneous Federated Learning for Resource-constrained Mobile Computing Systems
All 177
  1. Multivariate Scenario Generation of Day-Ahead Electricity Prices using Normalizing Flows
  2. PrivateLoRA For Efficient Privacy Preserving LLM
  3. Creating and Leveraging a Synthetic Dataset of Cloud Optical Thickness Measures for Cloud Detection in MSI
  4. On the Hyperparameter Loss Landscapes of Machine Learning Models: An Exploratory Study
  5. Shadow loss: Memory-linear deep metric learning for efficient training
  6. High-resolution Population Maps Derived from Sentinel-1 and Sentinel-2
  7. When Side-Channel Attacks Break the Black-Box Property of Embedded Artificial Intelligence
  8. Direct Preference-Based Evolutionary Multi-Objective Optimization with Dueling Bandit
  9. GRJointNET: Synergistic Completion and Part Segmentation on 3D Incomplete Point Clouds
  10. EIGEN: Expert-Informed Joint Learning Aggregation for High-Fidelity Information Extraction from Document Images
  11. Docking Multirotors in Close Proximity using Learnt Downwash Models
  12. Jam-ALT: A Formatting-Aware Lyrics Transcription Benchmark
  13. FViT-Grasp: Grasping Objects With Using Fast Vision Transformers
  14. Learning Dynamic Selection and Pricing of Out-of-Home Deliveries
  15. MedISure: Towards Assuring Machine Learning-based Medical Image Classifiers using Mixup Boundary Analysis
  16. Low Latency Instance Segmentation by Continuous Clustering for LiDAR Sensors
  17. Deep Interactive Segmentation of Medical Images: A Systematic Review and Taxonomy
  18. Investigating the use of publicly available natural videos to learn Dynamic MR image reconstruction
  19. Human Machine Co-Creation. A Complementary Cognitive Approach to Creative Character Design Process Using GANs
  20. RankFeat&RankWeight: Rank-1 Feature/Weight Removal for Out-of-distribution Detection
  21. Handling The Non-Smooth Challenge in Tensor SVD: A Multi-Objective Tensor Recovery Framework
  22. Electric Network Frequency Optical Sensing Devices
  23. Learning Uniform Clusters on Hypersphere for Deep Graph-level Clustering
  24. Object Location Prediction in Real-time using LSTM Neural Network and Polynomial Regression
  25. Optimal Power Flow in Highly Renewable Power System Based on Attention Neural Networks
  26. Exploring Methods for Cross-lingual Text Style Transfer: The Case of Text Detoxification
  27. MetaFBP: Learning to Learn High-Order Predictor for Personalized Facial Beauty Prediction
  28. Parameter Exchange for Robust Dynamic Domain Generalization
  29. Predicting Patient Recovery or Mortality Using Deep Neural Decision Tree and Forest
  30. Some Like It Small: Czech Semantic Embedding Models for Industry Applications
  31. Exploring the impact of social stress on the adaptive dynamics of COVID-19: Typing the behavior of na"ive populations faced with epidemics
  32. Expanding the deep-learning model to diagnosis LVNC: Limitations and trade-offs
  33. Dialogue Quality and Emotion Annotations for Customer Support Conversations
  34. A DRL solution to help reduce the cost in waiting time of securing a traffic light for cyclists
  35. Query by Activity Video in the Wild
  36. General Phrase Debiaser: Debiasing Masked Language Models at a Multi-Token Level
  37. Unsupervised Learning for Topological Classification of Transportation Networks
  38. Can Physics Informed Neural Operators Self Improve?
  39. Leveraging Optimal Transport via Projections on Subspaces for Machine Learning Applications
  40. A Multi-solution Study on GDPR AI-enabled Completeness Checking of DPAs
  41. PointPCA+: Extending PointPCA objective quality assessment metric
  42. Minimizing Factual Inconsistency and Hallucination in Large Language Models
  43. Locally Optimal Descent for Dynamic Stepsize Scheduling
  44. Legal Requirements Analysis
  45. Language-guided Few-shot Semantic Segmentation
  46. Which Matters Most in Making Fund Investment Decisions? A Multi-granularity Graph Disentangled Learning Framework
  47. Challenges of Large Language Models for Mental Health Counseling
  48. A Cross Attention Approach to Diagnostic Explainability using Clinical Practice Guidelines for Depression
  49. Grammatical Error Correction via Mixed-Grained Weighted Training
  50. Perceptual Image Compression with Cooperative Cross-Modal Side Information
  51. Progressive Learning with Visual Prompt Tuning for Variable-Rate Image Compression
  52. Touring sampling with pushforward maps
  53. Exact Combinatorial Optimization with Temporo-Attentional Graph Neural Networks
  54. Stability and L2-penalty in Model Averaging
  55. HypUC: Hyperfine Uncertainty Calibration with Gradient-boosted Corrections for Reliable Regression on Imbalanced Electrocardiograms
  56. Enhancing Peak Assignment in 13C NMR Spectroscopy: A Novel Approach Using Multimodal Alignment
  57. Algorithmic Fairness Generalization under Covariate and Dependence Shifts Simultaneously
  58. Mechanical Characterization and Inverse Design of Stochastic Architected Metamaterials Using Neural Operators
  59. AdaTyper: Adaptive Semantic Column Type Detection
  60. Enhancing Intrusion Detection In Internet Of Vehicles Through Federated Learning
  61. Evidential Active Recognition: Intelligent and Prudent Open-World Embodied Perception
  62. DaG LLM ver 1.0: Pioneering Instruction-Tuned Language Modeling for Korean NLP
  63. Scalable AI Generative Content for Vehicular Network Semantic Communication
  64. Dynamic Compositional Graph Convolutional Network for Efficient Composite Human Motion Prediction
  65. Detection and Identification Accuracy of PCA-Accelerated Real-Time Processing of Hyperspectral Imagery
  66. GS-Pose: Category-Level Object Pose Estimation via Geometric and Semantic Correspondence
  67. Learning Hierarchical Polynomials with Three-Layer Neural Networks
  68. Archiving Body Movements: Collective Generation of Chinese Calligraphy
  69. A Unified Framework for Fair Spectral Clustering With Effective Graph Learning
  70. Learning Optimal and Fair Policies for Online Allocation of Scarce Societal Resources from Data Collected in Deployment
  71. Extraction of n = 0 pick-up by locked mode detectors based on neural networks in J-TEXT
  72. Transformer-based Named Entity Recognition in Construction Supply Chain Risk Management in Australia
  73. 3D-MIR: A Benchmark and Empirical Study on 3D Medical Image Retrieval in Radiology
  74. Towards Transferable Multi-modal Perception Representation Learning for Autonomy: NeRF-Supervised Masked AutoEncoder
  75. On Principles of Emergent Organization
  76. Security and Privacy Challenges in Deep Learning Models
  77. OASIS: Offsetting Active Reconstruction Attacks in Federated Learning