mlsanityData to 14 Oct 2026

Papers

New on arXiv

Sun 3 Sep 2023

95 papers

  1. RSDiff: Remote Sensing Image Generation from Text Using Diffusion ModelDiffusion models → Inverse problems and image restoration
  2. Diffusion Models with Deterministic Normalizing Flow PriorsDiffusion models → Diffusion foundations and sampling
  3. COMEDIAN: Self-Supervised Learning and Knowledge Distillation for Action Spotting using TransformersKnowledge distillation → General knowledge distillation methods
  4. BDC-Adapter: Brownian Distance Covariance for Better Vision-Language ReasoningLLM reasoning → Multimodal reasoning +1
  5. LoGoPrompt: Synthetic Text Images Can Be Good Visual Prompts for Vision-Language ModelsMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  6. EdaDet: Open-Vocabulary Object Detection Using Early Dense AlignmentMultimodal LLMs / vision-language models → Driving VLMs and open-vocabulary detection
  7. VGDiffZero: Text-to-image Diffusion Models Can Be Zero-shot Visual GroundersDiffusion models → Image generation, text-to-image and editing
  8. ArSDM: Colonoscopy Images Synthesis with Adaptive Refinement Semantic Diffusion ModelsDiffusion models → Medical imaging and segmentation
  9. A Study on the Implementation of Generative AI Services Using an Enterprise Data-Based LLM Application ArchitectureRetrieval-augmented generation → RAG pipeline design and evaluation
  10. Robust and Efficient Interference Neural Networks for Defending Against Adversarial Attacks in ImageNet
  11. Bias Testing and Mitigation in LLM-based Code Generation
  12. Mapping AI Arguments in Journalism Studies
  13. Traveling Waves Encode the Recent Past and Enhance Sequence Learning
  14. Generative Data Augmentation using LLMs improves Distributional Robustness in Question Answering
  15. Generative Social Choice
  16. Federated Orthogonal Training: Mitigating Global Catastrophic Forgetting in Continual Federated Learning
  17. MAP: Domain Generalization via Meta-Learning on Anatomy-Consistent Pseudo-Modalities
  18. FOR-instance: a UAV laser scanning benchmark dataset for semantic and instance segmentation of individual trees
  19. A Comparative Evaluation of FedAvg and Per-FedAvg Algorithms for Dirichlet Distributed Heterogeneous Data
  20. Bayesian inference of composition-dependent phase diagrams
  21. Deception Game: Closing the Safety-Learning Loop in Interactive Robot Autonomy
  22. SOAR: Scene-debiasing Open-set Action Recognition
  23. Multimodal Contrastive Learning with Hard Negative Sampling for Human Activity Recognition
  24. S2RF: Semantically Stylized Radiance Fields
  25. Large AI Model Empowered Multimodal Semantic Communications
  26. Modified Step Size for Enhanced Stochastic Gradient Descent: Convergence and Experiments
  27. Towards Generic Image Manipulation Detection with Weakly-Supervised Self-Consistency Learning
  28. Representations Matter: Embedding Modes of Large Language Models using Dynamic Mode Decomposition
  29. The Normal Distributions Indistinguishability Spectrum and its Application to Privacy-Preserving Machine Learning
  30. BodySLAM++: Fast and Tightly-Coupled Visual-Inertial Camera and Human Motion Tracking
  31. Generalizability and Application of the Skin Reflectance Estimate Based on Dichromatic Separation (SREDS)
  32. lfads-torch: A modular and extensible implementation of latent factor analysis via dynamical systems
  33. Saturn: An Optimized Data System for Large Model Deep Learning Workloads
  34. Siren's Song in the AI Ocean: A Survey on Hallucination in Large Language Models
  35. Implicit regularization of deep residual networks towards neural ODEs
  36. Physics-inspired Neural Networks for Parameter Learning of Adaptive Cruise Control Systems
  37. Spectral Adversarial MixUp for Few-Shot Unsupervised Domain Adaptation
  38. MAGMA: Music Aligned Generative Motion Autodecoder
  39. A Visual Interpretation-Based Self-Improved Classification System Using Virtual Adversarial Training
  40. A Survey on Service Route and Time Prediction in Instant Delivery: Taxonomy, Progress, and Prospects
  41. LogGPT: Exploring ChatGPT for Log-Based Anomaly Detection
  42. Pre-trained Neural Recommenders: A Transferable Zero-Shot Framework for Recommendation Systems
  43. Holistic Dynamic Frequency Transformer for Image Fusion and Exposure Correction
  44. Cognition-Mode Aware Variational Representation Learning Framework for Knowledge Tracing
  45. Logic of subjective probability
  46. FusionAI: Decentralized Training and Deploying LLMs with Massive Consumer-Level GPUs
  47. Deep Unfolding Convolutional Dictionary Model for Multi-Contrast MRI Super-resolution and Reconstruction
  48. End-to-End Learning on Multimodal Knowledge Graphs
  49. Symbolically integrating tensor networks over various random tensors by the second version of Python RTNI
  50. Spatial-temporal Vehicle Re-identification
  51. Noise robust speech emotion recognition with signal-to-noise ratio adapting speech enhancement
  52. An Asynchronous Linear Filter Architecture for Hybrid Event-Frame Cameras
  53. An Accurate Graph Generative Model with Tunable Features
  54. Large Language Models for Generative Recommendation: A Survey and Visionary Discussions
  55. Advances in machine-learning-based sampling motivated by lattice quantum chromodynamics
  56. FedFwd: Federated Learning without Backpropagation
  57. Interpretable Sequence Clustering
  58. Attention Where It Matters: Rethinking Visual Document Understanding with Selective Region Concentration
  59. Financial Fraud Detection using Quantum Graph Neural Networks
  60. AutoML-GPT: Large Language Model for AutoML
  61. AI driven B-cell Immunotherapy Design
  62. Double Clipping: Less-Biased Variance Reduction in Off-Policy Evaluation
  63. Quantitative Energy Prediction based on Carbon Emission Analysis by DPR Framework
  64. MedChatZH: a Better Medical Adviser Learns from Better Instructions
  65. Hybrid-Supervised Dual-Search: Leveraging Automatic Learning for Loss-free Multi-Exposure Image Fusion
  66. Acoustic-to-articulatory inversion for dysarthric speech: Are pre-trained self-supervised representations favorable?
  67. Solving Non-Rectangular Reward-Robust MDPs via Frequency Regularization
  68. AdvMono3D: Advanced Monocular 3D Object Detection with Depth-Aware Robust Adversarial Training
  69. Turn Fake into Real: Adversarial Head Turn Attacks Against Deepfake Detection
  70. CARNet: Collaborative Adversarial Resilience for Robust Underwater Image Enhancement and Perception
  71. M2HGCL: Multi-Scale Meta-Path Integrated Heterogeneous Graph Contrastive Learning
  72. Enhancing Infrared Small Target Detection Robustness with Bi-Level Adversarial Framework
  73. CoTDet: Affordance Knowledge Prompting for Task Driven Object Detection
  74. Face Clustering for Connection Discovery from Event Images
  75. Stabilize to Act: Learning to Coordinate for Bimanual Manipulation
  76. MILA: Memory-Based Instance-Level Adaptation for Cross-Domain Object Detection
  77. Chinese Text Recognition with A Pre-Trained CLIP-Like Model Through Image-IDS Aligning
  78. Tropical Geometric Tools for Machine Learning: the TML package
  79. Orientation-Independent Chinese Text Recognition in Scene Images
  80. UnsMOT: Unified Framework for Unsupervised Multi-Object Tracking with Geometric Topology Guidance
  81. Robust Adversarial Defense by Tensor Factorization
  82. Federated Few-shot Learning for Cough Classification with Edge Devices
  83. Muti-Stage Hierarchical Food Classification
  84. Towards Efficient Modeling and Inference in Multi-Dimensional Gaussian Process State-Space Models
  85. Spatial and Visual Perspective-Taking via View Rotation and Relation Reasoning for Embodied Reference Understanding
  86. Channel Attention Separable Convolution Network for Skin Lesion Segmentation
  87. Business Process Text Sketch Automation Generation Using Large Language Model
  88. Multidomain transformer-based deep learning for early detection of network intrusion
  89. Separable Hamiltonian Neural Networks
  90. MQENet: A Mesh Quality Evaluation Neural Network Based on Dynamic Graph Attention
  91. AB2CD: AI for Building Climate Damage Classification and Detection
  92. Semi-supervised 3D Video Information Retrieval with Deep Neural Network and Bi-directional Dynamic-time Warping Algorithm
  93. Integration of Vision-based Object Detection and Grasping for Articulated Manipulator in Lunar Conditions
  94. Efficient Curriculum based Continual Learning with Informative Subset Selection for Remote Sensing Scene Classification
  95. Distribution learning via neural differential equations: a nonparametric statistical perspective