mlsanityData to 14 Oct 2026

Papers

New on arXiv

Sun 8 Sep 2024

110 papers

  1. GenCAD: Image-Conditioned Computer-Aided Design Generation with Transformer-Based Contrastive Representation and Diffusion PriorsDiffusion models → 3D, point cloud and scene generation
  2. STLLM-DF: A Spatial-Temporal Large Language Model with Diffusion for Enhanced Multi-Mode Traffic System ForecastingDiffusion models → Diffusion and flow policies for robotics
  3. Mamba-Enhanced Text-Audio-Video Alignment Network for Emotion Recognition in ConversationsState-space sequence models (S4, Mamba) → Speech and audio SSMs
  4. Seemingly Plausible Distractors in Multi-Hop Reasoning: Are Large Language Models Attentive Readers?LLM reasoning → Knowledge- and tool-augmented reasoning
  5. QuantFactor REINFORCE: Mining Steady Formulaic Alpha Factors with Variance-bounded REINFORCEDeep reinforcement learning methods → Adversarial robustness and RL in finance
  6. Diffusion-based Speech Enhancement with Schr"odinger Bridge and Symmetric Noise ScheduleDiffusion models → Audio, speech and music
  7. PIP: Detecting Adversarial Examples in Large Vision-Language Models via Attention Patterns of Irrelevant Probe QuestionsMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness
  8. An Analysis of Logit Learning with the r-Lambert FunctionOffline RL and imitation learning from data → Inverse reinforcement learning
  9. TF-Mamba: A Time-Frequency Network for Sound Source LocalizationState-space sequence models (S4, Mamba) → Speech and audio SSMs
  10. A Survey on Diffusion Models for Recommender SystemsDiffusion models → Diffusion recommenders
  11. InstInfer: In-Storage Attention Offloading for Cost-Effective Long-Context LLM InferenceEfficient LLM inference and serving → KV cache optimization
  12. Soft Actor-Critic with Beta Policy via Implicit Reparameterization GradientsDeep reinforcement learning methods → RL theory and sample complexity
  13. Explaining Human Comparisons using Alignment-Importance Heatmaps
  14. Evaluating Large Language Models with Tests of Spanish as a Foreign Language: Pass or Fail?
  15. Efficient Classification of Histopathology Images
  16. Expanding Expressivity in Transformer Models with M"obiusAttention
  17. Elastic On-Device LLM Service
  18. RAGent: Retrieval-based Access Control Policy Generation
  19. Evaluation of Tropical Cyclone Track and Intensity Forecasts from Artificial Intelligence Weather Prediction (AIWP) Models
  20. KModels: Unlocking AI for Business Applications
  21. Developing an Explainable Artificial Intelligent (XAI) Model for Predicting Pile Driving Vibrations in Bangkok's Subsoil
  22. Socially Responsible Data for Large Multilingual Language Models
  23. FedFT: Improving Communication Performance for Federated Learning with Frequency Space Transformation
  24. Empowering Bayesian Neural Networks with Functional Priors through Anchored Ensembling for Mechanics Surrogate Modeling Applications
  25. A Low-Computational Video Synopsis Framework with a Standard Dataset
  26. BBS: Bi-directional Bit-level Sparsity for Deep Learning Acceleration
  27. Comparison of Two Augmentation Methods in Improving Detection Accuracy of Hemarthrosis
  28. Exploring Intrinsic Language-specific Subspaces in Fine-tuning Multilingual Neural Machine Translation
  29. Synthetic Tabular Data Generation for Class Imbalance and Fairness: A Comparative Study
  30. ICML Topological Deep Learning Challenge 2024: Beyond the Graph Domain
  31. Influence-based Attributions can be Manipulated
  32. Low Latency Transformer Inference on FPGAs for Physics Applications with hls4ml
  33. SEF: A Method for Computing Prediction Intervals by Shifting the Error Function in Neural Networks
  34. A Survey on Mixup Augmentations and Beyond
  35. Lung-DETR: Deformable Detection Transformer for Sparse Lung Nodule Anomaly Detection
  36. Interactive Machine Teaching by Labeling Rules and Instances
  37. Bellwether Trades: Characteristics of Trades influential in Predicting Future Price Movements in Markets
  38. Generalization of Geometric Graph Neural Networks with Lipschitz Loss Functions
  39. Learning to Classify Quantum Phases of Matter with a Few Measurements
  40. Sliding-Window Thompson Sampling for Non-Stationary Settings
  41. Insights from Benchmarking Frontier Language Models on Web App Code Generation
  42. Advanced Machine Learning Framework for Efficient Plant Disease Prediction
  43. Exploring Fungal Morphology Simulation and Dynamic Light Containment from a Graphics Generation Perspective
  44. Stress Predictions in Polycrystal Plasticity using Graph Neural Networks with Subgraph Training
  45. CD-NGP: A Fast Scalable Continual Representation for Dynamic Scenes
  46. Can OOD Object Detectors Learn from Foundation Models?
  47. Inference for Large Scale Regression Models with Dependent Errors
  48. Image color consistency in datasets: the Smooth-TPS3D method
  49. OneGen: Efficient One-Pass Unified Generation and Retrieval for LLMs
  50. Ultron: Enabling Temporal Geometry Compression of 3D Mesh Sequences using Temporal Correspondence and Mesh Deformation
  51. Better Spanish Emotion Recognition In-the-wild: Bringing Attention to Deep Spectrum Voice Analysis
  52. TanDepth: Leveraging Global DEMs for Metric Monocular Depth Estimation in UAVs
  53. Revisiting Trace Norm Minimization for Tensor Tucker Completion: A Direct Multilinear Rank Learning Approach
  54. READoc: A Unified Benchmark for Realistic Document Structured Extraction
  55. MHS-STMA: Multimodal Hate Speech Detection via Scalable Transformer-Based Multilevel Attention Framework
  56. Imputation of Time-varying Edge Flows in Graphs by Multilinear Kernel Regression and Manifold Learning
  57. Hate Content Detection via Novel Pre-Processing Sequencing and Ensemble Methods
  58. PdfTable: A Unified Toolkit for Deep Learning-Based Table Extraction
  59. PMT: Progressive Mean Teacher via Exploring Temporal Consistency for Semi-Supervised Medical Image Segmentation
  60. WaterSeeker: Pioneering Efficient Detection of Watermarked Segments in Large Documents
  61. EdaCSC: Two Easy Data Augmentation Methods for Chinese Spelling Correction
  62. MaxCutPool: differentiable feature-aware Maxcut for pooling in graph neural networks
  63. DreamMapping: High-Fidelity Text-to-3D Generation via Variational Distribution Mapping
  64. Time-Distributed Feature Learning for Internet of Things Network Traffic Classification
  65. The first Cadenza challenges: using machine learning competitions to improve music for listeners with a hearing loss
  66. Leveraging WaveNet for Dynamic Listening Head Modeling from Speech
  67. Transformer with Leveraged Masked Autoencoder for video-based Pain Assessment
  68. Adaptive k-nearest neighbor classifier based on the local estimation of the shape operator
  69. From Computation to Consumption: Exploring the Compute-Energy Link for Training and Testing Neural Networks for SED Systems
  70. A General Framework for Clustering and Distribution Matching with Bandit Feedback
  71. Lepskii Principle for Distributed Kernel Ridge Regression
  72. Sight View Constraint for Robust Point Cloud Registration
  73. Dynamic Demand Management for Parcel Lockers
  74. Machine Learning-Based Prediction of Key Genes Correlated to the Subretinal Lesion Severity in a Mouse Model of Age-Related Macular Degeneration
  75. Unsupervised Multimodal 3D Medical Image Registration with Multilevel Correlation Balanced Optimization
  76. Deep Generic Representations for Domain-Generalized Anomalous Sound Detection
  77. Exploring WavLM Back-ends for Speech Spoofing and Deepfake Detection
  78. Unified theoretical guarantees for stability, consistency, and convergence in neural PDE solvers from non-IID data to physics-informed networks
  79. GUI Test Migration via Abstraction and Concretization
  80. Deep Self-Cleansing for Medical Image Segmentation with Noisy Labels
  81. Stability and convergence analysis of AdaGrad for non-convex optimization via novel stopping time-based techniques
  82. Sequential Recommendation via Adaptive Robust Attention with Multi-dimensional Embeddings
  83. Vision-fused Attack: Advancing Aggressive and Stealthy Adversarial Text against Neural Machine Translation
  84. Audio-Guided Fusion Techniques for Multimodal Emotion Analysis
  85. Towards Patronizing and Condescending Language in Chinese Videos: A Multimodal Dataset and Detector
  86. A Pair Programming Framework for Code Generation via Multi-Plan Exploration and Feedback-Driven Refinement
  87. Visual Grounding with Multi-modal Conditional Adaptation
  88. A Double Tracking Method for Optimization with Decentralized Generalized Orthogonality Constraints
  89. Learning nonnegative matrix factorizations from compressed data
  90. DynamicFL: Federated Learning with Dynamic Communication Resource Allocation
  91. 2DSig-Detect: a semi-supervised framework for anomaly detection on image data using 2D-signatures
  92. Multi-V2X: A Large Scale Multi-modal Multi-penetration-rate Dataset for Cooperative Perception
  93. RCBEVDet++: Toward High-accuracy Radar-Camera Fusion 3D Perception Network
  94. Time-independent Spiking Neuron via Membrane Potential Estimation for Efficient Spiking Neural Networks
  95. Enhancing Convolutional Neural Networks with Higher-Order Numerical Difference Methods
  96. HYDRA: Hybrid Data Multiplexing and Run-time Layer Configurable DNN Accelerator
  97. PatchAlign:Fair and Accurate Skin Disease Image Classification by Alignment with Clinical Labels
  98. Balancing Security and Accuracy: A Novel Federated Learning Approach for Cyberattack Detection in Blockchain Networks
  99. Natias: Neuron Attribution based Transferable Image Adversarial Steganography
  100. Evaluation of Google Translate for Mandarin Chinese translation using sentiment and semantic analysis
All 110
  1. GS-PT: Exploiting 3D Gaussian Splatting for Comprehensive Point Cloud Understanding via Self-supervised Learning
  2. A foundation model enpowered by a multi-modal prompt engine for universal seismic geobody interpretation across surveys
  3. DDNet: Deformable Convolution and Dense FPN for Surface Defect Detection in Recycled Books
  4. Evaluating Neural Networks Architectures for Spring Reverb Modelling
  5. Deep Bayesian Active Learning-to-Rank with Relative Annotation for Estimation of Ulcerative Colitis Severity
  6. Attention-Based Efficient Breath Sound Removal in Studio Audio Recordings
  7. Fast Deep Predictive Coding Networks for Videos Feature Extraction without Labels
  8. UMOD: A Novel and Effective Urban Metro Origin-Destination Flow Prediction Method
  9. An Analog and Digital Hybrid Attention Accelerator for Transformers with Charge-based In-memory Computing
  10. Anomaly Detection for Real-World Cyber-Physical Security using Quantum Hybrid Support Vector Machines