mlsanityData to 14 Oct 2026

Papers

New on arXiv

Sat 25 Nov 2023

95 papers

  1. GPT4Video: A Unified Multimodal Large Language Model for lnstruction-Followed Understanding and Safety-Aware GenerationMultimodal LLMs / vision-language models → Video understanding with MLLMs
  2. Z^*: Zero-shot Style Transfer via Attention RearrangementDiffusion models → Image generation, text-to-image and editing
  3. LANS: A Layout-Aware Neural Solver for Plane Geometry ProblemLLM reasoning → Spatial and embodied reasoning
  4. Localizing Lying in Llama: Understanding Instructed Dishonesty on True-False Questions Through Prompting, Probing, and PatchingMechanistic interpretability → Probing deception, bias and beliefs
  5. Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large DatasetsWorld models → Video-generation world models and simulators +1
  6. Leveraging Diffusion Perturbations for Measuring Fairness in Computer VisionDiffusion models → Image generation, text-to-image and editing
  7. InstaStyle: Inversion Noise of a Stylized Image is Secretly a Style AdviserDiffusion models → Image generation, text-to-image and editing
  8. Point Cloud Pre-training with Diffusion ModelsDiffusion models → 3D, point cloud and scene generation
  9. Effective Backdoor Mitigation in Vision-Language Models Depends on the Pre-training ObjectiveMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness +1
  10. FreePIH: Training-Free Painterly Image Harmonization with Diffusion ModelDiffusion models → Image generation, text-to-image and editing
  11. GDTS: Goal-Guided Diffusion Model with Tree Sampling for Multi-Modal Pedestrian Trajectory PredictionDiffusion models → Diffusion and flow policies for robotics
  12. AutoEval-Video: An Automatic Benchmark for Assessing Large Vision Language Models in Open-Ended Video Question AnsweringMultimodal LLMs / vision-language models → Video understanding with MLLMs
  13. Resfusion: Denoising Diffusion Probabilistic Models for Image Restoration Based on Prior Residual NoiseDiffusion models → Inverse problems and image restoration
  14. Projected Off-Policy Q-Learning (POP-QL) for Stabilizing Offline Reinforcement LearningOffline RL and imitation learning from data → Offline RL algorithms
  15. Precision Agriculture: Crop Mapping using Machine Learning and Sentinel-2 Satellite Imagery
  16. A Hybrid SOM and K-means Model for Time Series Energy Consumption Clustering
  17. New Online Communities: Graph Deep Learning on Anonymous Voting Networks to Identify Sybils in Polycentric Governance
  18. Automatic Synthetic Data and Fine-grained Adaptive Feature Alignment for Composed Person Retrieval
  19. RandMSAugment: A Mixed-Sample Augmentation for Limited-Data Scenarios
  20. Elucidating and Overcoming the Challenges of Label Noise in Supervised Contrastive Learning
  21. Modelling wildland fire burn severity in California using a spatial Super Learner approach
  22. Enhancing Sentiment Analysis Results through Outlier Detection Optimization
  23. mvlearnR and Shiny App for multiview learning
  24. Aiming to Minimize Alcohol-Impaired Road Fatalities: Utilizing Fairness-Aware and Domain Knowledge-Infused Artificial Intelligence
  25. Testable Learning with Distribution Shift
  26. Can SAM recognize crops? Quantifying the zero-shot performance of a semantic segmentation foundation model on generating crop-type maps using satellite imagery for precision agriculture
  27. Multi-fidelity Constrained Optimization for Stochastic Black Box Simulators
  28. SwiftLearn: A Data-Efficient Training Method of Deep Learning Models using Importance Sampling
  29. NCL-SM: A Fully Annotated Dataset of Images from Human Skeletal Muscle Biopsies
  30. Everybody Needs a Little HELP: Explaining Graphs via Hierarchical Concepts
  31. UAE: Universal Anatomical Embedding on Multi-modality Medical Images
  32. Relevance feedback strategies for recall-oriented neural information retrieval
  33. Solving the Right Problem is Key for Translational NLP: A Case Study in UMLS Vocabulary Insertion
  34. Unbalancedness in Neural Monge Maps Improves Unpaired Domain Translation
  35. Speech-Based Blood Pressure Estimation with Enhanced Optimization and Incremental Clustering
  36. AugmentTRAJ: A framework for point-based trajectory data augmentation
  37. Fine-Grained Unsupervised Cross-Modality Domain Adaptation for Vestibular Schwannoma Segmentation
  38. Where2Start: Leveraging initial States for Robust and Sample-Efficient Reinforcement Learning
  39. A GPU-based Hydrodynamic Simulator with Boid Interactions
  40. X-Ray to CT Rigid Registration Using Scene Coordinate Regression
  41. Weakly-Supervised Audio-Visual Segmentation
  42. Multilingual self-supervised speech representations improve the speech recognition of low-resource African languages with codeswitching
  43. Mug-STAN: Adapting Image-Language Pretrained Models for General Video Understanding
  44. Introducing SSBD+ Dataset with a Convolutional Pipeline for detecting Self-Stimulatory Behaviours in Children using raw videos
  45. Accurate and interpretable drug-drug interaction prediction enabled by knowledge subgraph learning
  46. Automatically Finding and Categorizing Replication Studies
  47. Detection of developmental language disorder in Cypriot Greek children using a neural network algorithm
  48. Task adaption by biologically inspired stochastic comodulation
  49. Gradient Descent with Polyak's Momentum Finds Flatter Minima via Large Catapults
  50. Training a Hopfield Variational Autoencoder with Equilibrium Propagation
  51. MPCNN: A Novel Matrix Profile Approach for CNN-based Sleep Apnea Classification
  52. Low-latency Visual Previews of Large Synchrotron Micro-CT Datasets
  53. On-Device Soft Sensors: Real-Time Fluid Flow Estimation from Level Sensor Data
  54. Agent as Cerebrum, Controller as Cerebellum: Implementing an Embodied LMM-based Agent on Drones
  55. nlpBDpatriots at BLP-2023 Task 2: A Transfer Learning Approach to Bangla Sentiment Analysis
  56. nlpBDpatriots at BLP-2023 Task 1: A Two-Step Classification for Violence Inciting Text Detection in Bangla
  57. Double-Flow-based Steganography without Embedding for Image-to-Image Hiding
  58. Offensive Language Identification in Transliterated and Code-Mixed Bangla
  59. Occlusion Sensitivity Analysis with Augmentation Subspace Perturbation in Deep Feature Space
  60. E-CORE: Emotion Correlation Enhanced Empathetic Dialogue Generation
  61. VSCode: General Visual Salient and Camouflaged Object Detection with 2D Prompt Learning
  62. Adapter is All You Need for Tuning Visual Tasks
  63. Satellite-based feature extraction and multivariate time-series prediction of biotoxin contamination in shellfish
  64. Exploring Causal Learning through Graph Neural Networks: An In-depth Review
  65. Coordinate-Aware Modulation for Neural Fields
  66. View it like a radiologist: Shifted windows for deep learning augmentation of CT images
  67. SAME++: A Self-supervised Anatomical eMbeddings Enhanced medical image registration framework using stable sampling and regularized transformation
  68. Neural Network Based Approach to Recognition of Meteor Tracks in the Mini-EUSO Telescope Data
  69. Multi-task Planar Reconstruction with Feature Warping Guidance
  70. Incorporating granularity bias as the margin into contrastive loss for video captioning
  71. Eliminating Domain Bias for Federated Learning in Representation Space
  72. Segmentation of diagnostic tissue compartments on whole slide images with renal thrombotic microangiopathies (TMAs)
  73. Walking a Tightrope -- Evaluating Large Language Models in High-Risk Domains
  74. Selective Inference for Changepoint detection by Recurrent Neural Network
  75. Identification of morphological fingerprint in perinatal brains using quasi-conformal mapping and contrastive learning
  76. Vector-Quantized Prompt Learning for Paraphrase Generation
  77. OpenNet: Incremental Learning for Autonomous Driving Object Detection with Balanced Loss
  78. Robust Graph Neural Networks via Unbiased Aggregation
  79. One-Shot Transfer Learning for Nonlinear ODEs
  80. View-Based Luminance Mapping in Open Workplace
  81. Coordinate-based Neural Network for Fourier Phase Retrieval
  82. DECap: Towards Generalized Explicit Caption Editing via Diffusion Mechanism
  83. Faster Minimum Bayes Risk Decoding with Confidence-based Pruning
  84. Resolution- and Stimulus-agnostic Super-Resolution of Ultra-High-Field Functional MRI: Application to Visual Studies
  85. CUCL: Codebook for Unsupervised Continual Learning
  86. A latent linear model for nonlinear coupled oscillators on graphs
  87. Continual Referring Expression Comprehension via Dual Modular Memorization
  88. Support Vector Machine Implementation on MPI-CUDA and Tensorflow Framework
  89. Class Gradient Projection For Continual Learning
  90. LLM-Assisted Code Cleaning For Training Accurate Code Generators
  91. Parkinson's Disease Classification Using Contrastive Graph Cross-View Learning with Multimodal Fusion of SPECT Images and Clinical Features
  92. Code Search Debiasing:Improve Search Results beyond Overall Ranking Performance
  93. HyperDID: Hyperspectral Intrinsic Image Decomposition with Deep Feature Embedding
  94. Towards Scalable 3D Anomaly Detection and Localization: A Benchmark via 3D Anomaly Synthesis and A Self-Supervised Learning Network
  95. A unified framework for learning with nonlinear model classes from arbitrary linear samples