mlsanityData to 14 Oct 2026

Papers

New on arXiv

Sat 9 Sep 2023

97 papers

  1. Towards Robust Model Watermark via Reducing Parametric VulnerabilityLLM safety and security → Watermarking generated content and models
  2. A Review on Robot Manipulation Methods in Human-Robot InteractionsOffline RL and imitation learning from data → Robot manipulation imitation learning
  3. Unified Language-Vision Pretraining in LLM with Dynamic Discrete Visual TokenizationLLM reasoning → Multimodal reasoning
  4. Exploring Large Language Models for Communication Games: An Empirical Study on WerewolfWorld models → World models for language agents
  5. Reducing the False Positive Rate Using Bayesian Inference in Autonomous Driving Perception
  6. Beyond Traditional Teaching: The Potential of Large Language Models and Chatbots in Graduate Engineering Education
  7. Towards LLM-based Autograding for Short Textual Answers
  8. Recall-driven Precision Refinement: Unveiling Accurate Fall Detection using LSTM
  9. Finding Influencers in Complex Networks: An Effective Deep Reinforcement Learning Approach
  10. Verifiable Reinforcement Learning Systems via Compositionality
  11. A Fast Algorithm for Moderating Critical Nodes via Edge Removal
  12. Evaluating Chatbots to Promote Users' Trust -- Practices and Open Problems
  13. Good-looking but Lacking Faithfulness: Understanding Local Explanation Methods through Trend-based Testing
  14. Gromov-Hausdorff Distances for Comparing Product Manifolds of Model Spaces
  15. MultiCaM-Vis: Visual Exploration of Multi-Classification Model with High Number of Classes
  16. SHAPE: A Sample-adaptive Hierarchical Prediction Network for Medication Recommendation
  17. ConvFormer: Plug-and-Play CNN-Style Transformers for Improving Medical Image Segmentation
  18. How to Evaluate Semantic Communications for Images with ViTScore Metric?
  19. Semi-supervised Instance Segmentation with a Learned Shape Prior
  20. SortedAP: Rethinking evaluation metrics for instance segmentation
  21. Symplectic Structure-Aware Hamiltonian (Graph) Embeddings
  22. A Gentle Introduction to Gradient-Based Optimization and Variational Inequalities for Machine Learning
  23. Approximating ReLU on a Reduced Ring for Efficient MPC-based Private Inference
  24. Distributional Data Augmentation Methods for Low Resource Language
  25. Approximation Results for Gradient Descent trained Neural Networks
  26. Reverse-Engineering Decoding Strategies Given Blackbox Access to a Language Generation System
  27. AmbientFlow: Invertible generative models from incomplete, noisy measurements
  28. Speech Emotion Recognition with Distilled Prosodic and Linguistic Affect Representations
  29. Leveraging Large Language Models for Exploiting ASR Uncertainty
  30. AnyPose: Anytime 3D Human Pose Forecasting via Neural Ordinary Differential Equations
  31. HAct: Out-of-Distribution Detection with Neural Net Activation Histograms
  32. Neural Semantic Surface Maps
  33. Global Convergence of Receding-Horizon Policy Search in Learning Estimator Designs
  34. Neurons in Large Language Models: Dead, N-gram, Positional
  35. Few-Shot Medical Image Segmentation via a Region-enhanced Prototypical Transformer
  36. Correcting sampling biases via importance reweighting for spatial modeling
  37. FaNS: a Facet-based Narrative Similarity Metric
  38. Non-linear dimension reduction in factor-augmented vector autoregressions
  39. ABC Easy as 123: A Blind Counter for Exemplar-Free Multi-Class Class-agnostic Counting
  40. Detecting Violations of Differential Privacy for Quantum Algorithms
  41. Speech2Lip: High-fidelity Speech to Lip Generation by Learning from a Short Video
  42. Neural Latent Geometry Search: Product Manifold Inference via Gromov-Hausdorff-Informed Bayesian Optimization
  43. Timely Fusion of Surround Radar/Lidar for Object Detection in Autonomous Driving Systems
  44. Towards Real-World Burst Image Super-Resolution: Benchmark and Method
  45. CPMR: Context-Aware Incremental Sequential Recommendation with Pseudo-Multi-Task Learning
  46. TMComposites: Plug-and-Play Collaboration Between Specialized Tsetlin Machines
  47. VeRi3D: Generative Vertex-based Radiance Fields for 3D Controllable Human Image Synthesis
  48. A Full-fledged Commit Message Quality Checker Based on Machine Learning
  49. Latent Spatiotemporal Adaptation for Generalized Face Forgery Video Detection
  50. MMHQA-ICL: Multimodal In-context Learning for Hybrid Question Answering over Text, Tables and Images
  51. Stochastic Gradient Descent outperforms Gradient Descent in recovering a high-dimensional signal in a glassy energy landscape
  52. IRCNN+: An Enhanced Iterative Residual Convolutional Neural Network for Non-stationary Signal Decomposition
  53. Latent Degradation Representation Constraint for Single Image Deraining
  54. SeaEval for Multilingual Foundation Models: From Cross-Lingual Alignment to Cultural Reasoning
  55. Visual Material Characteristics Learning for Circular Healthcare
  56. AudRandAug: Random Image Augmentations for Audio Classification
  57. A Comprehensive Survey on Deep Learning Techniques in Educational Data Mining
  58. RR-CP: Reliable-Region-Based Conformal Prediction for Trustworthy Medical Image Classification
  59. Probabilistic Triangulation for Uncalibrated Multi-View 3D Human Pose Estimation
  60. A Novel Training Framework for Physics-informed Neural Networks: Towards Real-time Applications in Ultrafast Ultrasound Blood Flow Imaging
  61. Deep Video Restoration for Under-Display Camera
  62. Mirror-Aware Neural Humans
  63. When to Learn What: Model-Adaptive Data Augmentation Curriculum
  64. Affine Invariant Ensemble Transform Methods to Improve Predictive Uncertainty in Neural Networks
  65. Data Augmentation for Conversational AI
  66. Learning Spiking Neural Network from Easy to Hard task
  67. Towards Better Multi-modal Keyphrase Generation via Visual Entity Enhancement and Multi-granularity Image Noise Filtering
  68. A Spatiotemporal Deep Neural Network for Fine-Grained Multi-Horizon Wind Prediction
  69. TCGAN: Convolutional Generative Adversarial Network for Time Series Classification and Clustering
  70. Transitions in echo index and dependence on input repetitions
  71. EPA: Easy Prompt Augmentation on Large Language Models via Multiple Sources and Multiple Targets
  72. Frequency-Aware Self-Supervised Long-Tailed Learning
  73. Toward Reproducing Network Research Results Using Large Language Models
  74. Jade: A Differentiable Physics Engine for Articulated Rigid Bodies with Intersection-Free Frictional Contact
  75. UnitModule: A Lightweight Joint Image Enhancement Module for Underwater Object Detection
  76. Advantage Actor-Critic with Reasoner: Explaining the Agent's Behavior from an Exploratory Perspective
  77. Analysis of Disinformation and Fake News Detection Using Fine-Tuned Large Language Model
  78. A Spatial-Temporal Deformable Attention based Framework for Breast Lesion Detection in Videos
  79. Weak-PDE-LEARN: A Weak Form Based Approach to Discovering PDEs From Noisy, Limited Data
  80. Advancements in Upper Body Exoskeleton: Implementing Active Gravity Compensation with a Feedforward Controller
  81. Code-Style In-Context Learning for Knowledge-Based Question Answering
  82. Redundancy-Free Self-Supervised Relational Learning for Graph Clustering
  83. DeNoising-MOT: Towards Multiple Object Tracking with Severe Occlusions
  84. Embedding structure matters: Comparing methods to adapt multilingual vocabularies to new languages
  85. Flexible and Robust Counterfactual Explanations with Minimal Satisfiable Perturbations
  86. BiLMa: Bidirectional Local-Matching for Text-based Person Re-identification
  87. SSHNN: Semi-Supervised Hybrid NAS Network for Echocardiographic Image Segmentation
  88. Compact: Approximating Complex Activation Functions for Secure Computation
  89. FIAT: Fusing learning paradigms with Instruction-Accelerated Tuning
  90. MADLAD-400: A Multilingual And Document-Level Large Audited Dataset
  91. Progressive Feature Adjustment for Semi-supervised Learning from Pretrained Models
  92. Generation and Recombination for Multifocus Image Fusion with Free Number of Inputs
  93. Intelligent upper-limb exoskeleton integrated with soft wearable bioelectronics and deep-learning for human intention-driven strength augmentation based on sensory feedback
  94. Video and Synthetic MRI Pre-training of 3D Vision Architectures for Neuroimage Analysis
  95. Exploring Robust Features for Improving Adversarial Robustness
  96. Efficient Finetuning Large Language Models For Vietnamese Chatbot
  97. Towards Understanding Neural Collapse: The Effects of Batch Normalization and Weight Decay