mlsanityData to 14 Oct 2026

Papers

New on arXiv

Sat 22 Apr 2023

77 papers

  1. N2G: A Scalable Approach for Quantifying Interpretable Neuron Representations in Large Language ModelsMechanistic interpretability → Circuits and mechanistic analysis
  2. Boosting Theory-of-Mind Performance in Large Language Models via PromptingLLM alignment / RLHF / preference optimisation → Process reward models for reasoning
  3. Fast Diffusion Probabilistic Model Sampling through the lens of Backward Error AnalysisDiffusion models → Diffusion foundations and sampling
  4. Conditional Denoising Diffusion for Sequential RecommendationDiffusion models → Diffusion recommenders
  5. Pipeline MoE: A Flexible MoE Implementation with Pipeline ParallelismMixture-of-experts → Efficient MoE training and inference systems
  6. Lightweight Toxicity Detection in Spoken Language: A Transformer-based Approach for Edge DevicesKnowledge distillation → Knowledge distillation for LLMs
  7. Knowledge Distillation from 3D to Bird's-Eye-View for LiDAR Semantic SegmentationKnowledge distillation → Detection and dense prediction distillation
  8. Sequential Recommendation with Probabilistic Logical ReasoningLLM reasoning → LLM reasoning for recommendation
  9. On Accelerating Diffusion-Based Sampling Process via Improved Integration ApproximationDiffusion models → Diffusion foundations and sampling
  10. Lookahead Diffusion Probabilistic Models for Refining Mean EstimationDiffusion models → Diffusion foundations and sampling
  11. Identifying Appropriate Intellectual Property Protection Mechanisms for Machine Learning Models: A Systematization of Watermarking, Fingerprinting, Model Access, and AttacksLLM safety and security → Watermarking generated content and models
  12. Dialectical language model evaluation: An initial appraisal of the commonsense spatial reasoning abilities of LLMsLLM reasoning → Spatial and embodied reasoning
  13. "I'm" Lost in Translation: Pronoun Missteps in Crowdsourced Data Sets
  14. Transcending the "Male Code": Implicit Masculine Biases in NLP Contexts
  15. Can Voice Assistants Sound Cute? Towards a Model of Kawaii Vocalics
  16. Physics-guided generative adversarial network to learn physical models
  17. Vision Transformers, a new approach for high-resolution and large-scale mapping of canopy heights
  18. Understanding Lexical Biases when Identifying Gang-related Social Media Communications
  19. Weight-based Mask for Domain Adaptation
  20. LLM+P: Empowering Large Language Models with Optimal Planning Proficiency
  21. (Vector) Space is Not the Final Frontier: Product Search as Program Synthesis
  22. A Comparative Study of Pre-trained Speech and Audio Embeddings for Speech Emotion Recognition
  23. 3D-IntPhys: Towards More Generalized 3D-grounded Visual Intuitive Physics under Challenging Scenes
  24. Increasing the Scope as You Learn: Adaptive Bayesian Optimization in Nested Subspaces
  25. OmniLabel: A Challenging Benchmark for Language-Based Object Detection
  26. Recurrent Neural Networks and Long Short-Term Memory Networks: Tutorial and Survey
  27. Reinforcement Learning with an Abrupt Model Change
  28. An approach to extract information from academic transcripts of HUST
  29. Dilated-UNet: A Fast and Accurate Medical Image Segmentation Approach using a Dilated Transformer and U-Net Architecture
  30. Dehazing-NeRF: Neural Radiance Fields from Hazy Images
  31. Improving Stain Invariance of CNNs for Segmentation by Fusing Channel Attention and Domain-Adversarial Training
  32. Constructing a meta-learner for unsupervised anomaly detection
  33. Breaching FedMD: Image Recovery via Paired-Logits Inversion Attack
  34. Hyper-Laplacian Regularized Concept Factorization in Low-rank Tensor Space for Multi-view Clustering
  35. L3Cube-IndicSBERT: A simple approach for learning cross-lingual sentence representations using multilingual BERT
  36. Universal Adversarial Backdoor Attacks to Fool Vertical Federated Learning in Cloud-Edge Collaboration
  37. A Review of Deep Learning for Video Captioning
  38. SACANet: scene-aware class attention network for semantic segmentation of remote sensing images
  39. STNet: Spatial and Temporal feature fusion network for change detection in remote sensing images
  40. Detecting Spoilers in Movie Reviews with External Movie Knowledge and User Networks
  41. A bounded rationality account of dependency length minimization in Hindi
  42. The Devil is in the Upsampling: Architectural Decisions Made Simpler for Denoising with Deep Image Prior
  43. LaMP: When Large Language Models Meet Personalization
  44. SSN: Stockwell Scattering Network for SAR Image Change Detection
  45. Fast MRI Reconstruction via Edge Attention
  46. ML-based Approaches for Wireless NLOS Localization: Input Representations and Uncertainty Estimation
  47. Transformer-Based Language Model Surprisal Predicts Human Reading Times Best with About Two Billion Training Tokens
  48. Incomplete Multimodal Learning for Remote Sensing Data Fusion
  49. LiDAR2Map: In Defense of LiDAR-Based Semantic Map Construction Using Online Camera Distillation
  50. SimplyMime: A Control at Our Fingertips
  51. Stimulating student engagement with an AI board game tournament
  52. Unsupervised CD in satellite image time series by contrastive learning and feature tracking
  53. Towards Carbon-Neutral Edge Computing: Greening Edge AI by Harnessing Spot and Future Carbon Markets
  54. SAILER: Structure-aware Pre-trained Language Model for Legal Case Retrieval
  55. Detecting Political Opinions in Tweets through Bipartite Graph Analysis: A Skip Aggregation Graph Convolution Approach
  56. Detecting Adversarial Faces Using Only Real Face Self-Perturbations
  57. Learning Symbolic Representations Through Joint GEnerative and DIscriminative Training
  58. Single-stage Multi-human Parsing via Point Sets and Center-based Offsets
  59. Medium. Permeation: SARS-COV-2 Painting Creation by Generative Model
  60. Romanian Multiword Expression Detection Using Multilingual Adversarial Training and Lateral Inhibition
  61. NaviNeRF: NeRF-based 3D Representation Disentanglement by Latent Semantic Navigation
  62. Semantic Specialization for Knowledge-based Word Sense Disambiguation
  63. Differentially Private Synthetic Data Generation via Lipschitz-Regularised Variational Autoencoders
  64. Two Birds, One Stone: A Unified Framework for Joint Learning of Image and Video Style Transfers
  65. Input Augmentation with SAM: Boosting Medical Image Segmentation with Segmentation Foundation Model
  66. Self-supervised Learning by View Synthesis
  67. Understanding and Improving Feature Learning for Out-of-Distribution Generalization
  68. SAWU-Net: Spatial Attention Weighted Unmixing Network for Hyperspectral Images
  69. Spectral Normalization and Dual Contrastive Regularization for Image-to-Image Translation
  70. A Semi-Supervised Framework for Misinformation Detection
  71. Unmatched uncertainty mitigation through neural network supported model predictive control
  72. BiTrackGAN: Cascaded CycleGANs to Constraint Face Aging
  73. MAWSEO: Adversarial Wiki Search Poisoning for Illicit Online Promotion
  74. Nonverbal Cues in Human-Robot Interaction: A Communication Studies Perspective
  75. On the Identification of the Energy related Issues from the App Reviews
  76. VisiTherS: Visible-thermal infrared stereo disparity estimation of human silhouette
  77. Trust and Reliance in Consensus-Based Explanations from an Anti-Misinformation Agent