mlsanityData to 14 Oct 2026

Papers

New on arXiv

Sat 6 May 2023

98 papers

  1. Structure-CLIP: Towards Scene Graph Knowledge to Enhance Multi-modal Structured RepresentationsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  2. A Latent Diffusion Model for Protein Structure GenerationDiffusion models → Flow matching, time series and science
  3. Efficient and Degree-Guided Graph Generation via Discrete Diffusion ModelingDiffusion models → Flow matching, time series and science
  4. Plan-and-Solve Prompting: Improving Zero-Shot Chain-of-Thought Reasoning by Large Language ModelsLLM reasoning → Prompting and chain-of-thought reasoning
  5. Exploring One-shot Semi-supervised Federated Learning with A Pre-trained Diffusion ModelDiffusion models → Robustness, privacy and adversarial aspects
  6. Diffusion-NAT: Self-Prompting Discrete Diffusion for Non-Autoregressive Text GenerationDiffusion models → Discrete and text diffusion
  7. AADiff: Audio-Aligned Video Synthesis with Text-to-Image DiffusionDiffusion models → Audio, speech and music
  8. Replicating Complex Dialogue Policy of Humans via Offline Imitation Learning with Supervised RegularizationOffline RL and imitation learning from data → Language-conditioned policies and VLAs
  9. Towards Prompt-robust Face Privacy Protection via Adversarial Decoupling Augmentation FrameworkDiffusion models → Robustness, privacy and adversarial aspects
  10. Structural and Statistical Texture Knowledge Distillation for Semantic SegmentationKnowledge distillation → Detection and dense prediction distillation
  11. Improved Techniques for Maximum Likelihood Estimation for Diffusion ODEsDiffusion models → Diffusion foundations and sampling
  12. DocDiff: Document Enhancement via Residual Diffusion ModelsDiffusion models → Inverse problems and image restoration
  13. Simulation and Prediction of Countercurrent Spontaneous Imbibition at Early and Late Times Using Physics-Informed Neural Networks
  14. Detecting Concept Drift for the reliability prediction of Software Defects using Instance Interpretation
  15. Analysis of Climate Campaigns on Social Media using Bayesian Model Averaging
  16. Accelerate Langevin Sampling with Birth-Death Process and Exploration Component
  17. Two to Five Truths in Non-Negative Matrix Factorization
  18. TASTY: A Transformer based Approach to Space and Time complexity
  19. Efficient information recovery from Pauli noise via classical shadow
  20. Controllable Mixed-Initiative Dialogue Generation through Prompting
  21. Bounding the Invertibility of Privacy-preserving Instance Encoding using Fisher Information
  22. Transformer-Based Hierarchical Clustering for Brain Network Analysis
  23. Maintaining Stability and Plasticity for Predictive Churn Reduction
  24. Artificial Neuropsychology: Are Large Language Models Developing Executive Functions?
  25. Learning Mixtures of Gaussians with Censored Data
  26. Transform-Equivariant Consistency Learning for Temporal Sentence Grounding
  27. Exploring Human-Like Translation Strategy with Large Language Models
  28. The Fundamental Limits of Structure-Agnostic Functional Estimation
  29. DMF-TONN: Direct Mesh-free Topology Optimization using Neural Networks
  30. On the Usage of Continual Learning for Out-of-Distribution Generalization in Pre-trained Language Models of Code
  31. "When Words Fail, Emojis Prevail": Generating Sarcastic Utterances with Emoji Using Valence Reversal and Semantic Incongruity
  32. Leveraging Semantic Relationships to Prioritise Indicators of Compromise in Additive Manufacturing Systems
  33. Rhetorical Role Labeling of Legal Documents using Transformers and Graph Neural Networks
  34. Symbolic Regression on FPGAs for Fast Machine Learning Inference
  35. Gradient Leakage Defense with Key-Lock Module for Federated Learning
  36. An improved regret analysis for UCB-N and TS-N
  37. Self-Edit: Fault-Aware Code Editor for Code Generation
  38. Efficient Learning for Selecting Top-m Context-Dependent Designs
  39. A Minimal Approach for Natural Language Action Space in Text-based Games
  40. Robust Tensor CUR Decompositions: Rapid Low-Tucker-Rank Tensor Recovery with Sparse Corruption
  41. SANTA: Separate Strategies for Inaccurate and Incomplete Annotation Noise in Distantly-Supervised Named Entity Recognition
  42. PointCMP: Contrastive Mask Prediction for Self-supervised Learning on Point Cloud Videos
  43. Explaining RL Decisions with Trajectories
  44. The Best Defense is Attack: Repairing Semantics in Textual Adversarial Examples
  45. Semi-Asynchronous Federated Edge Learning Mechanism via Over-the-air Computation
  46. A Blockchain-based Platform for Reliable Inference and Training of Large-Scale Models
  47. Decentralised Semi-supervised Onboard Learning for Scene Classification in Low-Earth Orbit
  48. Science and Technology Ontology: A Taxonomy of Emerging Topics
  49. SST-ReversibleNet: Reversible-prior-based Spectral-Spatial Transformer for Efficient Hyperspectral Image Reconstruction
  50. Actively Discovering New Slots for Task-oriented Conversation
  51. Degradation-Noise-Aware Deep Unfolding Transformer for Hyperspectral Image Denoising
  52. Echoes: Unsupervised Debiasing via Pseudo-bias Labeling in an Echo Chamber
  53. Refining the Responses of LLMs by Themselves
  54. Wasserstein-Fisher-Rao Embedding: Logical Query Embeddings with Local Comparison and Global Transport
  55. A Sea-Land Clutter Classification Framework for Over-the-Horizon-Radar Based on Weighted Loss Semi-supervised GAN
  56. Weighted Point Cloud Normal Estimation
  57. Electromyography Signal Classification Using Deep Learning
  58. Towards a Simple Framework of Skill Transfer Learning for Robotic Ultrasound-guidance Procedures
  59. ANTONIO: Towards a Systematic Method of Generating NLP Benchmarks for Verification
  60. Dual Degradation Representation for Joint Deraining and Low-Light Enhancement in the Dark
  61. LEO: Generative Latent Image Animator for Human Video Synthesis
  62. Multi-object Video Generation from Single Frame Layouts
  63. Pre-training Language Model as a Multi-perspective Course Learner
  64. Unlocking the Power of GANs in Non-Autoregressive Text Generation
  65. DiscoPrompt: Path Prediction Prompt Tuning for Implicit Discourse Relation Recognition
  66. Adaptive loose optimization for robust question answering
  67. NER-to-MRC: Named-Entity Recognition Completely Solving as Machine Reading Comprehension
  68. Feature Chirality in Deep Learning Models
  69. Beyond the Model: Data Pre-processing Attack to Deep Learning Models in Android Apps
  70. Beyond Rule-based Named Entity Recognition and Relation Extraction for Process Model Generation from Natural Language Text
  71. Machine-Learning-Based Classification of GPS Signal Reception Conditions Using a Dual-Polarized Antenna in Urban Areas
  72. Learning Action Embeddings for Off-Policy Evaluation
  73. Label-Free Multi-Domain Machine Translation with Stage-wise Training
  74. HACMan: Learning Hybrid Actor-Critic Maps for 6D Non-Prehensile Manipulation
  75. Adam-family Methods for Nonsmooth Optimization with Convergence Guarantees
  76. Residual Prompt Tuning: Improving Prompt Tuning with Residual Reparameterization
  77. Annotation-efficient learning for OCT segmentation
  78. Revisiting Lightweight Compiler Provenance Recovery on ARM Binaries
  79. An Overview of AI and Blockchain Integration for Privacy-Preserving
  80. Trajectory-oriented optimization of stochastic epidemiological models
  81. Active Continual Learning: On Balancing Knowledge Retention and Learnability
  82. Automated Spatio-Temporal Graph Contrastive Learning
  83. DBAT: Dynamic Backward Attention Transformer for Material Segmentation with Cross-Resolution Patches
  84. HateMM: A Multi-Modal Dataset for Hate Video Classification
  85. Variational Nonlinear Kalman Filtering with Unknown Process Noise Covariance
  86. White Matter Hyperintensities Segmentation Using Probabilistic TransUNet
  87. Listen to Look into the Future: Audio-Visual Egocentric Gaze Anticipation
  88. Prompt What You Need: Enhancing Segmentation in Rainy Scenes with Anchor-based Prompting
  89. Synthesizing PET images from High-field and Ultra-high-field MR images Using Joint Diffusion Attention Model
  90. Rethinking Class Imbalance in Machine Learning
  91. NL-CS Net: Deep Learning with Non-Local Prior for Image Compressive Sensing
  92. Twin support vector quantile regression
  93. Approximation by non-symmetric networks for cross-domain learning
  94. Energy-Latency Attacks to On-Device Neural Networks via Sponge Poisoning
  95. On High-dimensional and Low-rank Tensor Bandits
  96. SINCERE: Sequential Interaction Networks representation learning on Co-Evolving RiEmannian manifolds
  97. Fairness in Image Search: A Study of Occupational Stereotyping in Image Retrieval and its Debiasing
  98. NorBench -- A Benchmark for Norwegian Language Models