mlsanityData to 14 Oct 2026

Papers

New on arXiv

Tue 9 May 2023

230 papers

  1. Fine-tuning Language Models with Generative Adversarial Reward ModellingLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
  2. A Review of Vision-Language Models and their Performance on the Hateful Memes ChallengeMultimodal LLMs / vision-language models → Social bias and fairness in VLMs
  3. DeepTextMark: A Deep Learning-Driven Text Watermarking Approach for Identifying Large Language Model Generated TextLLM safety and security → Watermarking generated content and models
  4. DifFIQA: Face Image Quality Assessment Using Denoising Diffusion Probabilistic ModelsDiffusion models → Inverse problems and image restoration
  5. Vision-Language Models in Remote Sensing: Current Progress and Future TrendsMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  6. BadCS: A Backdoor Attack Framework for Code searchLLM safety and security → Backdoor and data poisoning attacks
  7. Exploiting Pseudo Image Captions for Multimodal SummarizationMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  8. Style-A-Video: Agile Diffusion for Arbitrary Text-based Video Style TransferDiffusion models → Image generation, text-to-image and editing
  9. Echo from noise: synthetic ultrasound image generation using diffusion models for real image segmentationDiffusion models → Medical imaging and segmentation
  10. Large Language Models Need Holistically Thought in Medical Conversational QALLM reasoning → Clinical and biomedical applications
  11. COKE: A Cognitive Knowledge Graph for Machine Theory of MindWorld models → World models for language agents
  12. Turning Privacy-preserving Mechanisms against Federated LearningLLM safety and security → Federated unlearning and poisoning
  13. DynamicKD: An Effective Knowledge Distillation via Dynamic Entropy Correction-Based Distillation for Gap OptimizingKnowledge distillation → General knowledge distillation methods
  14. Multi-Teacher Knowledge Distillation For Text Image Machine TranslationKnowledge distillation → Knowledge distillation for LLMs
  15. COLA: Contextualized Commonsense Causal Reasoning from the Causal Inference PerspectiveLLM reasoning → Causal reasoning in LLMs
  16. SUR-adapter: Enhancing Text-to-Image Pre-trained Diffusion Models with Large Language ModelsDiffusion models → Image generation, text-to-image and editing
  17. MoT: Memory-of-Thought Enables ChatGPT to Self-ImproveLLM reasoning → Test-time compute and efficient thinking +1
  18. SRIL: Selective Regularization for Class-Incremental LearningKnowledge distillation → Distillation for continual learning
  19. A New Era of Mobility: Exploring Digital Twin Applications in Autonomous Vehicular Systems
  20. Zero-shot personalized lip-to-speech synthesis with face image based voice control
  21. Exploring the Efficacy of ChatGPT in Analyzing Student Teamwork Feedback with an Existing Taxonomy
  22. Self-Supervised Learning for Point Clouds Data: A Survey
  23. Quantum Machine Learning for Malware Classification
  24. Copula Variational LSTM for High-dimensional Cross-market Multivariate Dependence Modeling
  25. Temporal and Heterogeneous Graph Neural Network for Financial Time Series Prediction
  26. QVoice: Arabic Speech Pronunciation Learning Application
  27. Hawkes Process Based on Controlled Differential Equations
  28. Pseudo-Hamiltonian system identification
  29. Convex Quaternion Optimization for Signal Processing: Theory and Applications
  30. FedPDD: A Privacy-preserving Double Distillation Framework for Cross-silo Federated Recommendation
  31. Mitigating Bias in Text Classification via Prompt-Based Text Transformation
  32. StarCoder: may the source be with you!
  33. EdgeNet : Encoder-decoder generative Network for Auction Design in E-commerce Online Advertising
  34. The Vault: A Comprehensive Multilingual Dataset for Advancing Code Understanding and Generation
  35. Alleviating Over-smoothing for Unsupervised Sentence Representation
  36. Change Detection Methods for Remote Sensing in the Last Decade: A Comprehensive Review
  37. Assessment of Reinforcement Learning Algorithms for Nuclear Power Plant Fuel Optimization
  38. Towards an Automatic Optimisation Model Generator Assisted with Generative Pre-trained Transformer
  39. Stochastic Texture Filtering
  40. On the Information Capacity of Nearest Neighbor Representations
  41. Even Small Correlation and Diversity Shifts Pose Dataset-Bias Issues
  42. Segment Anything Model (SAM) Enhanced Pseudo Labels for Weakly Supervised Semantic Segmentation
  43. Seeing double with a multifunctional reservoir computer
  44. Fully Bayesian VIB-DeepSSM
  45. Testing for Overfitting
  46. Unsupervised Domain Adaptation for Medical Image Segmentation via Feature-space Density Matching
  47. Regular Splitting Graph Network for 3D Human Pose Estimation
  48. Comprehensive Dataset of Synthetic and Manipulated Overhead Imagery for Development and Evaluation of Forensic Tools
  49. Enhancing Gappy Speech Audio Signals with Generative Adversarial Networks
  50. Learning to Parallelize with OpenMP by Augmented Heterogeneous AST Representation
  51. Multi-Object Self-Supervised Depth Denoising
  52. Visual Place Recognition with Low-Resolution Images
  53. Instant-NeRF: Instant On-Device Neural Radiance Field Training via Algorithm-Accelerator Co-Designed Near-Memory Processing
  54. On the average-case complexity of learning output distributions of quantum circuits
  55. Reducing the Cost of Cycle-Time Tuning for Real-World Policy Optimization
  56. Ranking & Reweighting Improves Group Distributional Robustness
  57. When and What to Ask Through World States and Text Instructions: IGLU NLP Challenge Solution
  58. A Systematic Literature Review on Hardware Reliability Assessment Methods for Deep Neural Networks
  59. Multilevel Sentence Embeddings for Personality Prediction
  60. Message Passing Neural Networks for Traffic Forecasting
  61. Graph-Based Reductions for Parametric and Weighted MDPs
  62. DOCTOR: A Multi-Disease Detection Continual Learning Framework Based on Wearable Medical Sensors
  63. Duke Spleen Data Set: A Publicly Available Spleen MRI and CT dataset for Training Segmentation
  64. Enhancing Clinical Predictive Modeling through Model Complexity-Driven Class Proportion Tuning for Class Imbalanced Data: An Empirical Study on Opioid Overdose Prediction
  65. CodeIE: Large Code Generation Models are Better Few-Shot Information Extractors
  66. Language models can generate molecules, materials, and protein binding sites directly in three dimensions as XYZ, CIF, and PDB files
  67. DexArt: Benchmarking Generalizable Dexterous Manipulation with Articulated Objects
  68. An Evaluation and Ranking of Different Voting Schemes for Improved Visual Place Recognition
  69. Effects of data time lag in a decision-making system using machine learning for pork price prediction
  70. UAdam: Unified Adam-Type Algorithmic Framework for Non-Convex Stochastic Optimization
  71. 2 * n is better than n2: Decomposing Event Coreference Resolution into Two Tractable Problems
  72. Policy Gradient Methods in the Presence of Symmetries and State Abstractions
  73. ImageBind: One Embedding Space To Bind Them All
  74. InternGPT: Solving Vision-Centric Tasks by Interacting with ChatGPT Beyond Language
  75. ShapeCoder: Discovering Abstractions for Visual Programs from Unstructured Primitives
  76. TidyBot: Personalized Robot Assistance with Large Language Models
  77. Could AI be the Great Filter? What Astrobiology can Teach the Intelligence Community about Anthropogenic Risks
  78. SwinIA: Self-Supervised Blind-Spot Image Denoising without Convolutions
  79. Predicting Cardiovascular Disease Risk using Photoplethysmography and Deep Learning
  80. Towards Building the Federated GPT: Federated Instruction Tuning
  81. A duality framework for analyzing random feature and two-layer neural networks
  82. Representation Learning for Person or Entity-centric Knowledge Graphs: An Application in Healthcare
  83. An Exploration of Encoder-Decoder Approaches to Multi-Label Classification for Legal and Biomedical Text
  84. Metric Space Magnitude and Generalisation in Neural Networks
  85. Can point cloud networks learn statistical shape models of anatomies?
  86. The Case Records of ChatGPT: Language Models and Complex Clinical Questions
  87. The Role of Relevance in Fair Ranking
  88. Collaborative Chinese Text Recognition with Personalized Federated Learning
  89. Deep Learning and Geometric Deep Learning: an introduction for mathematicians and physicists
  90. Region-based Contrastive Pretraining for Medical Image Retrieval with Anatomic Query
  91. "Alexa doesn't have that many feelings": Children's understanding of AI through interactions with smart speakers in their homes
  92. PET-NeuS: Positional Encoding Tri-Planes for Neural Surfaces
  93. AudioSlots: A slot-centric generative model for audio separation
  94. StrAE: Autoencoding for Pre-Trained Embeddings using Explicit Structure
  95. RLocator: Reinforcement Learning for Bug Localization
  96. Group Activity Recognition via Dynamic Composition and Interaction
  97. Fashion CUT: Unsupervised domain adaptation for visual pattern classification in clothes using synthetic data and pseudo-labels
  98. Large Language Models Humanize Technology
  99. An Algorithm For Adversary Aware Decentralized Networked MARL
  100. SMAClite: A Lightweight Environment for Multi-Agent Reinforcement Learning
All 230
  1. SkelEx and BoundEx: Natural Visualization of ReLU Neural Networks
  2. Distributional Multi-Objective Decision Making
  3. Social Value Orientation and Integral Emotions in Multi-Agent Systems
  4. ColonMapper: topological mapping and localization for colonoscopy
  5. Integrating Holistic and Local Information to Estimate Emotional Reaction Intensity
  6. EFE: End-to-end Frame-to-Gaze Estimation
  7. RMES: Real-Time Micro-Expression Spotting Using Phase From Riesz Pyramid
  8. Minimal Learning Machine for Multi-Label Learning
  9. Self-supervised dense representation learning for live-cell microscopy with time arrow prediction
  10. FedGT: Identification of Malicious Clients in Federated Learning with Secure Aggregation
  11. Recursions Are All You Need: Towards Efficient Deep Unfolding Networks
  12. Effects of Real-Life Traffic Sign Alteration on YOLOv7- an Object Recognition Model
  13. Self-Supervised Anomaly Detection of Rogue Soil Moisture Sensors
  14. Real-time instance segmentation with polygons using an Intersection-over-Union loss
  15. MAUPQA: Massive Automatically-created Polish Question Answering Dataset
  16. Effects of sub-word segmentation on performance of transformer language models
  17. Going beyond research datasets: Novel intent discovery in the industry setting
  18. Beyond Good Intentions: Reporting the Research Landscape of NLP for Social Good
  19. Graph Neural Networks for Airfoil Design
  20. The emergence of clusters in self-attention dynamics
  21. Multi-Tier Hierarchical Federated Learning-assisted NTN for Intelligent IoT Services
  22. What is the best recipe for character-level encoder-only modelling?
  23. Restormer-Plus for Real World Image Deraining: One State-of-the-Art Solution to the GT-RAIN Challenge (CVPR 2023 UG2+ Track 3)
  24. Multiscale Augmented Normalizing Flows for Image Compression
  25. Robust Implicit Regularization via Weight Normalization
  26. StyleSync: High-Fidelity Generalized and Personalized Lip Sync in Style-based Generator
  27. Tomography of Quantum States from Structured Measurements via quantum-aware transformer
  28. WikiWeb2M: A Page-Level Multimodal Wikipedia Dataset
  29. Bone Marrow Cytomorphology Cell Detection using InceptionResNetV2
  30. High-throughput Cotton Phenotyping Big Data Pipeline Lambda Architecture Computer Vision Deep Neural Networks
  31. Egocentric Hierarchical Visual Semantics
  32. DC3DCD: unsupervised learning for multiclass 3D point cloud change detection
  33. Estimating related words computationally using language model from the Mahabharata -- an Indian epic
  34. Measuring Rule-based LTLf Process Specifications: A Probabilistic Data-driven Approach
  35. Completeness, Recall, and Negation in Open-World Knowledge Bases: A Survey
  36. Consistent Text Categorization using Data Augmentation in e-Commerce
  37. Investigating the Corruption Robustness of Image Classifiers with Random Lp-norm Corruptions
  38. CaseEncoder: A Knowledge-enhanced Pre-trained Model for Legal Case Encoding
  39. Sharpness-Aware Minimization Alone can Improve Adversarial Robustness
  40. VEDLIoT -- Next generation accelerated AIoT systems and applications
  41. PLM-GNN: A Webpage Classification Method based on Joint Pre-trained Language Model and Graph Neural Network
  42. MSVQ: Self-Supervised Learning with Multiple Sample Views and Queues
  43. Deep Graph Neural Networks via Posteriori-Sampling-based Node-Adaptive Residual Module
  44. Large Language Model Programs
  45. Towards Writer Retrieval for Historical Datasets
  46. Learning Dynamic Point Cloud Compression via Hierarchical Inter-frame Block Matching
  47. Safe Deep RL for Intraoperative Planning of Pedicle Screw Placement
  48. A Taxonomy of Foundation Model based Systems through the Lens of Software Architecture
  49. GPT-NAS: Evolutionary Neural Architecture Search with the Generative Pre-Trained Model
  50. Towards the Characterization of Representations Learned via Capsule-based Network Architectures
  51. Trustworthy Multi-phase Liver Tumor Segmentation via Evidence-based Uncertainty
  52. Rudolf Christoph Eucken at SemEval-2023 Task 4: An Ensemble Approach for Identifying Human Values from Arguments
  53. ArgU: A Controllable Factual Argument Generator
  54. Explainable Recommender with Geometric Information Bottleneck
  55. Detection of depression on social networks using transformers and ensembles
  56. TPS++: Attention-Enhanced Thin-Plate Spline for Scene Text Recognition
  57. Application of Artificial Intelligence in the Classification of Microscopical Starch Images for Drug Formulation
  58. How Informative is the Approximation Error from Tensor Decomposition for Neural Network Compression?
  59. CAMIL: Context-Aware Multiple Instance Learning for Cancer Detection and Subtyping in Whole Slide Images
  60. Structured Sentiment Analysis as Transition-based Dependency Graph Parsing
  61. The Perfect Victim: Computational Analysis of Judicial Attitudes towards Victims of Sexual Violence
  62. Eiffel Tower: A Deep-Sea Underwater Dataset for Long-Term Visual Localization
  63. Mediapipe and CNNs for Real-Time ASL Gesture Recognition
  64. Boosting Zero-shot Cross-lingual Retrieval by Training on Artificially Code-Switched Data
  65. On the Limitations of Model Stealing with Uncertainty Quantification Models
  66. Dialogue Planning via Brownian Bridge Stochastic Process for Goal-directed Proactive Dialogue
  67. Fooling State-of-the-Art Deepfake Detection with High-Quality Deepfakes
  68. Causal Discovery via Conditional Independence Testing with Proxy Variables
  69. VCSUM: A Versatile Chinese Meeting Summarization Dataset
  70. Learning to Personalize Recommendation based on Customers' Shopping Intents
  71. Causal Discovery from Subsampled Time Series with Proxy Variables
  72. DietCNN: Multiplication-free Inference for Quantized CNNs
  73. Robust Acoustic and Semantic Contextual Biasing in Neural Transducers for Speech Recognition
  74. Rotation Synchronization via Deep Matrix Factorization
  75. Guided Focal Stack Refinement Network for Light Field Salient Object Detection
  76. Survey of Federated Learning Models for Spatial-Temporal Mobility Applications
  77. Patch-DrosoNet: Classifying Image Partitions With Fly-Inspired Models For Lightweight Visual Place Recognition
  78. Attack Named Entity Recognition by Entity Boundary Interference
  79. Distilling Script Knowledge from Large Language Models for Constrained Language Planning
  80. Towards Understanding Generalization of Macro-AUC in Multi-label Learning
  81. Leveraging Generative AI Models for Synthetic Data Generation in Healthcare: Balancing Research and Privacy
  82. Learnable Behavior Control: Breaking Atari Human World Records via Sample-Efficient Behavior Selection
  83. Architectural Vision for Quantum Computing in the Edge-Cloud Continuum
  84. Traffic Forecasting on New Roads Using Spatial Contrastive Pre-Training (SCPT)
  85. FedNoRo: Towards Noise-Robust Federated Learning by Addressing Class Imbalance and Label Noise Heterogeneity
  86. Semantic Embedded Deep Neural Network: A Generic Approach to Boost Multi-Label Image Classification Performance
  87. FishRecGAN: An End to End GAN Based Network for Fisheye Rectification and Calibration
  88. BARA: Efficient Incentive Mechanism with Online Reward Budget Allocation in Cross-Silo Federated Learning
  89. Graph Neural Network-based surrogate model for granular flows
  90. Dataset of a parameterized U-bend flow for Deep Learning Applications
  91. Novel Synthetic Data Tool for Data-Driven Cardboard Box Localization
  92. CharSpan: Utilizing Lexical Similarity to Enable Zero-Shot Machine Translation for Extremely Low-resource Languages
  93. Getting More Juice Out of Your Data: Hard Pair Refinement Enhances Visual-Language Models Without Extra Data
  94. Exploration of Language Dependency for Japanese Self-Supervised Speech Representation Models
  95. LSAS: Lightweight Sub-attention Strategy for Alleviating Attention Bias Problem
  96. DeepFire2: A Convolutional Spiking Neural Network Accelerator on FPGAs
  97. CSED: A Chinese Semantic Error Diagnosis Corpus
  98. Simplicial Hopfield networks
  99. Hybrid Transformer and CNN Attention Network for Stereo Image Super-resolution
  100. FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performance
  101. Logic for Explainable AI
  102. Summarization with Precise Length Control
  103. E2TIMT: Efficient and Effective Modal Adapter for Text Image Machine Translation
  104. Cooperating Graph Neural Networks with Deep Reinforcement Learning for Vaccine Prioritization
  105. Effective Medical Code Prediction via Label Internal Alignment
  106. Child Palm-ID: Contactless Palmprint Recognition for Children
  107. Latent Interactive A2C for Improved RL in Open Many-Agent Systems
  108. Multi-Granularity Denoising and Bidirectional Alignment for Weakly Supervised Semantic Segmentation
  109. DeepTree: Modeling Trees with Situated Latents
  110. Physics-informed neural network for seismic wave inversion in layered semi-infinite domain
  111. A Mountain-Shaped Single-Stage Network for Accurate Image Restoration
  112. Adapt and Align to Improve Zero-Shot Sketch-Based Image Retrieval
  113. Linguistic More: Taking a Further Step toward Efficient and Accurate Scene Text Recognition
  114. Read, Diagnose and Chat: Towards Explainable and Interactive LLMs-Augmented Depression Detection in Social Media
  115. Localisation of Mammographic masses by Greedy Backtracking of Activations in the Stacked Auto-Encoders
  116. To AI or not to AI, to Buy Local or not to Buy Local: A Mathematical Theory of Real Price
  117. Generating Phishing Attacks using ChatGPT
  118. Dual flow fusion model for concrete surface crack segmentation
  119. A Kriging-Random Forest Hybrid Model for Real-time Ground Property Prediction during Earth Pressure Balance Shield Tunneling
  120. Comparing Foundation Models using Data Kernels
  121. Flexible Job Shop Scheduling via Dual Attention Network Based Reinforcement Learning
  122. Flame: Simplifying Topology Extension in Federated Learning
  123. Communication-Robust Multi-Agent Learning by Adaptable Auxiliary Multi-Agent Adversary Generation
  124. When a CBR in Hand is Better than Twins in the Bush
  125. Semi-Supervised Federated Learning for Keyword Spotting
  126. TinyML Design Contest for Life-Threatening Ventricular Arrhythmia Detection
  127. Wooden Sleeper Deterioration Detection for Rural Railway Prognostics Using Unsupervised Deeper FCDDs
  128. Towards unraveling calibration biases in medical image analysis
  129. Adaptive Domain Generalization for Digital Pathology Images
  130. Who Needs Decoders? Efficient Estimation of Sequence-level Attributes