mlsanityData to 14 Oct 2026

Papers

New on arXiv

Tue 12 Sep 2023

221 papers

  1. How We Define Harm Impacts Data Annotations: Explaining How Annotators Distinguish Hateful, Offensive, and Toxic CommentsLLM safety and security → Safety alignment, refusal and guardrails
  2. Adapt and Diffuse: Sample-adaptive Reconstruction via Latent Diffusion ModelsDiffusion models → Inverse problems and image restoration
  3. Reasoning with Latent Diffusion in Offline Reinforcement LearningDiffusion models → Diffusion and flow policies for robotics +1
  4. InstaFlow: One Step is Enough for High-Quality Diffusion-Based Text-to-Image GenerationDiffusion models → Flow matching, time series and science
  5. Self-Training and Multi-Task Learning for Limited Data: Evaluation Study on Object DetectionKnowledge distillation → Detection and dense prediction distillation
  6. Fg-T2M: Fine-Grained Text-Driven Human Motion Generation via Diffusion ModelDiffusion models → Video generation
  7. Re-Reading Improves Reasoning in Large Language ModelsLLM reasoning → Reasoning benchmarks and evaluation
  8. Mitigating the Alignment Tax of RLHFLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  9. Efficient Memory Management for Large Language Model Serving with PagedAttentionEfficient LLM inference and serving → KV cache optimization
  10. Elucidating the solution space of extended reverse-time SDE for diffusion modelsDiffusion models → Diffusion foundations and sampling
  11. Prompting4Debugging: Red-Teaming Text-to-Image Diffusion Models by Finding Problematic PromptsDiffusion models → Robustness, privacy and adversarial aspects +1
  12. RAP-Gen: Retrieval-Augmented Patch Generation with CodeT5 for Automatic Program RepairRetrieval-augmented generation → RAG for code
  13. Backdoor Attacks and Countermeasures in Natural Language Processing Models: A Comprehensive Security ReviewLLM safety and security → Backdoor and data poisoning attacks
  14. Beyond Generation: Harnessing Text to Image Models for Object Detection and SegmentationDiffusion models → Image generation, text-to-image and editing
  15. Language Models as Black-Box Optimizers for Vision-Language ModelsMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  16. Catch You Everything Everywhere: Guarding Textual Inversion via Concept WatermarkingLLM safety and security → Watermarking generated content and models
  17. Introducing Shape Prior Module in Diffusion Model for Medical Image SegmentationDiffusion models → Medical imaging and segmentation
  18. ACT: Empowering Decision Transformer with Dynamic Programming via Advantage ConditioningOffline RL and imitation learning from data → Decision transformers and sequence modeling
  19. Enhancing Representation in Radiography-Reports Foundation Model: A Granular Alignment Algorithm Using Masked Contrastive LearningMultimodal LLMs / vision-language models → Medical vision-language models
  20. Co-learning synaptic delays, weights and adaptation in spiking neural networks
  21. Exploiting Machine Unlearning for Backdoor Attacks in Deep Learning System
  22. Fingerprint Attack: Client De-Anonymization in Federated Learning
  23. Automating global landslide detection with heterogeneous ensemble deep-learning classification
  24. SAF: Smart Aggregation Framework for Revealing Atoms Importance Rank and Improving Prediction Rates in Drug Discovery
  25. Bayesian longitudinal tensor response regression for modeling neuroplasticity
  26. Molecular Conformation Generation via Shifting Scores
  27. PCN: A Deep Learning Approach to Jet Tagging Utilizing Novel Graph Construction Methods and Chebyshev Graph Convolutions
  28. Recovering from Privacy-Preserving Masking with Large Language Models
  29. Evaluating Dynamic Topic Models
  30. Improving Robustness of Neural Inverse Text Normalization via Data-Augmentation, Semi-Supervised Learning, and Post-Aligning Method
  31. Performance of ChatGPT-3.5 and GPT-4 on the United States Medical Licensing Examination With and Without Distractions
  32. Efficient Graphics Representation with Differentiable Indirection
  33. Kid-Whisper: Towards Bridging the Performance Gap in Automatic Speech Recognition for Children VS. Adults
  34. Respiratory Disease Classification and Biometric Analysis Using Biosignals from Digital Stethoscopes
  35. Sleep Stage Classification Using a Pre-trained Deep Learning Model
  36. The Grand Illusion: The Myth of Software Portability and Implications for ML Progress
  37. CloudBrain-NMR: An Intelligent Cloud Computing Platform for NMR Spectroscopy Processing, Reconstruction and Analysis
  38. Mind the Gap: Optimal and Equitable Encouragement Policies
  39. MELAGE: A purely python based Neuroimaging software (Neonatal)
  40. HurriCast: Synthetic Tropical Cyclone Track Generation for Hurricane Forecasting
  41. Using Unsupervised and Supervised Learning and Digital Twin for Deep Convective Ice Storm Classification
  42. Exploring Large Language Models for Ontology Alignment
  43. Overview of Human Activity Recognition Using Sensor Data
  44. Spectral Convergence of Complexon Shift Operators
  45. Goal Space Abstraction in Hierarchical Reinforcement Learning via Reachability Analysis
  46. Comparing Llama-2 and GPT-3 LLMs for HPC kernels generation
  47. Bregman Graph Neural Network
  48. Quantum Data Center: Perspectives
  49. G-Mapper: Learning a Cover in the Mapper Construction
  50. The Relational Bottleneck as an Inductive Bias for Efficient Abstraction
  51. Epistemic Modeling Uncertainty of Rapid Neural Network Ensembles for Adaptive Learning
  52. A Sequentially Fair Mechanism for Multiple Sensitive Attributes
  53. Accelerating Deep Neural Networks via Semi-Structured Activation Sparsity
  54. On the Contraction Coefficient of the Schr"odinger Bridge for Stochastic Linear Systems
  55. A Reinforcement Learning Approach for Robotic Unloading from Visual Observations
  56. RT-LM: Uncertainty-Aware Resource Management for Real-Time Inference of Language Models
  57. Multi-dimensional Fusion and Consistency for Semi-supervised Medical Image Segmentation
  58. Unsupervised Learning of Nanoindentation Data to Infer Microstructural Details of Complex Materials
  59. Harmonic-NAS: Hardware-Aware Multimodal Neural Architecture Search on Resource-constrained Devices
  60. Hybrid Algorithm Selection and Hyperparameter Tuning on Distributed Machine Learning Resources: A Hierarchical Agent-based Approach
  61. Rank2Tell: A Multimodal Driving Dataset for Joint Importance Ranking and Reasoning
  62. Do Generative Large Language Models need billions of parameters?
  63. Convergence of Gradient-based MAML in LQR
  64. Self-explainable Graph Neural Network for Alzheimer's Disease And Related Dementias Risk Prediction
  65. Electron Energy Regression in the CMS High-Granularity Calorimeter Prototype
  66. Zero-Shot Visual Classification with Guided Cropping
  67. Promises of Deep Kernel Learning for Control Synthesis
  68. Commands as AI Conversations
  69. AmodalSynthDrive: A Synthetic Amodal Perception Dataset for Autonomous Driving
  70. Text Encoders Lack Knowledge: Leveraging Generative LLMs for Domain-Specific Semantic Textual Similarity
  71. Guided Adversarial Robust Transfer Learning with Source Mixing
  72. Hierarchical Multi-Task Learning Framework for Session-based Recommendations
  73. Strong-Weak Integrated Semi-supervision for Unsupervised Single and Multi Target Domain Adaptation
  74. Exploring the Benefits of Differentially Private Pre-training and Parameter-Efficient Fine-tuning for Table Transformers
  75. Ethnicity and Biometric Uniqueness: Iris Pattern Individuality in a West African Database
  76. Minimum Bayes' Risk Decoding for System Combination of Grammatical Error Correction Systems
  77. A Q-learning Approach for Adherence-Aware Recommendations
  78. Overview of Memotion 3: Sentiment and Emotion Analysis of Codemixed Hinglish Memes
  79. DF-TransFusion: Multimodal Deepfake Detection via Lip-Audio Cross-Attention and Facial Self-Attention
  80. Leveraging Large Language Models and Weak Supervision for Social Media data annotation: an evaluation using COVID-19 self-reported vaccination tweets
  81. A Distributed Data-Parallel PyTorch Implementation of the Distributed Shampoo Optimizer for Training Neural Networks At-Scale
  82. Leveraging Large Language Models for Automated Dialogue Analysis
  83. Learning topological operations on meshes with application to block decomposition of polygons
  84. Flows for Flows: Morphing one Dataset into another with Maximum Likelihood Estimation
  85. Action Segmentation Using 2D Skeleton Heatmaps and Multi-Modality Fusion
  86. Widely Interpretable Semantic Representation: Frameless Meaning Representation for Broader Applicability
  87. Narrowing the Gap between Supervised and Unsupervised Sentence Representation Learning with Large Language Model
  88. Quantized Non-Volatile Nanomagnetic Synapse based Autoencoder for Efficient Unsupervised Network Anomaly Detection
  89. Learning Disentangled Avatars with Hybrid 3D Representations
  90. LEAP Hand: Low-Cost, Efficient, and Anthropomorphic Hand for Robot Learning
  91. Attention De-sparsification Matters: Inducing Diversity in Digital Pathology Representation Learning
  92. Exploring Non-additive Randomness on ViT against Query-Based Black-Box Attacks
  93. Unveiling the potential of large language models in generating semantic and cross-language clones
  94. AGMDT: Virtual Staining of Renal Histology Images with Adjacency-Guided Multi-Domain Transfer
  95. On Computationally Efficient Learning of Exponential Family Distributions
  96. Ensemble Mask Networks
  97. Style2Fab: Functionality-Aware Segmentation for Fabricating Personalized 3D Models with Generative AI
  98. Padding-free Convolution based on Preservation of Differential Characteristics of Kernels
  99. Cited Text Spans for Citation Text Generation
  100. Learning to Predict Concept Ordering for Common Sense Generation
All 221
  1. Using Reed-Muller Codes for Classification with Rejection and Recovery
  2. Generalized Regret Analysis of Thompson Sampling using Fractional Posteriors
  3. Band-gap regression with architecture-optimized message-passing neural networks
  4. Exploring Flat Minima for Domain Generalization with Large Learning Rates
  5. Grounded Language Acquisition From Object and Action Imagery
  6. SAMPLING: Scene-adaptive Hierarchical Multiplane Images Representation for Novel View Synthesis from a Single Image
  7. Learning Minimalistic Tsetlin Machine Clauses with Markov Boundary-Guided Pruning
  8. Semantic and Articulated Pedestrian Sensing Onboard a Moving Vehicle
  9. AI4Food-NutritionFW: A Novel Framework for the Automatic Synthesis and Analysis of Eating Behaviours
  10. Towards High-Quality Specular Highlight Removal by Leveraging Large-Scale Synthetic Data
  11. Modeling Supply and Demand in Public Transportation Systems
  12. Transferability analysis of data-driven additive manufacturing knowledge: a case study between powder bed fusion and directed energy deposition
  13. Jersey Number Recognition using Keyframe Identification from Low-Resolution Broadcast Videos
  14. IBAFormer: Intra-batch Attention Transformer for Domain Generalized Semantic Segmentation
  15. OTAS: Unsupervised Boundary Detection for Object-Centric Temporal Action Segmentation
  16. ELRA: Exponential learning rate adaption gradient descent optimization method
  17. ssVERDICT: Self-Supervised VERDICT-MRI for Enhanced Prostate Tumour Characterisation
  18. Modality Unifying Network for Visible-Infrared Person Re-Identification
  19. Toward Discretization-Consistent Closure Schemes for Large Eddy Simulation Using Reinforcement Learning
  20. Enhancing multimodal cooperation via sample-level modality valuation
  21. Rethinking Evaluation Metric for Probability Estimation Models Using Esports Data
  22. Calibration in Machine Learning Uncertainty Quantification: beyond consistency to target adaptivity
  23. Risk-Aware Reinforcement Learning through Optimal Transport Theory
  24. The first step is the hardest: Pitfalls of Representing and Tokenizing Temporal Data for Large Language Models
  25. A Consistent and Scalable Algorithm for Best Subset Selection in Single Index Models
  26. On the Injunction of XAIxArt
  27. Compiled Models, Built-In Exploits: Uncovering Pervasive Bit-Flip Attack Surfaces in DNN Executables
  28. Use neural networks to recognize students' handwritten letters and incorrect symbols
  29. Human Action Co-occurrence in Lifestyle Vlogs using Graph Link Prediction
  30. Long-term drought prediction using deep neural networks based on geospatial weather data
  31. SGNet: Salient Geometric Network for Point Cloud Registration
  32. Fast Sparse PCA via Positive Semidefinite Projection for Unsupervised Feature Selection
  33. SCP: Scene Completion Pre-training for 3D Object Detection
  34. 360^circ from a Single Camera: A Few-Shot Approach for LiDAR Segmentation
  35. Optimization Guarantees of Unfolded ISTA and ADMM Networks With Smooth Soft-Thresholding
  36. A 3M-Hybrid Model for the Restoration of Unique Giant Murals: A Case Study on the Murals of Yongle Palace
  37. Improving and Evaluating the Detection of Fragmentation in News Recommendations with the Clustering of News Story Chains
  38. Computer Vision Pipeline for Automated Antarctic Krill Analysis
  39. Assessing the Generalization Gap of Learning-Based Speech Enhancement Systems in Noisy and Reverberant Environments
  40. Glancing Future for Simultaneous Machine Translation
  41. Dual-Path Temporal Map Optimization for Make-up Temporal Video Grounding
  42. AKEM: Aligning Knowledge Base to Queries with Ensemble Model for Entity Recognition and Linking
  43. Certified Robust Models with Slack Control and Large Lipschitz Constants
  44. Overview of GUA-SPA at IberLEF 2023: Guarani-Spanish Code Switching Analysis
  45. Active Label Refinement for Semantic Segmentation of Satellite Images
  46. Robust-MBDL: A Robust Multi-branch Deep Learning Based Model for Remaining Useful Life Prediction and Operational Condition Identification of Rotating Machines
  47. Improving Generalization Capability of Deep Learning-Based Nuclei Instance Segmentation by Non-deterministic Train Time and Deterministic Test Time Stain Normalization
  48. Towards Reliable Domain Generalization: A New Dataset and Evaluations
  49. Measuring vagueness and subjectivity in texts: from symbolic to neural VAGO
  50. Annotating Data for Fine-Tuning a Neural Ranker? Current Active Learning Strategies are not Better than Random Selection
  51. JOADAA: joint online action detection and action anticipation
  52. LEyes: A Lightweight Framework for Deep Learning-Based Eye Tracking using Synthetic Eye Images
  53. Accelerating Edge AI with Morpher: An Integrated Design, Compilation and Simulation Framework for CGRAs
  54. AstroLLaMA: Towards Specialized Foundation Models in Astronomy
  55. Dynamic Visual Prompt Tuning for Parameter Efficient Transfer Learning
  56. A robust synthetic data generation framework for machine learning in High-Resolution Transmission Electron Microscopy (HRTEM)
  57. CHITNet: A Complementary to Harmonious Information Transfer Network for Infrared and Visible Image Fusion
  58. Characterizing Latent Perspectives of Media Houses Towards Public Figures
  59. HOC-Search: Efficient CAD Model and Pose Retrieval from RGB-D Scans
  60. Towards Visual Taxonomy Expansion
  61. Can we predict the Most Replayed data of video streaming platforms?
  62. Fidelity-Induced Interpretable Policy Extraction for Reinforcement Learning
  63. Estimating exercise-induced fatigue from thermal facial images
  64. A General Framework for Verification and Control of Dynamical Models via Certificate Synthesis
  65. Measuring Catastrophic Forgetting in Cross-Lingual Transfer Paradigms: Exploring Tuning Strategies
  66. Plasticity-Optimized Complementary Networks for Unsupervised Continual Learning
  67. BHASA: A Holistic Southeast Asian Linguistic and Cultural Evaluation Suite for Large Language Models
  68. A Machine Learning Framework to Deconstruct the Primary Drivers for Electricity Market Price Events
  69. Information Flow in Graph Neural Networks: A Clinical Triage Use Case
  70. A2V: A Semi-Supervised Domain Adaptation Framework for Brain Vessel Segmentation via Two-Phase Training Angiography-to-Venography Translation
  71. Efficient MRI Parallel Imaging Reconstruction by K-Space Rendering via Generalized Implicit Neural Representation
  72. Selection of contributing factors for predicting landslide susceptibility using machine learning and deep learning models
  73. Verifiable Fairness: Privacy-preserving Computation of Fairness for Machine Learning Systems
  74. Breaking through the learning plateaus of in-context learning in Transformer
  75. A Perceptron-based Fine Approximation Technique for Linear Separation
  76. Real-Time Semantic Segmentation: A Brief Survey & Comparative Study in Remote Sensing
  77. BatMan-CLR: Making Few-shots Meta-Learners Resilient Against Label Noise
  78. Improved Monte Carlo tree search formulation with multiple root nodes for discrete sizing optimization of truss structures
  79. GraspGF: Learning Score-based Grasping Primitive for Human-assisting Dexterous Grasping
  80. Normality Learning-based Graph Anomaly Detection via Multi-Scale Contrastive Learning
  81. Energy-Aware Federated Learning with Distributed User Sampling and Multichannel ALOHA
  82. Federated Learning for Large-Scale Scene Modeling with Neural Radiance Fields
  83. A new meteor detection application robust to camera movements
  84. Learning from History: Task-agnostic Model Contrastive Learning for Image Restoration
  85. Emergent Communication in Multi-Agent Reinforcement Learning for Future Wireless Networks
  86. Text Tells the Cost: Predicting and Analyzing Repayment Effort of Self-Admitted Technical Debt
  87. DSLOT-NN: Digit-Serial Left-to-Right Neural Network Accelerator
  88. Feature Aggregation Network for Building Extraction from High-resolution Remote Sensing Images
  89. Interpolation, Approximation and Controllability of Deep Neural Networks
  90. Content Reduction, Surprisal and Information Density Estimation for Long Documents
  91. SoccerNet 2023 Challenges Results
  92. TSSAT: Two-Stage Statistics-Aware Transformation for Artistic Style Transfer
  93. Life-inspired Interoceptive Artificial Intelligence for Autonomous and Adaptive Agents
  94. ATTA: Anomaly-aware Test-Time Adaptation for Out-of-Distribution Detection in Segmentation
  95. FLDNet: A Foreground-Aware Network for Polyp Segmentation Leveraging Long-Distance Dependencies
  96. Learning Unbiased News Article Representations: A Knowledge-Infused Approach
  97. CleanUNet 2: A Hybrid Speech Denoising Model on Waveform and Spectrogram
  98. Circuit Breaking: Removing Model Behaviors with Targeted Ablation
  99. Self-supervised Extraction of Human Motion Structures via Frame-wise Discrete Features
  100. Neural Network Layer Matrix Decomposition reveals Latent Manifold Encoding and Memory Capacity
  101. Evaluating the Ebb and Flow: An In-depth Analysis of Question-Answering Trends across Diverse Platforms
  102. The Moral Machine Experiment on Large Language Models
  103. GLAD: Content-aware Dynamic Graphs For Log Anomaly Detection
  104. Balanced and Explainable Social Media Analysis for Public Health with Large Language Models
  105. Knowledge-Guided Short-Context Action Anticipation in Human-Centric Videos
  106. Answering Subjective Induction Questions on Products by Summarizing Multi-sources Multi-viewpoints Knowledge
  107. Do PLMs Know and Understand Ontological Knowledge?
  108. MatSciML: A Broad, Multi-Task Benchmark for Solid-State Materials Modeling
  109. Combining Deep Learning and Street View Imagery to Map Smallholder Crop Types
  110. Frequency-Aware Masked Autoencoders for Multimodal Pretraining on Biosignals
  111. On Regularized Sparse Logistic Regression
  112. A Survey of Hallucination in Large Foundation Models
  113. SAGE: Structured Attribute Value Generation for Billion-Scale Product Catalogs
  114. Deep evidential fusion with uncertainty quantification and contextual discounting for multimodal medical image segmentation
  115. Stochastic LLMs do not Understand Language: Towards Symbolic, Explainable and Ontologically Based LLMs
  116. Medical Image Segmentation with Belief Function Theory and Deep Learning
  117. Quality-Agnostic Deepfake Detection with Intra-model Collaborative Learning
  118. Adversarial Attacks Assessment of Salient Object Detection via Symbolic Learning
  119. Strategic Behavior of Large Language Models: Game Structure vs. Contextual Framing
  120. Hierarchical Conditional Semi-Paired Image-to-Image Translation For Multi-Task Image Defect Correction On Shopping Websites
  121. Generalized Attacks on Face Verification Systems