mlsanityData to 14 Oct 2026

Papers

New on arXiv

Fri 15 Sep 2023

234 papers

  1. On Copyright Risks of Text-to-Image Diffusion ModelsDiffusion models → Robustness, privacy and adversarial aspects
  2. Self-training Strategies for Sentiment Analysis: An Empirical StudySynthetic data and self-improvement for LLMs → Self-training for few-shot NLP
  3. Probabilistic Constellation Shaping With Denoising Diffusion Probabilistic Models: A Novel ApproachDiffusion models → Diffusion for compression and wireless
  4. Sparse Autoencoders Find Highly Interpretable Features in Language ModelsMechanistic interpretability → SAE features and their applications
  5. Are Multilingual LLMs Culturally-Diverse Reasoners? An Investigation into Multicultural Proverbs and SayingsLLM reasoning → Reasoning benchmarks and evaluation
  6. Chain-of-Thought Reasoning is a Policy Improvement OperatorLLM reasoning → Prompting and chain-of-thought reasoning
  7. Viewpoint Integration and Registration with Vision Language Foundation Model for Image Change UnderstandingMultimodal LLMs / vision-language models → Medical vision-language models
  8. ICLEF: In-Context Learning with Expert Feedback for Explainable Style TransferLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
  9. A Bayesian Approach to Robust Inverse Reinforcement LearningOffline RL and imitation learning from data → Inverse reinforcement learning
  10. Denoising Diffusion Probabilistic Models for Hardware-Impaired CommunicationsDiffusion models → Diffusion for compression and wireless
  11. Augmenting conformers with structured state-space sequence models for online speech recognitionState-space sequence models (S4, Mamba) → Speech and audio SSMs
  12. HINT: Healthy Influential-Noise based Training to Defend against Data Poisoning AttacksLLM safety and security → Backdoor and data poisoning attacks
  13. Towards Practical and Efficient Image-to-Speech Captioning with Vision-Language Pre-training and Multi-modal TokensMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  14. Breathing New Life into 3D Assets with Generative RepaintingDiffusion models → 3D, point cloud and scene generation
  15. Generalised Diffusion Probabilistic Scale-SpacesDiffusion models → Diffusion foundations and sampling
  16. Large Intestine 3D Shape Refinement Using Point Diffusion Models for Digital Phantom GenerationDiffusion models → Medical imaging and segmentation
  17. One-Class Knowledge Distillation for Spoofing Speech DetectionKnowledge distillation → Speech and audio distillation
  18. A Generative Framework for Self-Supervised Facial Representation LearningDiffusion models → Image generation, text-to-image and editing
  19. Cross-lingual Knowledge Distillation via Flow-based Voice Conversion for Robust Polyglot Text-To-SpeechKnowledge distillation → Speech and audio distillation
  20. Cartoondiff: Training-free Cartoon Image Generation with Diffusion Transformer ModelsDiffusion models → Image generation, text-to-image and editing
  21. A Duty to Forget, a Right to be Assured? Exposing Vulnerabilities in Machine Unlearning ServicesLLM safety and security → Machine unlearning
  22. STDG: Semi-Teacher-Student Training Paradigram for Depth-guided One-stage Scene Graph GenerationKnowledge distillation → Detection and dense prediction distillation
  23. LASER: LLM Agent with State-Space Exploration for Web NavigationLLM agents and tool use → Web, search, and research agents
  24. Draft & Verify: Lossless Large Language Model Acceleration via Self-Speculative DecodingEfficient LLM inference and serving → Speculative decoding
  25. Two-Step Knowledge Distillation for Tiny Speech EnhancementKnowledge distillation → Speech and audio distillation
  26. Detail Reinforcement Diffusion Model: Augmentation Fine-Grained Visual Categorization in Few-Shot ConditionsDiffusion models → Image generation, text-to-image and editing
  27. Quantum Machine Learning in the Cognitive Domain: Alzheimer's Disease Study
  28. DeepCompass: AI-driven Location-Orientation Synchronization for Navigating Platforms
  29. Towards the generation of synchronized and believable non-verbal facial behaviors of a talking virtual agent
  30. Detecting Relevant Information in High-Volume Chat Logs: Keyphrase Extraction for Grooming and Drug Dealing Forensic Analysis
  31. Systematic Analysis of COVID-19 Ontologies
  32. Exploring Embeddings for Measuring Text Relatedness: Unveiling Sentiments and Relationships in Online Comments
  33. Adaptive Communications in Collaborative Perception with Domain Alignment for Autonomous Driving
  34. GPT-Lab: Next Generation Of Optimal Chemistry Discovery By GPT Driven Robotic Lab
  35. Uncovering Neural Scaling Laws in Molecular Representation Learning
  36. Personality Profiling: How informative are social media profiles in predicting personal information?
  37. InvestLM: A Large Language Model for Investment using Financial Domain Instruction Tuning
  38. Model-based Deep Learning for High-Dimensional Periodic Structures
  39. Electroencephalogram Sensor Data Compression Using An Asymmetrical Sparse Autoencoder With A Discrete Cosine Transform Layer
  40. Multidimensional well-being of US households at a fine spatial scale using fused household surveys: fusionACS
  41. Neural Metamaterial Networks for Nonlinear Material Design
  42. Long-term Neurological Sequelae in Post-COVID-19 Patients: A Machine Learning Approach to Predict Outcomes
  43. OpenAI Cribbed Our Tax Example, But Can GPT-4 Really Do Tax?
  44. EgoObjects: A Large-Scale Egocentric Dataset for Fine-Grained Object Understanding
  45. URA*: Uncertainty-aware Path Planning using Image-based Aerial-to-Ground Traversability Estimation for Off-road Environments
  46. Learning Linearized Models from Nonlinear Systems with Finite Data
  47. SHAPNN: Shapley Value Regularized Tabular Neural Network
  48. D3: Data Diversity Design for Systematic Generalization in Visual Question Answering
  49. Privacy-preserving Early Detection of Epileptic Seizures in Videos
  50. Fin-Fact: A Benchmark Dataset for Multimodal Financial Fact Checking and Explanation Generation
  51. BioinspiredLLM: Conversational Large Language Model for the Mechanics of Biological and Bio-inspired Materials
  52. Beyond Labels: Leveraging Deep Learning and LLMs for Content Metadata
  53. Quantifying predictive uncertainty of aphasia severity in stroke patients with sparse heteroscedastic Bayesian high-dimensional regression
  54. Projected Task-Specific Layers for Multi-Task Reinforcement Learning
  55. Enhance audio generation controllability through representation similarity regularization
  56. Rethinking Cross-Domain Pedestrian Detection: A Background-Focused Distribution Alignment Framework for Instance-Free One-Stage Detectors
  57. The Use of Multi-Scale Fiducial Markers To Aid Takeoff and Landing Navigation by Rotorcraft
  58. Mining Patents with Large Language Models Elucidates the Chemical Function Landscape
  59. Biased Attention: Do Vision Transformers Amplify Gender Bias More than Convolutional Neural Networks?
  60. Circular Clustering with Polar Coordinate Reconstruction
  61. Diverse Audio Embeddings -- Bringing Features Back Outperforms CLAP!
  62. Wasserstein Distributionally Robust Policy Evaluation and Learning for Contextual Bandits
  63. Unified Brain MR-Ultrasound Synthesis using Multi-Modal Hierarchical Representations
  64. Improved Breast Cancer Diagnosis through Transfer Learning on Hematoxylin and Eosin Stained Histology Images
  65. Personalized Food Image Classification: Benchmark Datasets and New Baseline
  66. Active Learning for Fine-Grained Sketch-Based Image Retrieval
  67. AlbNER: A Corpus for Named Entity Recognition in Albanian
  68. Concept explainability for plant diseases classification
  69. AV-MaskEnhancer: Enhancing Video Representations through Audio-Visual Masked Autoencoder
  70. Experimental Assessment of a Forward-Collision Warning System Fusing Deep Learning and Decentralized Radio Sensing
  71. Pointing the Way: Refining Radar-Lidar Localization Using Learned ICP Weights
  72. MusiLingo: Bridging Music and Text with Pre-trained Language Models for Music Captioning and Query Response
  73. SculptBot: Pre-Trained Models for 3D Deformable Object Manipulation
  74. Segmentation of Tubular Structures Using Iterative Training with Tailored Samples
  75. Generating Semantic Graph Corpora with Graph Expansion Grammar
  76. Adaptive Sample Sharing for Multi Agent Linear Bandits
  77. Price of Safety in Linear Best Arm Identification
  78. Vocabulary-level Memory Efficiency for Language Model Fine-tuning
  79. Performance Metrics for Probabilistic Ordinal Classifiers
  80. Wasserstein Distributionally Robust Control Barrier Function using Conditional Value-at-Risk with Differentiable Convex Programming
  81. No Imputation Needed: A Switch Approach to Irregularly Sampled Time Series
  82. Resolving Legalese: A Multilingual Exploration of Negation Scope Resolution in Legal Documents
  83. BANSAC: A dynamic BAyesian Network for adaptive SAmple Consensus
  84. Evaluating the Impact of Local Differential Privacy on Utility Loss via Influence Functions
  85. Fake News Detectors are Biased against Texts Generated by Large Language Models
  86. Quantifying Credit Portfolio sensitivity to asset correlations with interpretable generative neural networks
  87. Adversarial Attacks on Tables with Entity Swap
  88. An inspection technology of inner surface of the fine hole based on machine vision
  89. MAPLE: Mobile App Prediction Leveraging Large Language Model Embeddings
  90. Intent Detection at Scale: Tuning a Generic Model using Relevant Intents
  91. CoCA: Fusing Position Embedding with Collinear Constrained Attention in Transformers for Long Context Window Extending
  92. Towards Robust and Smooth 3D Multi-Person Pose Estimation from Monocular Videos in the Wild
  93. A Stochastic Online Forecast-and-Optimize Framework for Real-Time Energy Dispatch in Virtual Power Plants under Uncertainty
  94. Projected Langevin dynamics and a gradient flow for entropic optimal transport
  95. Robust e-NeRF: NeRF from Sparse & Noisy Events under Non-Uniform Motion
  96. "Merge Conflicts!" Exploring the Impacts of External Distractors to Parametric Knowledge Graphs
  97. Attention-Only Transformers and Implementing MLPs with Attention Heads
  98. Neural Machine Translation Models Can Learn to be Few-shot Learners
  99. Robust Frame-to-Frame Camera Rotation Estimation in Crowded Scenes
  100. Compositional Foundation Models for Hierarchical Planning
All 234
  1. Replacing softmax with ReLU in Vision Transformers
  2. Indian-BhED: A Dataset for Measuring India-Centric Biases in Large Language Models
  3. Neural Network Driven, Interactive Design for Nonlinear Optical Molecules Based on Group Contribution Method
  4. Local Differential Privacy in Graph Neural Networks: a Reconstruction Approach
  5. How Transferable are Attribute Controllers on Pretrained Multilingual Translation Models?
  6. The Impact of Different Backbone Architecture on Autonomous Vehicle Dataset
  7. Deep Reinforcement Learning for Efficient and Fair Allocation of Health Care Resources
  8. Towards Robust Continual Learning with Bayesian Adaptive Moment Regularization
  9. Efficient and robust Sensor Placement in Complex Environments
  10. When do Generative Query and Document Expansions Fail? A Comprehensive Study Across Methods, Retrievers, and Datasets
  11. Visual Speech Recognition for Languages with Limited Labeled Data using Automatic Labels from Whisper
  12. Towards Last-layer Retraining for Group Robustness with Fewer Annotations
  13. Automated dermatoscopic pattern discovery by clustering neural network output for human-computer interaction
  14. EvoPrompt: Connecting LLMs with Evolutionary Algorithms Yields Powerful Prompt Optimizers
  15. Scaling Laws for Sparsely-Connected Foundation Models
  16. SCT: A Simple Baseline for Parameter-Efficient Fine-Tuning via Salient Channels
  17. OccupancyDETR: Using DETR for Mixed Dense-sparse 3D Occupancy Prediction
  18. HealthFC: Verifying Health Claims with Evidence-Based Medical Fact-Checking
  19. Deep-learning-powered data analysis in plankton ecology
  20. POCKET: Pruning Random Convolution Kernels for Time Series Classification from a Feature Selection Perspective
  21. Using Large Language Models for Knowledge Engineering (LLMKE): A Case Study on Wikidata
  22. Towards Word-Level End-to-End Neural Speaker Diarization with Auxiliary Network
  23. XFedHunter: An Explainable Federated Learning Framework for Advanced Persistent Threat Detection in SDN
  24. YCB-Ev 1.1: Event-vision dataset for 6DoF object pose estimation
  25. 3D Arterial Segmentation via Single 2D Projections and Depth Supervision in Contrast-Enhanced CT Images
  26. PoseFix: Correcting 3D Human Poses with Natural Language
  27. VulnSense: Efficient Vulnerability Detection in Ethereum Smart Contracts by Multimodal Learning with Graph Neural Network and Language Model
  28. On some limitations of data-driven weather forecasting models
  29. TreeLearn: A deep learning method for segmenting individual trees from ground-based LiDAR forest point clouds
  30. Silver Retriever: Advancing Neural Passage Retrieval for Polish Question Answering
  31. Explaining Search Result Stances to Opinionated People
  32. Combining TF-GridNet and Mixture Encoder for Continuous Speech Separation for Meeting Transcription
  33. Advancing the Evaluation of Traditional Chinese Language Models: Towards a Comprehensive Benchmark Suite
  34. Toward responsible face datasets: modeling the distribution of a disentangled latent space for sampling face images from demographic groups
  35. Chunked Attention-based Encoder-Decoder Model for Streaming Speech Recognition
  36. Segment Anything Model for Brain Tumor Segmentation
  37. IHT-Inspired Neural Network for Single-Snapshot DOA Estimation with Sparse Linear Arrays
  38. X-PDNet: Accurate Joint Plane Instance Segmentation and Monocular Depth Estimation with Cross-Task Distillation and Boundary Correction
  39. MIML: Multiplex Image Machine Learning for High Precision Cell Classification via Mechanical Traits within Microfluidic Systems
  40. FedDCSR: Federated Cross-domain Sequential Recommendation via Disentangled Representation Learning
  41. Deformable Neural Radiance Fields using RGB and Event Cameras
  42. A new method of modeling the multi-stage decision-making process of CRT using machine learning with uncertainty quantification
  43. Make Deep Networks Shallow Again
  44. Constraint-Free Structure Learning with Smooth Acyclic Orientations
  45. 3D SA-UNet: 3D Spatial Attention UNet with 3D Atrous Spatial Pyramid Pooling for White Matter Hyperintensities Segmentation
  46. Optimizing Modular Robot Composition: A Lexicographic Genetic Algorithm Approach
  47. Exploring Meta Information for Audio-based Zero-shot Bird Classification
  48. Learning by Self-Explaining
  49. A Unified View Between Tensor Hypergraph Neural Networks And Signal Denoising
  50. Double Domain Guided Real-Time Low-Light Image Enhancement for Ultra-High-Definition Transportation Surveillance
  51. On undesired emergent behaviors in compound prostate cancer detection systems
  52. Unleashing Potential of Evidence in Knowledge-Intensive Dialogue Generation
  53. PatFig: Generating Short and Long Captions for Patent Figures
  54. DiaCorrect: Error Correction Back-end For Speaker Diarization
  55. Boosting Fair Classifier Generalization through Adaptive Priority Reweighing
  56. Understanding the limitations of self-supervised learning for tabular anomaly detection
  57. Beyond Domain Gap: Exploiting Subjectivity in Sketch-Based Person Retrieval
  58. An Efficient Wide-Range Pseudo-3D Vehicle Detection Using A Single Camera
  59. Robust Burned Area Delineation through Multitask Learning
  60. M3Net: Multilevel, Mixed and Multistage Attention Network for Salient Object Detection
  61. Continual Learning with Deep Streaming Regularized Discriminant Analysis
  62. Headless Language Models: Learning without Predicting with Contrastive Weight Tying
  63. Reward Engineering for Generating Semi-structured Explanation
  64. Data Distribution Bottlenecks in Grounding Language Models to Knowledge Bases
  65. A Theoretical and Empirical Study on the Convergence of Adam with an "Exact" Constant Step Size in Non-Convex Settings
  66. Let's Predict Who Will Move to a New Job
  67. Estimation of Counterfactual Interventions under Uncertainties
  68. Distributional Inclusion Hypothesis and Quantifications: Probing for Hypernymy in Functional Distributional Semantics
  69. How to Handle Different Types of Out-of-Distribution Scenarios in Computational Argumentation? A Comprehensive and Fine-Grained Field Study
  70. Conditional validity of heteroskedastic conformal regression
  71. Self-Consistent Narrative Prompts on Abductive Natural Language Inference
  72. T-UDA: Temporal Unsupervised Domain Adaptation in Sequential Point Clouds
  73. A Real-Time Active Speaker Detection System Integrating an Audio-Visual Signal with a Spatial Querying Mechanism
  74. Structural Self-Supervised Objectives for Transformers
  75. Edge Based Oriented Object Detection
  76. Leveraging the Power of Data Augmentation for Transformer-based Tracking
  77. BROW: Better featuRes fOr Whole slide image based on self-distillation
  78. Sampling-Free Probabilistic Deep State-Space Models
  79. Autonomous and Human-Driven Vehicles Interacting in a Roundabout: A Quantitative and Qualitative Evaluation
  80. Optimization of Rank Losses for Image Retrieval
  81. Deep Nonnegative Matrix Factorization with Beta Divergences
  82. A Geometric Perspective on Autoencoders
  83. A Real-time Faint Space Debris Detector With Learning-based LCM
  84. Topological Node2vec: Enhanced Graph Embedding via Persistent Homology
  85. Human-Inspired Topological Representations for Visual Object Recognition in Unseen Environments
  86. Efficient Polyp Segmentation Via Integrity Learning
  87. Ensuring Topological Data-Structure Preservation under Autoencoder Compression due to Latent Space Regularization in Gauss--Legendre nodes
  88. VERSE: Virtual-Gradient Aware Streaming Lifelong Learning with Anytime Inference
  89. UniST: Towards Unifying Saliency Transformer for Video Saliency Prediction and Detection
  90. Unified Risk Analysis for Weakly Supervised Learning
  91. Investigating Answerability of LLMs for Long-Form Question Answering
  92. HM-Conformer: A Conformer-based audio deepfake detection system with hierarchical pooling and multi-level classification token aggregation methods
  93. Salient Object Detection in Optical Remote Sensing Images Driven by Transformer
  94. One-stage Modality Distillation for Incomplete Multimodal Learning
  95. Sparsity-Aware Distributed Learning for Gaussian Processes with Linear Multiple Kernel
  96. Hyperspectral Image Denoising via Self-Modulating Convolutional Neural Networks
  97. ECEA: Extensible Co-Existing Attention for Few-Shot Object Detection
  98. An Explainable Deep-learning Model of Proton Auroras on Mars
  99. Encoded Summarization: Summarizing Documents into Continuous Vector Space for Legal Case Retrieval
  100. A Precision-Scalable RISC-V DNN Processor with On-Device Learning Capability at the Extreme Edge
  101. Multilingual Sentence-Level Semantic Search using Meta-Distillation Learning
  102. Using Large Language Model to Solve and Explain Physics Word Problems Approaching Human Level
  103. Large Language Models for Failure Mode Classification: An Investigation
  104. FedJudge: Federated Legal Large Language Model
  105. Unveiling Invariances via Neural Network Pruning
  106. Differentiable Resolution Compression and Alignment for Efficient Video Classification and Retrieval
  107. To Predict or to Reject: Causal Effect Estimation with Uncertainty on Networked Data
  108. A Ground Segmentation Method Based on Point Cloud Map for Unstructured Roads
  109. Self-Assessment Tests are Unreliable Measures of LLM Personality
  110. Cross-Modal Synthesis of Structural MRI and Functional Connectivity Networks via Conditional ViT-GANs
  111. AdSEE: Investigating the Impact of Image Style Editing on Advertisement Attractiveness
  112. A Testbed for Automating and Analysing Mobile Devices and their Applications
  113. RADE: Reference-Assisted Dialogue Evaluation for Open-Domain Dialogue
  114. Dynamic Visual Semantic Sub-Embeddings and Fast Re-Ranking
  115. DA-RAW: Domain Adaptive Object Detection for Real-World Adverse Weather Conditions
  116. Unimodal Aggregation for CTC-based Speech Recognition
  117. Syn-Att: Synthetic Speech Attribution via Semi-Supervised Unknown Multi-Class Ensemble of CNNs
  118. Audio Difference Learning for Audio Captioning
  119. PromptTTS++: Controlling Speaker Identity in Prompt-Based Text-to-Speech Using Natural Language Descriptions
  120. Multi-Scale Estimation for Omni-Directional Saliency Maps Using Learnable Equator Bias
  121. Find What You Want: Learning Demand-conditioned Object Attribute Space for Demand-driven Navigation
  122. Let's Roll: Synthetic Dataset Analysis for Pedestrian Detection Across Different Shutter Types
  123. AnyOKP: One-Shot and Instance-Aware Object Keypoint Extraction with Pretrained ViT
  124. Increasing diversity of omni-directional images generated from single image using cGAN based on MLPMixer
  125. Oobleck: Resilient Distributed Training of Large Models Using Pipeline Templates
  126. "I'm Not Confident in Debiasing AI Systems Since I Know Too Little": Teaching AI Creators About Gender Bias Through Hands-on Tutorials
  127. MetaF2N: Blind Image Super-Resolution by Learning Efficient Model Adaptation from Faces
  128. Empowering Private Tutoring by Chaining Large Language Models
  129. Data-Driven Goal Recognition in Transhumeral Prostheses Using Process Mining Techniques
  130. Research on Joint Representation Learning Methods for Entity Neighborhood Information and Description Information
  131. Characterizing the temporal dynamics of universal speech representations for generalizable deepfake detection
  132. hear-your-action: human action recognition by ultrasound active sensing
  133. Fast and Accurate Deep Loop Closing and Relocalization for Reliable LiDAR SLAM
  134. Supervised Stochastic Neighbor Embedding Using Contrastive Learning