mlsanityData to 14 Oct 2026

Papers

New on arXiv

Thu 9 Nov 2023

209 papers

  1. Chain of Images for Intuitively ReasoningLLM reasoning → Multimodal reasoning
  2. Bridging the Digital Divide: Performance Variation across Socio-Economic Factors in Vision-Language ModelsMultimodal LLMs / vision-language models → Social bias and fairness in VLMs
  3. GIPCOL: Graph-Injected Soft Prompting for Compositional Zero-Shot LearningMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  4. Agent Lumos: Unified and Modular Training for Open-Source Language AgentsLLM agents and tool use → General LLM agent frameworks and benchmarks
  5. FigStep: Jailbreaking Large Vision-Language Models via Typographic Visual PromptsMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness +2
  6. LLM Augmented Hierarchical AgentsLLM agents and tool use → Reinforcement learning for LLM agents
  7. LCM-LoRA: A Universal Stable-Diffusion Acceleration ModuleDiffusion models → Diffusion foundations and sampling
  8. Removing RLHF Protections in GPT-4 via Fine-TuningLLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks
  9. Object-centric Cross-modal Feature Distillation for Event-based Object DetectionKnowledge distillation → Detection and dense prediction distillation
  10. Retinal OCT Synthesis with Denoising Diffusion Probabilistic Models for Layer SegmentationDiffusion models → Medical imaging and segmentation
  11. Robust Retraining-free GAN Fingerprinting via Personalized NormalizationLLM safety and security → Watermarking generated content and models
  12. 3DStyle-Diffusion: Pursuing Fine-grained Text-driven 3D Stylization with 2D Diffusion ModelsDiffusion models → 3D, point cloud and scene generation
  13. ControlStyle: Text-Driven Stylized Image Generation Using Diffusion PriorsDiffusion models → Image generation, text-to-image and editing
  14. Control3D: Towards Controllable Text-to-3D GenerationDiffusion models → 3D, point cloud and scene generation
  15. Cognitively Inspired Components for Social Conversational AgentsLLM agents and tool use → General LLM agent frameworks and benchmarks
  16. LLaVA-Plus: Learning to Use Tools for Creating Multimodal AgentsMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning +1
  17. Diffusion Based Causal Representation LearningLLM reasoning → Causal reasoning in LLMs
  18. TencentLLMEval: A Hierarchical Evaluation of Real-World Capabilities for Human-Aligned LLMsLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
  19. u-LLaVA: Unifying Multi-Modal Tasks via Large Language ModelMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  20. On the Road with GPT-4V(ision): Early Explorations of Visual-Language Model on Autonomous DrivingMultimodal LLMs / vision-language models → Driving VLMs and open-vocabulary detection +1
  21. Improving Vision-and-Language Reasoning via Spatial Relations ModelingLLM reasoning → Multimodal reasoning
  22. RAGLog: Log Anomaly Detection using Retrieval Augmented GenerationRetrieval-augmented generation → Privacy and security of RAG
  23. BrainNetDiff: Generative AI Empowers Brain Network Generation via Multimodal Diffusion ModelDiffusion models → Medical imaging and segmentation
  24. Conic10K: A Challenging Math Problem Understanding and Reasoning DatasetLLM reasoning → Mathematical reasoning
  25. GRASP: A Disagreement Analysis Framework to Assess Group Associations in PerspectivesLLM safety and security → Safety alignment, refusal and guardrails
  26. Glioblastoma Tumor Segmentation using an Ensemble of Vision Transformers
  27. Large Human Language Models: A Need and the Challenges
  28. Leveraging Artificial Intelligence Technology for Mapping Research to Sustainable Development Goals: A Case Study
  29. Vision Encoder-Decoder Models for AI Coaching
  30. Protein-ligand binding representation learning from fine-grained interactions
  31. CarbNN: A Novel Active Transfer Learning Neural Network To Build De Novo Metal Organic Frameworks (MOFs) for Carbon Capture
  32. Ball Mill Fault Prediction Based on Deep Convolutional Auto-Encoding Network
  33. Gaussian Differential Privacy on Riemannian Manifolds
  34. Devil in the Landscapes: Inferring Epidemic Exposure Risks from Street View Imagery
  35. Hallucination-minimized Data-to-answer Framework for Financial Decision-makers
  36. Identification of Books That are Suitable for Middle School Students Using Artificial Neural Networks
  37. Large Language Models can Strategically Deceive their Users when Put Under Pressure
  38. Dialogizer: Context-aware Conversational-QA Dataset Generation from Textual Sources
  39. ShipGen: A Diffusion Model for Parametric Ship Hull Generation with Multiple Objectives and Constraints
  40. Game Theory Solutions in Sensor-Based Human Activity Recognition: A Review
  41. Labor Space: A Unifying Representation of the Labor Market via Large Language Models
  42. An Experimental Design for Anytime-Valid Causal Inference on Multi-Armed Bandits
  43. Is a Seat at the Table Enough? Engaging Teachers and Students in Dataset Specification for ML in Education
  44. Detecting Suspicious Commenter Mob Behaviors on YouTube Using Graph2Vec
  45. The Paradox of Noise: An Empirical Study of Noise-Infusion Mechanisms to Improve Generalization, Stability, and Privacy in Federated Learning
  46. Structured Transforms Across Spaces with Cost-Regularized Optimal Transport
  47. Towards stable real-world equation discovery with assessing differentiating quality influence
  48. Are "Hierarchical" Visual Representations Hierarchical?
  49. Real-time Control of Electric Autonomous Mobility-on-Demand Systems via Graph Reinforcement Learning
  50. Language-guided Robot Grasping: CLIP-based Referring Grasp Synthesis in Clutter
  51. DONUT-hole: DONUT Sparsification by Harnessing Knowledge and Optimizing Learning Efficiency
  52. PolyMaX: General Dense Prediction with Mask Transformer
  53. Are Chatbots Reliable Text Annotators? Sometimes
  54. Dirichlet Energy Enhancement of Graph Neural Networks by Framelet Augmentation
  55. Generative Explanations for Graph Neural Network: Methods and Evaluations
  56. Compressed and Sparse Models for Non-Convex Decentralized Learning
  57. Step and Smooth Decompositions as Topological Clustering
  58. Deep Natural Language Feature Learning for Interpretable Prediction
  59. Optimal simulation-based Bayesian decisions
  60. Efficiently Adapting Pretrained Language Models To New Languages
  61. Generating Pragmatic Examples to Train Neural Program Synthesizers
  62. Adaptive Compression-Aware Split Learning and Inference for Enhanced Network Efficiency
  63. LogShield: A Transformer-based APT Detection System Leveraging Self-Attention
  64. Neural Network Methods for Radiation Detectors and Imaging
  65. Whole-body Detection, Recognition and Identification at Altitude and Range
  66. Verilog-to-PyG -- A Framework for Graph Learning and Augmentation on RTL Designs
  67. Long-Horizon Dialogue Understanding for Role Identification in the Game of Avalon with Large Language Models
  68. Intelligent Cervical Spine Fracture Detection Using Deep Learning Methods
  69. FMViT: A multiple-frequency mixing Vision Transformer
  70. Mirasol3B: A Multimodal Autoregressive model for time-aligned and contextual modalities
  71. 3DGAUnet: 3D generative adversarial networks with a 3D U-Net based generator to achieve the accurate and effective synthesis of clinical tumor image data for pancreatic cancer
  72. Conditional Optimal Transport on Function Spaces
  73. Multi-Modal Gaze Following in Conversational Scenarios
  74. A theory for the sparsity emerged in the Forward Forward algorithm
  75. Explainable artificial intelligence for Healthcare applications using Random Forest Classifier with LIME and SHAP
  76. An Experiment in Retrofitting Competency Questions for Existing Ontologies
  77. Prompt Engineering a Prompt Engineer
  78. Enhancing Instance-Level Image Classification with Set-Level Labels
  79. Window Attention is Bugged: How not to Interpolate Position Embeddings
  80. Efficient Parallelization Layouts for Large-Scale Distributed Model Training
  81. What Do I Hear? Generating Sounds for Visuals with ChatGPT
  82. Real-Time Neural Rasterization for Large Scenes
  83. Diffusion-Generative Multi-Fidelity Learning for Physical Simulation
  84. 3D-QAE: Fully Quantum Auto-Encoding of 3D Point Clouds
  85. Reconstructing Objects in-the-wild for Realistic Sensor Simulation
  86. FAMuS: Frames Across Multiple Sources
  87. SynH2R: Synthesizing Hand-Object Motions for Learning Human-to-Robot Handovers
  88. Sorting Out Quantum Monte Carlo
  89. Multimodal Foundation Models Exploit Text to Make Medical Image Predictions
  90. Conversational AI Threads for Visualizing Multidimensional Datasets
  91. A Coefficient Makes SVRG Effective
  92. A new framework for Marketing Mix Modeling: Addressing Channel Influence Bias and Cross-Channel Effects
  93. Zero-Shot Goal-Directed Dialogue via RL on Imagined Conversations
  94. Inference for Probabilistic Dependency Graphs
  95. SigScatNet: A Siamese + Scattering based Deep Learning Approach for Signature Forgery Detection and Similarity Assessment
  96. Outlier-Robust Wasserstein DRO
  97. Exploring Emotion Expression Recognition in Older Adults Interacting with a Virtual Coach
  98. High-Performance Transformers for Table Structure Recognition Need Early Convolutions
  99. Disentangling Quantum and Classical Contributions in Hybrid Quantum Machine Learning Architectures
  100. Exploiting Neural-Network Statistics for Low-Power DNN Inference
All 209
  1. The Iron(ic) Melting Pot: Reviewing Human Evaluation in Humour, Irony and Sarcasm Generation
  2. Towards End-to-End Spoken Grammatical Error Correction
  3. L-WaveBlock: A Novel Feature Extractor Leveraging Wavelets for Generative Adversarial Networks
  4. Multi-Agent Quantum Reinforcement Learning using Evolutionary Optimization
  5. A Deep Learning Method for Simultaneous Denoising and Missing Wedge Reconstruction in Cryogenic Electron Tomography
  6. Embedding Space Interpolation Beyond Mini-Batch, Beyond Pairs and Beyond Examples
  7. Information-theoretic generalization bounds for learning from quantum data
  8. SeaTurtleID2022: A long-span dataset for reliable sea turtle re-identification
  9. BakedAvatar: Baking Neural Fields for Real-Time Head Avatar Synthesis
  10. From Learning Management System to Affective Tutoring system: a preliminary study
  11. Anytime-Constrained Reinforcement Learning
  12. Dirichlet Active Learning
  13. General Policies, Subgoal Structure, and Planning Width
  14. Disease Gene Prioritization With Quantum Walks
  15. META4: Semantically-Aligned Generation of Metaphoric Gestures Using Self-Supervised Text and Speech Representation
  16. Using ResNet to Utilize 4-class T2-FLAIR Slice Classification Based on the Cholinergic Pathways Hyperintensities Scale for Pathological Aging
  17. Do Ensembling and Meta-Learning Improve Outlier Detection in Randomized Controlled Trials?
  18. Text Representation Distillation via Information Bottleneck Principle
  19. Transformer-based Model for Oral Epithelial Dysplasia Segmentation
  20. All Should Be Equal in the Eyes of Language Models: Counterfactually Aware Fair Text Generation
  21. A Practical Approach to Novel Class Discovery in Tabular Data
  22. Fair Wasserstein Coresets
  23. Parkinson's Disease Detection through Vocal Biomarkers and Advanced Machine Learning Algorithms
  24. Dual Pipeline Style Transfer with Input Distribution Differentiation
  25. Taxonomy for Resident Space Objects in LEO: A Deep Learning Approach
  26. Statistical Learning of Conjunction Data Messages Through a Bayesian Non-Homogeneous Poisson Process
  27. Active Mining Sample Pair Semantics for Image-text Matching
  28. Counterfactually Fair Representation
  29. Mirror: A Universal Framework for Various Information Extraction Tasks
  30. Generalization in medical AI: a perspective on developing scalable models
  31. Predicting the Position Uncertainty at the Time of Closest Approach with Diffusion Models
  32. Linear Gaussian Bounding Box Representation and Ring-Shaped Rotated Convolution for Oriented Object Detection
  33. Data Distillation for Neural Network Potentials toward Foundational Dataset
  34. SIRE: scale-invariant, rotation-equivariant estimation of artery orientations using graph neural networks
  35. The Sample Complexity Of ERMs In Stochastic Convex Optimization
  36. Improving Hand Recognition in Uncontrolled and Uncooperative Environments using Multiple Spatial Transformers and Loss Functions
  37. Memorisation Cartography: Mapping out the Memorisation-Generalisation Continuum in Neural Machine Translation
  38. Training Robust Deep Physiological Measurement Models with Synthetic Video-based Data
  39. Beyond the training set: an intuitive method for detecting distribution shift in model-based optimization
  40. Basis functions nonlinear data-enabled predictive control: Consistent and computationally efficient formulations
  41. There's no Data Like Better Data: Using QE Metrics for MT Data Filtering
  42. Accelerated Shapley Value Approximation for Data Evaluation
  43. SynFacePAD 2023: Competition on Face Presentation Attack Detection Based on Privacy-aware Synthetic Training Data
  44. Real-time Addressee Estimation: Deployment of a Deep-Learning Model on the iCub Robot
  45. Spatial Attention-based Distribution Integration Network for Human Pose Estimation
  46. RepQ: Generalizing Quantization-Aware Training for Re-Parametrized Architectures
  47. ABIGX: A Unified Framework for eXplainable Fault Detection and Classification
  48. SPADES: A Realistic Spacecraft Pose Estimation Dataset using Event Sensing
  49. Data Valuation and Detections in Federated Learning
  50. Reliable and Efficient Data Collection in UAV-based IoT Networks
  51. Challenging the Validity of Personality Tests for Large Language Models
  52. BeLLM: Backward Dependency Enhanced Large Language Model for Sentence Embeddings
  53. VoxNeRF: Bridging Voxel Representation and Neural Radiance Fields for Enhanced Indoor View Synthesis
  54. Causal Inference from Text: Unveiling Interactions between Variables
  55. SAMVG: A Multi-stage Image Vectorization Model with the Segment-Anything Model
  56. Single-shot Tomography of Discrete Dynamic Objects
  57. Modelling prospective memory and resilient situated communications via Wizard of Oz
  58. Don't Waste a Single Annotation: Improving Single-Label Classifiers Through Soft Labels
  59. Model-Based Minimum Bayes Risk Decoding for Text Generation
  60. Latent Task-Specific Graph Network Simulators
  61. Uncertainty Wrapper in the medical domain: Establishing transparent uncertainty quantification for opaque machine learning models in practice
  62. When Meta-Learning Meets Online and Continual Learning: A Survey
  63. Widely Applicable Strong Baseline for Sports Ball Detection and Tracking
  64. A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions
  65. ConRad: Image Constrained Radiance Fields for 3D Generation from a Single Image
  66. Kantian Deontology Meets AI Alignment: Towards Morally Grounded Fairness Metrics
  67. Let's Get the FACS Straight -- Reconstructing Obstructed Facial Features
  68. Whisper in Focus: Enhancing Stuttered Speech Classification with Encoder Layer Optimization
  69. Green Resilience of Cyber-Physical Systems
  70. Adaptive-Labeling for Enhancing Remote Sensing Cloud Understanding
  71. Deep learning in computed tomography pulmonary angiography imaging: a dual-pronged approach for pulmonary embolism detection
  72. PRODIGy: a PROfile-based DIalogue Generation dataset
  73. TransReg: Cross-transformer as auto-registration module for multi-view mammogram mass detection
  74. Audio-visual Saliency for Omnidirectional Videos
  75. Mixture of Weak & Strong Experts on Graphs
  76. Large Language Models and Prompt Engineering for Biomedical Query Focused Multi-Document Summarisation
  77. FireMatch: A Semi-Supervised Video Fire Detection Network Based on Consistency and Distribution Alignment
  78. Perfecting Liquid-State Theories with Machine Intelligence
  79. Enhancing Computation Efficiency in Large Language Models through Weight and Activation Quantization
  80. RAPID: Training-free Retrieval-based Log Anomaly Detection with PLM considering Token-level information
  81. Weakly-supervised Deep Cognate Detection Framework for Low-Resourced Languages Using Morphological Knowledge of Closely-Related Languages
  82. Cross-modal Prompts: Adapting Large Pre-trained Models for Audio-Visual Downstream Tasks
  83. Dynamic Association Learning of Self-Attention and Convolution in Image Restoration
  84. OW-SLR: Overlapping Windows on Semi-Local Region for Image Super-Resolution
  85. Counter-Empirical Attacking based on Adversarial Reinforcement Learning for Time-Relevant Scoring System
  86. SCAAT: Improving Neural Network Interpretability via Saliency Constrained Adaptive Adversarial Training
  87. Hard-Negative Sampling for Contrastive Learning: Optimal Representation Geometry and Neural- vs Dimensional-Collapse
  88. Improving Computational Efficiency for Powered Descent Guidance via Transformer-based Tight Constraint Prediction
  89. Exploring and Analyzing Wildland Fire Data Via Machine Learning Techniques
  90. ScribblePolyp: Scribble-Supervised Polyp Segmentation through Dual Consistency Alignment
  91. Quranic Conversations: Developing a Semantic Search tool for the Quran using Arabic NLP Techniques
  92. Unsupervised Translation Quality Estimation Exploiting Synthetic Data and Pre-trained Multilingual Encoder
  93. Covering Number of Real Algebraic Varieties and Beyond: Improved Bounds and Applications
  94. A Survey of Large Language Models in Medicine: Progress, Application, and Challenge
  95. Reducing the Side-Effects of Oscillations in Training of Quantized YOLO Networks
  96. Personalized Online Federated Learning with Multiple Kernels
  97. A differentiable brain simulator bridging brain simulation and brain-inspired computing
  98. Self-similarity Prior Distillation for Unsupervised Remote Physiological Measurement
  99. GeoFormer: Predicting Human Mobility using Generative Pre-trained Transformer (GPT)
  100. Legal-HNet: Mixing Legal Long-Context Tokens with Hartley Transform
  101. Meta-learning of semi-supervised learning from tasks with heterogeneous attribute spaces
  102. Characterizing Large Language Models as Rationalizers of Knowledge-intensive Tasks
  103. Signal Temporal Logic-Guided Apprenticeship Learning
  104. Generalized test utilities for long-tail performance in extreme multi-label classification
  105. Social Media Bot Detection using Dropout-GAN
  106. POISE: Pose Guided Human Silhouette Extraction under Occlusions
  107. Mental Health Diagnosis in the Digital Age: Harnessing Sentiment Analysis on Social Media Platforms upon Ultra-Sparse Feature Content
  108. On the Behavior of Audio-Visual Fusion Architectures in Identity Verification Tasks
  109. Accelerating Exploration with Unlabeled Prior Data