mlsanityData to 14 Oct 2026

Papers

New on arXiv

Wed 8 May 2024

229 papers

  1. Preble: Efficient Distributed Prompt Scheduling for LLM ServingEfficient LLM inference and serving → Serving systems and request scheduling
  2. Fast Stochastic Policy Gradient: Negative Momentum for Reinforcement LearningDeep reinforcement learning methods → RL theory and sample complexity
  3. LLM-Augmented Agent-Based Modelling for Social Simulations: Challenges and OpportunitiesLLM agents and tool use → Social simulation and multi-agent debate
  4. Utilizing Large Language Models to Generate Synthetic Data to Increase the Performance of BERT-Based Neural NetworksSynthetic data and self-improvement for LLMs → Medical synthetic data and agents
  5. Model-Free Robust φ-Divergence Reinforcement Learning Using Both Offline and Online DataDeep reinforcement learning methods → RL theory and sample complexity
  6. Markowitz Meets Bellman: Knowledge-distilled Reinforcement Learning for Portfolio ManagementKnowledge distillation → On-policy and self-distillation for LLMs +1
  7. Evaluating Students' Open-ended Written Responses with LLMs: Using the RAG Framework for GPT-3.5, GPT-4, Claude-3, and Mistral-LargeRetrieval-augmented generation → RAG pipeline design and evaluation
  8. How Generalizable Is My Behavior Cloning Policy? A Statistical Approach to Trustworthy Performance EvaluationOffline RL and imitation learning from data → Robot manipulation imitation learning
  9. KV-Runahead: Scalable Causal LLM Inference by Parallel Key-Value Cache GenerationEfficient LLM inference and serving → KV cache optimization
  10. THRONE: An Object-based Hallucination Benchmark for the Free-form Generations of Large Vision-Language ModelsMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs
  11. Diffusion-HMC: Parameter Inference with Diffusion-model-driven Hamiltonian Monte CarloDiffusion models → Inverse problems and image restoration
  12. Attention-Driven Training-Free Efficiency Enhancement of Diffusion ModelsDiffusion models → Diffusion foundations and sampling
  13. Imagine Flash: Accelerating Emu Diffusion Models with Backward DistillationDiffusion models → Diffusion foundations and sampling
  14. FinePOSE: Fine-Grained Prompt-Driven 3D Human Pose Estimation via Diffusion ModelsDiffusion models → 3D, point cloud and scene generation
  15. MIDGARD: Self-Consistency Using Minimum Description Length for Structured Commonsense ReasoningLLM reasoning → Knowledge- and tool-augmented reasoning
  16. AirGapAgent: Protecting Privacy-Conscious Conversational AgentsLLM agents and tool use → Agent threats, guardrails and governance
  17. Novel Actor-Critic Algorithm for Robust Decision Making of CAV under Delays and Loss of V2X DataDeep reinforcement learning methods → RL for autonomous driving and traffic
  18. ADELIE: Aligning Large Language Models on Information ExtractionLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  19. HC-Mamba: Vision MAMBA with Hybrid Convolutional Techniques for Medical Image SegmentationState-space sequence models (S4, Mamba) → Mamba for medical image analysis
  20. Discrepancy-based Diffusion Models for Lesion Detection in Brain MRIDiffusion models → Medical imaging and segmentation
  21. A Review on Discriminative Self-supervised Learning Methods in Computer VisionKnowledge distillation → General knowledge distillation methods
  22. Frequency-Assisted Mamba for Remote Sensing Image Super-ResolutionState-space sequence models (S4, Mamba) → Point clouds, detection and remote sensing
  23. VisionGraph: Leveraging Large Multimodal Models for Graph Theory Problems in Visual ContextLLM reasoning → Multimodal reasoning +1
  24. Fast LiDAR Upsampling using Conditional Diffusion ModelsDiffusion models → 3D, point cloud and scene generation
  25. FlexEControl: Flexible and Efficient Multimodal Control for Text-to-Image GenerationDiffusion models → Image generation, text-to-image and editing
  26. Explanation as a Watermark: Towards Harmless and Multi-bit Model Ownership Verification via Watermarking Feature AttributionLLM safety and security → Watermarking generated content and models
  27. ACORN: Aspect-wise Commonsense Reasoning Explanation EvaluationLLM reasoning → Reasoning benchmarks and evaluation
  28. Variational Schr"odinger Diffusion ModelsDiffusion models → Diffusion foundations and sampling
  29. SemiCD-VL: Visual-Language Model Guidance Makes Better Semi-supervised Change DetectorMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  30. CourseGPT-zh: an Educational Large Language Model Based on Knowledge Distillation Incorporating Prompt OptimizationKnowledge distillation → Knowledge distillation for LLMs
  31. Teacher-Student Network for Real-World Face Super-Resolution with Progressive Embedding of Edge InformationKnowledge distillation → General knowledge distillation methods
  32. Chain of Thoughtlessness? An Analysis of CoT in PlanningLLM reasoning → Prompting and chain-of-thought reasoning
  33. Red-Teaming for Inducing Societal Bias in Large Language ModelsLLM safety and security → Safety alignment, refusal and guardrails
  34. An efficient machine learning approach for extracting eSports players distinguishing features and classifying their skill levels using symbolic transfer entropy and consensus nested cross validation
  35. A digital twin based approach to smart lighting design
  36. Compressed Latent Replays for Lightweight Continual Learning on Spiking Neural Networks
  37. Synthetic Data in Radiological Imaging: Current State and Future Outlook
  38. Controlling Chaos Using Edge Computing Hardware
  39. TSB: Tiny Shared Block for Efficient DNN Deployment on NVCIM Accelerators
  40. Multimodal Approach for Harmonized System Code Prediction
  41. Finite Groundings for ASP with Functions: A Journey through Consistency
  42. Untargeted Adversarial Attack on Knowledge Graph Embeddings
  43. Dynamic GNNs for Precise Seizure Detection and Classification from EEG Data
  44. ECG-SMART-NET: A Deep Learning Architecture for Precise ECG Diagnosis of Occlusion Myocardial Infarction
  45. Detection of Sleep Oxygen Desaturations from Electroencephalogram Signals
  46. Graphon Mean Field Games with a Representative Player: Analysis and Learning Algorithm
  47. Interpretable Cross-Examination Technique (ICE-T): Using highly informative features to boost LLM performance
  48. Malayalam Sign Language Identification using Finetuned YOLOv8 and Computer Vision Techniques
  49. Lightweight Spatial Modeling for Combinatorial Information Extraction From Documents
  50. ChatSOS: Vector Database Augmented Generative Question Answering Assistant in Safety Engineering
  51. Automated Conversion of Static to Dynamic Scheduler via Natural Language
  52. Multi-level Shared Knowledge Guided Learning for Knowledge Graph Completion
  53. Towards Less Biased Data-driven Scoring with Deep Learning-Based End-to-end Database Search in Tandem Mass Spectrometry
  54. CloudSense: A Model for Cloud Type Identification using Machine Learning from Radar data
  55. Physics-Enhanced Machine Learning: a position paper for dynamical systems investigations
  56. TrafficGPT: Towards Multi-Scale Traffic Analysis and Generation with Spatial-Temporal Agent Framework
  57. Few-Shot Class Incremental Learning via Robust Transformer Approach
  58. Real-Time Pill Identification for the Visually Impaired Using Deep Learning
  59. Estimating Noisy Class Posterior with Part-level Labels for Noisy Label Learning
  60. AFEN: Respiratory Disease Classification using Ensemble Learning
  61. Poser: Unmasking Alignment Faking LLMs by Manipulating Their Internals
  62. Vidur: A Large-Scale Simulation Framework For LLM Inference
  63. Cross-Modality Translation with Generative Adversarial Networks to Unveil Alzheimer's Disease Biomarkers
  64. Taking a Moment for Distributional Robustness
  65. Automated Program Repair: Emerging trends pose and expose problems for benchmarks
  66. GDGS: Gradient Domain Gaussian Splatting for Sparse Representation of Radiance Fields
  67. Large Language Model Enhanced Machine Learning Estimators for Classification
  68. Analysis and prevention of AI-based phishing email attacks
  69. Searching for Programmatic Policies in Semantic Spaces
  70. Towards Invariant Time Series Forecasting in Smart Cities
  71. How Inverse Conditional Flows Can Serve as a Substitute for Distributional Regression
  72. Adversary-Guided Motion Retargeting for Skeleton Anonymization
  73. Latent Variable Double Gaussian Process Model for Decoding Complex Neural Data
  74. EarthMatch: Iterative Coregistration for Fine-grained Localization of Astronaut Photography
  75. Mitigating Exaggerated Safety in Large Language Models
  76. Fishing for Magikarp: Automatically Detecting Under-trained Tokens in Large Language Models
  77. Initialization is Critical to Whether Transformers Fit Composite Functions by Reasoning or Memorizing
  78. ASPIRE: Iterative Amortized Posterior Inference for Bayesian Inverse Problems
  79. Mutual information and the encoding of contingency tables
  80. Interpretability Needs a New Paradigm
  81. "They are uncultured": Unveiling Covert Harms and Social Threats in LLM Generated Conversations
  82. Krey`ol-MT: Building MT for Latin American, Caribbean and Colonial African Creole Languages
  83. Arctic-Embed: Scalable, Efficient, and Accurate Text Embedding Models
  84. Model Reconstruction Using Counterfactual Explanations: A Perspective From Polytope Theory
  85. LOC-ZSON: Language-driven Object-Centric Zero-Shot Object Retrieval and Navigation
  86. Geometry-Informed Distance Candidate Selection for Adaptive Lightweight Omnidirectional Stereo Vision with Fisheye Images
  87. Transfer-LMR: Heavy-Tail Driving Behavior Recognition in Diverse Traffic Scenarios
  88. Offline Model-Based Optimization via Policy-Guided Gradient Search
  89. The Effect of Model Size on LLM Post-hoc Explainability via LIME
  90. Benchmarking Educational Program Repair
  91. QuaLLM: An LLM-based Framework to Extract Quantitative Insights from Online Forums
  92. Distributed Least Squares in Small Space via Sketching and Bias Reduction
  93. Joint semi-supervised and contrastive learning enables domain generalization and multi-domain segmentation
  94. Multiplicative Dynamic Mode Decomposition
  95. Challenges for Responsible AI Design and Workflow Integration in Healthcare: A Case Study of Automatic Feeding Tube Qualification in Radiology
  96. Deep Learning Method to Predict Wound Healing Progress Based on Collagen Fibers in Wound Tissue
  97. Relevant Irrelevance: Generating Alterfactual Explanations for Image Classifiers
  98. Harmonizing Program Induction with Rate-Distortion Theory
  99. A Review on Fragment-based De Novo 2D Molecule Generation
  100. Smart Portable Computer
All 229
  1. Learning Social Graph for Inactive User Recommendation
  2. OpenESS: Event-based Semantic Scene Understanding with Open Vocabularies
  3. Multi-Modal Data-Efficient 3D Scene Understanding for Autonomous Driving
  4. You Only Cache Once: Decoder-Decoder Architectures for Language Models
  5. Open Source Language Models Can Provide Feedback: Evaluating LLMs' Ability to Help Students Using GPT-4-As-A-Judge
  6. LLMs with Personalities in Multi-issue Negotiation Games
  7. SVDD Challenge 2024: A Singing Voice Deepfake Detection Challenge Evaluation Plan
  8. Deep learning-based variational autoencoder for classification of quantum and classical states of light
  9. BenthicNet: A global compilation of seafloor images for deep learning applications
  10. An LSTM-Based Chord Generation System Using Chroma Histogram Representations
  11. Cellular Traffic Prediction Using Online Prediction Algorithms
  12. EVA-X: A Foundation Model for General Chest X-ray Analysis with Self-supervised Learning
  13. Stability and Performance Analysis of Discrete-Time ReLU Recurrent Neural Networks
  14. RACH Traffic Prediction in Massive Machine Type Communications
  15. DiskGNN: Bridging I/O Efficiency and Model Accuracy for Out-of-Core GNN Training
  16. Conv-Basis: A New Paradigm for Efficient Attention Inference and Gradient Computation in Transformers
  17. Anomaly Detection in Certificate Transparency Logs
  18. Hybrid Quantum Graph Neural Network for Molecular Property Prediction
  19. CARE-SD: Classifier-based analysis for recognizing and eliminating stigmatizing and doubt marker labels in electronic health records: model development and validation
  20. Discretely Beyond 1/e: Guided Combinatorial Algorithms for Submodular Maximization
  21. SINBAD: Saliency-informed detection of breakage caused by ad blocking
  22. Full error analysis of the random deep splitting method for nonlinear parabolic PDEs and PIDEs
  23. Is Transductive Learning Equivalent to PAC Learning?
  24. A score-based particle method for homogeneous Landau equation
  25. Machine Learning Assisted Dynamical Classification of Trans-Neptunian Objects
  26. Encoder-Decoder Framework for Interactive Free Verses with Generation with Controllable High-Quality Rhyming
  27. A Survey on Occupancy Perception for Autonomous Driving: The Information Fusion Perspective
  28. Custom Gradient Estimators are Straight-Through Estimators in Disguise
  29. Picking watermarks from noise (PWFN): an improved robust watermarking model against intensive distortions
  30. Data-Error Scaling Laws in Machine Learning on Combinatorial Mutation-prone Sets: Proteins and Small Molecules
  31. ProbRadarM3F: mmWave Radar based Human Skeletal Pose Estimation with Probability Map Guided Multi-Format Feature Fusion
  32. Motion Capture Analysis of Verb and Adjective Types in Austrian Sign Language
  33. Selective Classification Under Distribution Shifts
  34. The Potential and Implications of Generative AI on HCI Education
  35. Hybrid Convolutional Neural Networks with Reliability Guarantee
  36. Identifying every building's function in large-scale urban areas with multi-modality remote-sensing data
  37. Multi-scale Bottleneck Transformer for Weakly Supervised Multimodal Violence Detection
  38. XAMPLER: Learning to Retrieve Cross-Lingual In-Context Examples
  39. Uncertainty quantification in metric spaces
  40. QFMTS: Generating Query-Focused Summaries over Multi-Table Inputs
  41. Biology-inspired joint distribution neurons based on Hierarchical Correlation Reconstruction allowing for multidirectional propagation of values and densities
  42. Approximation properties relative to continuous scale space for hybrid discretizations of Gaussian derivative operators
  43. Robust deep learning from weakly dependent data
  44. Concerns on Bias in Large Language Models when Creating Synthetic Personae
  45. Power Variable Projection for Initialization-Free Large-Scale Bundle Adjustment
  46. Sparse-PGD: A Unified Framework for Sparse Adversarial Perturbations Generation
  47. Designing Skill-Compatible AI: Methodologies and Frameworks in Chess
  48. Conversational Topic Recommendation in Counseling and Psychotherapy with Decision Transformer and Large Language Models
  49. Real-Time Motion Detection Using Dynamic Mode Decomposition
  50. Seeds of Stereotypes: A Large-Scale Textual Analysis of Race and Gender Associations with Diseases in Online Sources
  51. Reviewing Intelligent Cinematography: AI research for camera-based video production
  52. Multi-fidelity Hamiltonian Monte Carlo
  53. Mitigating Bias Using Model-Agnostic Data Attribution
  54. StyleMamba : State Space Model for Efficient Text-driven Image Style Transfer
  55. Learning Structural Causal Models through Deep Generative Models: Methods, Guarantees, and Challenges
  56. TGTM: TinyML-based Global Tone Mapping for HDR Sensors
  57. Concrete Dense Network for Long-Sequence Time Series Clustering
  58. The Entropy Enigma: Success and Failure of Entropy Minimization
  59. M2DNeRF: Multi-Modal Decomposition NeRF with 3D Feature Fields
  60. TENet: Targetness Entanglement Incorporating with Multi-Scale Pooling and Mutually-Guided Fusion for RGB-E Object Tracking
  61. HMANet: Hybrid Multi-Axis Aggregation Network for Image Super-Resolution
  62. Bridging the Gap Between Saliency Prediction and Image Quality Assessment
  63. Health Index Estimation Through Integration of General Knowledge with Unsupervised Learning
  64. An Artificial Intelligence Approach for Interpreting Creative Combinational Designs
  65. Dynamic Data Layout Optimization with Worst-case Guarantees
  66. Overcoming Anchoring Bias: The Potential of AI and XAI-based Decision Support
  67. End-to-End Semi-Supervised approach with Modulated Object Queries for Table Detection in Documents
  68. Communication-Efficient Collaborative Perception via Information Filling with Codebook
  69. P-ICL: Point In-Context Learning for Named Entity Recognition with Large Language Models
  70. Improving Long Text Understanding with Knowledge Distilled from Summarization Model
  71. Supervised Anomaly Detection for Complex Industrial Images
  72. A Sparse Tensor Generator with Efficient Feature Extraction
  73. Unsupervised Skin Feature Tracking with Deep Neural Networks
  74. Imprecise Probabilities Meet Partial Observability: Game Semantics for Robust POMDPs
  75. Harnessing the Power of MLLMs for Transferable Text-to-Image Person ReID
  76. Fault Identification Enhancement with Reinforcement Learning (FIERL)
  77. Developing trustworthy AI applications with foundation models
  78. DataSP: A Differential All-to-All Shortest Path Algorithm for Learning Costs and Predicting Paths with Context
  79. Fast Computation of Leave-One-Out Cross-Validation for k-NN Regression
  80. Delve into Base-Novel Confusion: Redundancy Exploration for Few-Shot Class-Incremental Learning
  81. Guiding adaptive shrinkage by co-data to improve regression-based prediction and feature selection
  82. Weakly-supervised Semantic Segmentation via Dual-stream Contrastive Learning of Cross-image Contextual Information
  83. Learning with Posterior Sampling for Revenue Management under Time-varying Demand
  84. Traj-LLM: A New Exploration for Empowering Trajectory Prediction with Pre-trained Large Language Models
  85. Imbalanced Graph Classification with Multi-scale Oversampling Graph Neural Networks
  86. HAGAN: Hybrid Augmented Generative Adversarial Network for Medical Image Synthesis
  87. Self-supervised Gait-based Emotion Representation Learning from Selective Strongly Augmented Skeleton Sequences
  88. Machine Learning-based NLP for Emotion Classification on a Cholera X Dataset
  89. GISR: Geometric Initialization and Silhouette-based Refinement for Single-View Robot Pose and Configuration Estimation
  90. FreeBind: Free Lunch in Unified Multimodal Space via Knowledge Fusion
  91. G"odel Number based Clustering Algorithm with Decimal First Degree Cellular Automata
  92. The Codecfake Dataset and Countermeasures for the Universally Detection of Deepfake Audio
  93. SCALA: Split Federated Learning with Concatenated Activations and Logit Adjustments
  94. Logical Negation Augmenting and Debiasing for Prompt-based Methods
  95. Enhancing Geometric Ontology Embeddings for EL++ with Negative Sampling and Deductive Closure Filtering
  96. MIPI 2024 Challenge on Demosaic for HybridEVS Camera: Methods and Results
  97. Regime Learning for Differentiable Particle Filters
  98. Pedestrian Attribute Recognition as Label-balanced Multi-label Learning
  99. Explaining Clustering of Ecological Momentary Assessment Data Through Temporal and Feature Attention
  100. xMTrans: Temporal Attentive Cross-Modality Fusion Transformer for Long-Term Traffic Prediction
  101. Fine-tuning Pre-trained Named Entity Recognition Models For Indian Languages
  102. ChuXin: 1.6B Technical Report
  103. APrompt4EM: Augmented Prompt Tuning for Generalized Entity Matching
  104. DALK: Dynamic Co-Augmentation of LLMs and KG to answer Alzheimer's Disease Questions with Scientific Literature
  105. Proportion Estimation by Masked Learning from Label Proportion
  106. A Novel Technique for Query Plan Representation Based on Graph Neural Nets
  107. General Place Recognition Survey: Towards Real-World Autonomy
  108. A unified error analysis for randomized low-rank approximation with application to data assimilation
  109. Transformer Architecture for NetsDB
  110. DeepDamageNet: A two-step deep-learning model for multi-disaster building damage segmentation and classification using satellite imagery
  111. From LLMs to Actions: Latent Codes as Bridges in Hierarchical Robot Control
  112. Zero-shot LLM-guided Counterfactual Generation: A Case Study on NLP Model Evaluation
  113. Dual-Image Enhanced CLIP for Zero-Shot Anomaly Detection
  114. Empathy Through Multimodality in Conversational Interfaces
  115. Hypergraph-enhanced Dual Semi-supervised Graph Classification
  116. Exploring Vision Transformers for 3D Human Motion-Language Models with Motion Patches
  117. Inference With Combining Rules From Multiple Differentially Private Synthetic Datasets
  118. Test-Time Augmentation for Traveling Salesperson Problem
  119. When Foresight Pruning Meets Zeroth-Order Optimization: Efficient Federated Learning for Low-Memory Devices
  120. Large Language Models for Cyber Security: A Systematic Literature Review
  121. Multi-Label Out-of-Distribution Detection with Spectral Normalized Joint Energy
  122. Honeyfile Camouflage: Hiding Fake Files in Plain Sight
  123. Conditional Local Feature Encoding for Graph Neural Networks
  124. AttacKG+:Boosting Attack Knowledge Graph Construction with Large Language Models
  125. SVD-AE: Simple Autoencoders for Collaborative Filtering
  126. All in One Framework for Multimodal Re-identification in the Wild
  127. Is the House Ready For Sleeptime? Generating and Evaluating Situational Queries for Embodied Question Answering
  128. Learning Phonotactics from Linguistic Informants
  129. Detecting and Refining HiRISE Image Patches Obscured by Atmospheric Dust