mlsanityData to 14 Oct 2026

Papers

New on arXiv

Sun 24 Nov 2024

146 papers

  1. Evolution of Thought: Diverse and High-Quality Reasoning via Multi-Objective OptimizationLLM reasoning → Test-time compute and efficient thinking +1
  2. Reinforcement learning-enhanced genetic algorithm for wind farm layout optimizationDeep reinforcement learning methods → RL for energy, networks and operations
  3. Improving Medical Diagnostics with Vision-Language Models: Convex Hull-Based Uncertainty AnalysisMultimodal LLMs / vision-language models → Medical vision-language models
  4. Chameleon: Adaptive Caching and Scheduling for Many-Adapter LLM Inference EnvironmentsEfficient LLM inference and serving → Serving systems and request scheduling
  5. Is 'Right' Right? Enhancing Object Orientation Understanding in Multimodal Large Language Models through Egocentric Instruction TuningMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  6. AnySynth: Harnessing the Power of Image Synthetic Data Generation for Generalized Vision-Language TasksDiffusion models → Image generation, text-to-image and editing +1
  7. Multimodal Diffusion Transformer with Memory Bank for Scalable Long-Duration Talking Video GenerationDiffusion models → Audio, speech and music
  8. eFedLLM: Efficient LLM Inference Based on Federated LearningEfficient LLM inference and serving → Serving systems and request scheduling
  9. Exploring Performance Contrasts in TableQA: Step-by-Step Reasoning Boosts Bigger Language Models, Limits Smaller Language ModelsLLM reasoning → Knowledge- and tool-augmented reasoning
  10. PIANIST: Learning Partially Observable World Models with LLMs for Multi-Agent Decision MakingWorld models → World models for language agents +1
  11. Anda: Unlocking Efficient LLM Inference with a Variable-Length Grouped Activation Data FormatEfficient LLM inference and serving → KV cache quantization
  12. Gaussian Scenes: Pose-Free Sparse-View Scene Reconstruction using Depth-Enhanced Diffusion PriorsDiffusion models → 3D, point cloud and scene generation
  13. Partial Identifiability and Misspecification in Inverse Reinforcement LearningOffline RL and imitation learning from data → Inverse reinforcement learning +1
  14. MobileMamba: Lightweight Multi-Receptive Visual Mamba NetworkState-space sequence models (S4, Mamba) → Vision Mamba backbones
  15. Repurposing Image Diffusion Models for Training-Free Music Style Transfer on Mel-spectrogramsDiffusion models → Audio, speech and music
  16. From Laws to Motivation: Guiding Exploration through Law-Based Reasoning and RewardsLLM reasoning → Reinforcement learning for reasoning
  17. Hiding Communication Cost in Distributed LLM Training via Micro-batch Co-executionMixture-of-experts → Efficient MoE training and inference systems
  18. Self-Calibrated CLIP for Training-Free Open-Vocabulary SegmentationMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  19. Do LLMs Really Think Step-by-step In Implicit Reasoning?LLM reasoning → Prompting and chain-of-thought reasoning
  20. ResCLIP: Residual Attention for Training-free Dense Vision-language InferenceMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  21. VaLiD: Mitigating the Hallucination of Large Vision Language Models by Visual Layer Fusion Contrastive DecodingMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs
  22. Broad Critic Deep Actor Reinforcement Learning for Continuous ControlDeep reinforcement learning methods → RL theory and sample complexity
  23. A Method for Building Large Language Models with Predefined KV Cache CapacityEfficient LLM inference and serving → KV cache optimization
  24. MambaTrack: Exploiting Dual-Enhancement for Night UAV TrackingState-space sequence models (S4, Mamba) → Point clouds, detection and remote sensing
  25. Test-time Alignment-Enhanced Adapter for Vision-Language ModelsMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  26. DynamicAvatars: Accurate Dynamic Facial Avatars Reconstruction and Precise Editing with Diffusion ModelsDiffusion models → 3D, point cloud and scene generation
  27. Chain of Attack: On the Robustness of Vision-Language Models Against Transfer-Based Adversarial AttacksMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness
  28. Comparative Analysis of Diffusion Generative Models in Computational PathologyDiffusion models → Medical imaging and segmentation
  29. ROOT: VLM based System for Indoor Scene Understanding and BeyondMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  30. LLaMA-MoE v2: Exploring Sparsity of LLaMA from Perspective of Mixture-of-Experts with Post-TrainingMixture-of-experts → MoE large language models
  31. RAMIE: Retrieval-Augmented Multi-task Information Extraction with Large Language Models on Dietary SupplementsRetrieval-augmented generation → Medical and biomedical RAG
  32. DrugAgent: Automating AI-aided Drug Discovery Programming through LLM Multi-Agent CollaborationLLM agents and tool use → Medical and scientific domain agents
  33. Revisiting Your Memory: Reconstruction of Affect-Contextualized Memory via EEG-guided Audiovisual Generation
  34. Uncertainty-Aware Regularization for Image-to-Image Translation
  35. High-precision medical speech recognition through synthetic data and semantic correction: UNITED-MEDASR
  36. Less is More: Efficient Model Merging with Binary Task Switch
  37. LeMoLE: LLM-Enhanced Mixture of Linear Experts for Time Series Forecasting
  38. Brick Kiln Dataset for Pakistan's IGP Region Using AI
  39. TransFair: Transferring Fairness from Ocular Disease Classification to Progression Prediction
  40. Mapping waterways worldwide with deep learning
  41. A Survey of Recent Advances and Challenges in Deep Audio-Visual Correlation Learning
  42. Advancing Uncertain Combinatorics through Graphization, Hyperization, and Uncertainization: Fuzzy, Neutrosophic, Soft, Rough, and Beyond
  43. Hide in Plain Sight: Clean-Label Backdoor for Auditing Membership Inference
  44. LibraGrad: Balancing Gradient Flow for Universally Better Vision Transformer Attributions
  45. Motion-Aware Animatable Gaussian Avatars Deblurring
  46. FunGrasp: Functional Grasping for Diverse Dexterous Hands
  47. The Visual Counter Turing Test (VCT2): A Benchmark for Evaluating AI-Generated Image Detection and the Visual AI Index (VAI)
  48. Imagine and Seek: Improving Composed Image Retrieval with an Imagined Proxy
  49. An investigation into the performances of the Current state-of-the-art Naive Bayes, Non-Bayesian and Deep Learning Based Classifier for Phishing Detection: A Survey
  50. Iris: Integrating Language into Diffusion-based Monocular Depth Estimation
  51. Peritumoral Expansion Radiomics for Improved Lung Cancer Classification
  52. Performance Implications of Multi-Chiplet Neural Processing Units on Autonomous Driving Perception
  53. Multi-ToM: Evaluating Multilingual Theory of Mind Capabilities in Large Language Models
  54. Ensuring Fair LLM Serving Amid Diverse Applications
  55. Investigating Factuality in Long-Form Text Generation: The Roles of Self-Known and Self-Unknown
  56. Kleene algebra with commutativity conditions is undecidable
  57. DRIVE: Dual-Robustness via Information Variability and Entropic Consistency in Source-Free Unsupervised Domain Adaptation
  58. Stability properties of gradient flow dynamics for the symmetric low-rank matrix factorization problem
  59. Advancing Transformative Education: Generative AI as a Catalyst for Equity and Innovation
  60. CNNs for Style Transfer of Digital to Film Photography
  61. Adaptive Methods through the Lens of SDEs: Theoretical Insights on the Role of Noise
  62. Understanding Machine Learning Paradigms through the Lens of Statistical Thermodynamics: A tutorial
  63. Customer Lifetime Value Prediction with Uncertainty Estimation Using Monte Carlo Dropout
  64. Cross-organ Deployment of EOS Detection AI without Retraining: Feasibility and Limitation
  65. Bringing the Context Back into Object Recognition, Robustly
  66. Improving Pre-trained Self-Supervised Embeddings Through Effective Entropy Maximization
  67. Generative Prompt Internalization
  68. Making Images from Images: Interleaving Denoising and Transformation
  69. Deep Learning for automated multi-scale functional field boundaries extraction using multi-date Sentinel-2 and PlanetScope imagery: Case Study of Netherlands and Pakistan
  70. PromptHSI: Universal Hyperspectral Image Restoration with Vision-Language Modulated Frequency Adaptation
  71. A Tunable Despeckling Neural Network Stabilized via Diffusion Equation
  72. An AutoML-based approach for Network Intrusion Detection
  73. Enhancing Symbolic Regression and Universal Physics-Informed Neural Networks with Dimensional Analysis
  74. Selective Inference for Time-Varying Moderated Effects
  75. Bimanual Grasp Synthesis for Dexterous Robot Hands
  76. Highly Efficient and Unsupervised Framework for Moving Object Detection in Satellite Videos
  77. Navigating the Effect of Parametrization for Dimensionality Reduction
  78. Distribution-aware Online Continual Learning for Urban Spatio-Temporal Forecasting
  79. Evaluating Large Language Models for Causal Modeling
  80. Optimization-Driven Statistical Models of Anatomies using Radial Basis Function Shape Representation
  81. ExAL: An Exploration Enhanced Adversarial Learning Algorithm
  82. DUA-D2C: Dynamic Uncertainty Aware Method for Overfitting Remediation in Deep Learning
  83. Optimizing Brain Tumor Segmentation with MedNeXt: BraTS 2024 SSA and Pediatrics
  84. PanoLlama: Generating Endless and Coherent Panoramas with Next-Token-Prediction LLMs
  85. Ruppert-Polyak averaging for Stochastic Order Oracle
  86. Generalizable Single-view Object Pose Estimation by Two-side Generating and Matching
  87. SVTRv2: CTC Beats Encoder-Decoder Models in Scene Text Recognition
  88. FedQP: Towards Accurate Federated Learning using Quadratic Programming Guided Mutation
  89. Unveiling the Superior Paradigm: A Comparative Study of Source-Free Domain Adaptation and Unsupervised Domain Adaptation
  90. Unveil Inversion and Invariance in Flow Transformer for Versatile Image Editing
  91. Modality Alignment Meets Federated Broadcasting
  92. Creating Scalable AGI: the Open General Intelligence Framework
  93. Efficient and Private: Memorisation under differentially private parameter-efficient fine-tuning in language models
  94. Expert-elicitation method for non-parametric joint priors using normalizing flows
  95. Variable-size Symmetry-based Graph Fourier Transforms for image compression
  96. Is Training Data Quality or Quantity More Impactful to Small Language Model Performance?
  97. Lattice φ4 field theory as a multi-agent system of financial markets
  98. FastTrackTr:Towards Fast Multi-Object Tracking with Transformers
  99. A Novel Data Augmentation Tool for Enhancing Machine Learning Classification: A New Application of the Higher Order Dynamic Mode Decomposition for Improved Cardiac Disease Identification
  100. LRSAA: Large-scale Remote Sensing Image Target Recognition and Automatic Annotation
All 146
  1. Benchmarking Active Learning for NILM
  2. LoRA-Mini : Adaptation Matrices Decomposition and Selective Training
  3. Medical Slice Transformer: Improved Diagnosis and Explainability on 3D Medical Images with DINOv2
  4. A review on Machine Learning based User-Centric Multimedia Streaming Techniques
  5. PG-SLAM: Photo-realistic and Geometry-aware RGB-D SLAM in Dynamic Environments
  6. Symmetric Perception and Ordinal Regression for Detecting Scoliosis Natural Image
  7. M3-CVC: Controllable Video Compression with Multimodal Generative Models
  8. Data Lineage Inference: Uncovering Privacy Vulnerabilities of Dataset Pruning
  9. Beyond adaptive gradient: Fast-Controlled Minibatch Algorithm for large-scale optimization
  10. Multi-Token Enhancing for Vision Representation Learning
  11. ZeroGS: Training 3D Gaussian Splatting from Unposed Images
  12. Enhancing the automatic segmentation and analysis of 3D liver vasculature models
  13. Context-Aware Detection of Mixed Critical Events using Video Classification
  14. Corner2Net: Detecting Objects as Cascade Corners
  15. Text-Guided Coarse-to-Fine Fusion Network for Robust Remote Sensing Visual Question Answering
  16. Gradient Norm Regularization Second-Order Algorithms for Solving Nonconvex-Strongly Concave Minimax Problems
  17. Detecting Turkish Synonyms Used in Different Time Periods
  18. LLM Online Spatial-temporal Signal Reconstruction Under Noise
  19. Integrating Deep Metric Learning with Coreset for Active Learning in 3D Segmentation
  20. Advanced Learning-Based Inter Prediction for Future Video Coding
  21. Decoding Urban Industrial Complexity: Enhancing Knowledge-Driven Insights via IndustryScopeGPT
  22. PR-MIM: Delving Deeper into Partial Reconstruction in Masked Image Modeling
  23. Beyond Data Scarcity: A Frequency-Driven Framework for Zero-Shot Forecasting
  24. PEnG: Pose-Enhanced Geo-Localisation
  25. Proceedings of the 6th International Workshop on Reading Music Systems
  26. LTCF-Net: A Transformer-Enhanced Dual-Channel Fourier Framework for Low-Light Image Restoration
  27. AnyEdit: Mastering Unified High-Quality Image Editing for Any Idea
  28. TableTime: Reformulating Time Series Classification as Training-Free Table Understanding with Large Language Models
  29. Enhancing Few-Shot Out-of-Distribution Detection with Gradient Aligned Context Optimization
  30. Development of Pre-Trained Transformer-based Models for the Nepali Language
  31. Fusion Matters: Learning Fusion in Deep Click-through Rate Prediction Models
  32. OccludeNet: A Causal Journey into Mixed-View Actor-Centric Video Action Recognition under Occlusions
  33. GSurf: Learning Signed Distance Fields from Splatting Opaque Gaussians for High-quality 3D Reconstruction
  34. Research on Effectiveness Evaluation and Optimization of Baseball Teaching Method Based on Machine Learning
  35. Learning Algorithm Hyperparameters for Fast Parametric Convex Optimization
  36. Tackling Data Heterogeneity in Federated Time Series Forecasting
  37. Understanding Student Acceptance, Trust, and Attitudes Toward AI-Generated Images for Educational Purposes
  38. Nimbus: Secure and Efficient Two-Party Inference for Transformers
  39. Fixing the Perspective: A Critical Examination of Zero-1-to-3
  40. Editable-DeepSC: Reliable Cross-Modal Semantic Communications for Facial Editing
  41. Deep Sparse Latent Feature Models for Knowledge Graph Completion
  42. State-Space Large Audio Language Models
  43. Disentangling the Complex Multiplexed DIA Spectra in De Novo Peptide Sequencing
  44. Towards RAW Object Detection in Diverse Conditions
  45. Can a Large Language Model Learn Matrix Functions In Context?
  46. Quantile deep learning models for multi-step ahead time series prediction