mlsanityData to 14 Oct 2026

Papers

New on arXiv

Sat 7 Sep 2024

106 papers

  1. Causality-Driven Reinforcement Learning for Joint Communication and SensingDeep reinforcement learning methods → RL for energy, networks and operations
  2. Just ASR + LLM? A Study on Speech Large Language Models' Ability to Identify and Understand Speaker in Spoken DialogueLLM reasoning → Audio-language model reasoning
  3. Reinforcement Learning-Based Adaptive Load Balancing for Dynamic Cloud EnvironmentsDeep reinforcement learning methods → RL for energy, networks and operations
  4. Plug-and-Hide: Provable and Adjustable Diffusion Generative SteganographyDiffusion models → Robustness, privacy and adversarial aspects +1
  5. Flow-TSVAD: Target-Speaker Voice Activity Detection via Latent Flow MatchingDiffusion models → Audio, speech and music
  6. Reinforcement Learning for Rate Maximization in IRS-aided OWC NetworksDeep reinforcement learning methods → RL for energy, networks and operations
  7. Sample and Oracle Efficient Reinforcement Learning for MDPs with Linearly-Realizable Value FunctionsDeep reinforcement learning methods → RL theory and sample complexity
  8. Context-Aware Replanning with Pre-explored Semantic Map for Object NavigationMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  9. Reward-Directed Score-Based Diffusion Models via q-LearningDiffusion models → Diffusion and flow policies for robotics +1
  10. POINTS: Improving Your Vision-language Model with Affordable StrategiesMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  11. Exploring Straightforward Conversational Red-TeamingLLM safety and security → Prompt injection and agent security
  12. Cross-attention Inspired Selective State Space Models for Target Sound ExtractionState-space sequence models (S4, Mamba) → Speech and audio SSMs
  13. SpotActor: Training-Free Layout-Controlled Consistent Image GenerationDiffusion models → Image generation, text-to-image and editing
  14. Action is the primary key: a categorical framework for episodic memories and logical reasoningLLM reasoning → Reasoning benchmarks and evaluation
  15. Improving Deep Reinforcement Learning by Reducing the Chain Effect of Value and Policy ChurnDeep reinforcement learning methods → Deep RL algorithms and representations
  16. LoCa: Logit Calibration for Knowledge DistillationKnowledge distillation → General knowledge distillation methods
  17. Training-Free Style Consistent Image Synthesis with Condition and Mask Guidance in E-CommerceDiffusion models → 3D, point cloud and scene generation
  18. MuAP: Multi-step Adaptive Prompt Learning for Vision-Language Model with Missing ModalityMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  19. Multi-Conditioned Denoising Diffusion Probabilistic Model (mDDPM) for Medical Image SynthesisDiffusion models → Medical imaging and segmentation
  20. A Lightweight GAN-Based Image Fusion Algorithm for Visible and Infrared Images
  21. Electrooptical Image Synthesis from SAR Imagery Using Generative Adversarial Networks
  22. DiVA-DocRE: A Discriminative and Voice-Aware Paradigm for Document-Level Relation Extraction
  23. Constrained Multi-Layer Contrastive Learning for Implicit Discourse Relationship Recognition
  24. Introducing MeMo: A Multimodal Dataset for Memory Modelling in Multiparty Conversations
  25. TracrBench: Generating Interpretability Testbeds with Large Language Models
  26. Sentiment Informed Sentence BERT-Ensemble Algorithm for Depression Detection
  27. Good Idea or Not, Representation of LLM Could Tell
  28. Unlocking Potential Binders: Multimodal Pretraining DEL-Fusion for Denoising DNA-Encoded Libraries
  29. Property Neurons in Self-Supervised Speech Transformers
  30. Maximizing Relation Extraction Potential: A Data-Centric Study to Unveil Challenges and Opportunities
  31. A Delta-evaluation function for column permutation problems
  32. Single-snapshot machine learning for super-resolution of turbulence
  33. Nearest Neighbor CCP-Based Molecular Sequence Analysis
  34. MoistNet: Machine Vision-based Deep Learning Models for Wood Chip Moisture Content Measurement
  35. Learning with Shared Representations: Statistical Rates and Efficient Algorithms
  36. Training-free Zero-shot Composed Image Retrieval via Weighted Modality Fusion and Similarity
  37. Activation Function Optimization Scheme for Image Classification
  38. NGD converges to less degenerate solutions than SGD
  39. Efficient Training of Transformers for Molecule Property Prediction on Small-scale Datasets
  40. Unlocking the Potential of Model Calibration in Federated Learning
  41. Learning Joint Models of Prediction and Optimization
  42. Centralized Selection with Preferences in the Presence of Biases
  43. A Quantitative Approach for Evaluating Disease Focus and Interpretability of Deep Learning Models for Alzheimer's Disease Classification
  44. Defeasible Reasoning on Concepts
  45. Learning to Open and Traverse Doors with a Legged Manipulator
  46. Towards identifying Source credibility on Information Leakage in Digital Gadget Market
  47. Improving the Finite Sample Estimation of Average Treatment Effects using Double/Debiased Machine Learning with Propensity Score Calibration
  48. Fine-Grained Representation Learning via Multi-Level Contrastive Learning without Class Priors
  49. Sequential Classification of Misinformation
  50. AdaptiveFusion: Adaptive Multi-Modal Multi-View Fusion for 3D Human Body Reconstruction
  51. Deep Computer Vision for Solar Physics Big Data: Opportunities and Challenges
  52. FedModule: A Modular Federated Learning Framework
  53. Rethinking The Training And Evaluation of Rich-Context Layout-to-Image Generation
  54. SPIRIT: Low Power Seizure Prediction using Unsupervised Online-Learning and Zoom Analog Frontends
  55. Reducing Events to Augment Log-based Anomaly Detection Models: An Empirical Study
  56. Achieving Peak Performance for Large Language Models: A Systematic Review
  57. MILE: A Mutation Testing Framework of In-Context Learning Systems
  58. NASH: Neural Architecture and Accelerator Search for Multiplication-Reduced Hybrid Models
  59. Metadata augmented deep neural networks for wild animal classification
  60. FreeAugment: Data Augmentation Search Across All Degrees of Freedom
  61. Top-GAP: Integrating Size Priors in CNNs for more Interpretability, Robustness, and Bias Mitigation
  62. SSFam: Scribble Supervised Salient Object Detection Family
  63. Generalized Learning of Coefficients in Spectral Graph Convolutional Networks
  64. Power Line Aerial Image Restoration under dverse Weather: Datasets and Baselines
  65. HULLMI: Human vs LLM identification with explainability
  66. Local-Prompt: Extensible Local Prompts for Few-Shot Out-of-Distribution Detection
  67. Phrase-Level Adversarial Training for Mitigating Bias in Neural Network-based Automatic Essay Scoring
  68. Beyond One-Time Validation: A Framework for Adaptive Validation of Prognostic and Diagnostic AI-based Medical Devices
  69. forester: A Tree-Based AutoML Tool in R
  70. Selective Self-Rehearsal: A Fine-Tuning Approach to Improve Generalization in Large Language Models
  71. Component Fourier Neural Operator for Singularly Perturbed Differential Equations
  72. Optimization Hyper-parameter Laws for Large Language Models
  73. Scalable Task Planning via Large Language Models and Structured World Representations
  74. Untie the Knots: An Efficient Data Augmentation Strategy for Long-Context Pre-Training in Language Models
  75. Medical Image Segmentation via Single-Source Domain Generalization with Random Amplitude Spectrum Synthesis
  76. Cross-Dataset Gaze Estimation by Evidential Inter-intra Fusion
  77. Training-Free Point Cloud Recognition Based on Geometric and Semantic Information Fusion
  78. Adaptative Context Normalization: A Boost for Deep Learning in Image Processing
  79. SGSeg: Enabling Text-free Inference in Language-guided Segmentation of Chest X-rays via Self-guidance
  80. Unsupervised Adaptive Normalization
  81. Fisheye-GS: Lightweight and Extensible Gaussian Splatting Module for Fisheye Cameras
  82. Explicit Mutual Information Maximization for Self-Supervised Learning
  83. Reward Guidance for Reinforcement Learning Tasks Based on Large Language Models: The LMGT Framework
  84. GRVFL-MV: Graph Random Vector Functional Link Based on Multi-View Learning
  85. Enhancing Image Authenticity Detection: Swin Transformers and Color Frame Analysis for CGI vs. Real Images
  86. Up-sampling-only and Adaptive Mesh-based GNN for Simulating Physical Systems
  87. CrysAtom: Distributed Representation of Atoms for Crystal Property Prediction
  88. Swin Transformer for Robust Differentiation of Real and Synthetic Images: Intra- and Inter-Dataset Analysis
  89. A Sample Efficient Alternating Minimization-based Algorithm For Robust Phase Retrieval
  90. VidLPRO: A underlineVideo-underlineLanguage underlinePre-training Framework for underlineRobotic and Laparoscopic Surgery
  91. Urban traffic analysis and forecasting through shared Koopman eigenmodes
  92. NapTune: Efficient Model Tuning for Mood Classification using Previous Night's Sleep Measures along with Wearable Time-series
  93. A Comprehensive Survey on Evidential Deep Learning and Its Applications
  94. Cross-Organ Domain Adaptive Neural Network for Pancreatic Endoscopic Ultrasound Image Segmentation
  95. Unleashing the Power of Generic Segmentation Models: A Simple Baseline for Infrared Small Target Detection
  96. Algorithmic Scenario Generation as Quality Diversity Optimization
  97. Harnessing physics-informed operators for high-dimensional reliability analysis problems
  98. Enhancing Deep Learning with Optimized Gradient Descent: Bridging Numerical Methods and Neural Network Training
  99. A Multi-scenario Attention-based Generative Model for Personalized Blood Pressure Time Series Forecasting
  100. Late Chunking: Contextual Chunk Embeddings Using Long-Context Embedding Models
All 106
  1. Dual-stream Feature Augmentation for Domain Generalization
  2. Hierarchical Sparse Representation Clustering for High-Dimensional Data Streams
  3. C2F-CHART: A Curriculum Learning Approach to Chart Classification
  4. Neural Augmentation Based Panoramic High Dynamic Range Stitching
  5. QueryBuilder: Human-in-the-Loop Query Development for Information Retrieval
  6. IIFE: Interaction Information Based Automated Feature Engineering