mlsanityData to 14 Oct 2026

Papers

New on arXiv

Wed 1 Jan 2025

127 papers

  1. SmartSpatial: Enhancing the 3D Spatial Arrangement Capabilities of Stable Diffusion Models and Introducing a Novel 3D Spatial Evaluation FrameworkDiffusion models → Image generation, text-to-image and editing
  2. 2.5 Years in Class: A Multimodal Textbook for Vision-Language PretrainingMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  3. Cached Adaptive Token Merging: Dynamic Token Reduction and Redundant Computation Elimination in Diffusion ModelDiffusion models → Diffusion foundations and sampling +1
  4. Diffusion Prism: Enhancing Diversity and Morphology Consistency in Mask-to-Image DiffusionDiffusion models → Diffusion foundations and sampling
  5. A Novel Diffusion Model for Pairwise Geoscience Data Generation with Unbalanced Training DatasetDiffusion models → Flow matching, time series and science
  6. Hierarchical Vision-Language Alignment for Text-to-Image Generation via Diffusion ModelsMultimodal LLMs / vision-language models → Image editing and quality assessment +1
  7. Diffusion Policies for Generative Modeling of Spacecraft TrajectoriesDiffusion models → Diffusion and flow policies for robotics
  8. β-DQN: Improving Deep Q-Learning By Evolving the BehaviorDeep reinforcement learning methods → Deep RL algorithms and representations
  9. Aligning LLMs with Domain Invariant Reward ModelsLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
  10. Population Aware Diffusion for Time Series GenerationDiffusion models → Flow matching, time series and science
  11. Large Language Model Based Multi-Agent System Augmented Complex Event Processing Pipeline for Internet of Multimedia ThingsLLM agents and tool use → General LLM agent frameworks and benchmarks
  12. Diversity Optimization for Travelling Salesman Problem via Deep Reinforcement LearningDeep reinforcement learning methods → RL for games and combinatorial optimization
  13. Agentic Systems: A Guide to Transforming Industries with Vertical AI AgentsLLM agents and tool use → General LLM agent frameworks and benchmarks
  14. TrustRAG: Enhancing Robustness and Trustworthiness in Retrieval-Augmented GenerationRetrieval-augmented generation → Privacy and security of RAG
  15. Exploring Structured Semantic Priors Underlying Diffusion Score for Test-time AdaptationDiffusion models → Diffusion foundations and sampling
  16. Interactionalism: Re-Designing Higher Learning for the Large Language Agent EraLLM agents and tool use → Educational agents and math problem solving
  17. Hybridising Reinforcement Learning and Heuristics for Hierarchical Directed Arc Routing ProblemsDeep reinforcement learning methods → RL for games and combinatorial optimization
  18. IllusionBench+: A Large-scale and Comprehensive Benchmark for Visual Illusion Understanding in Vision-Language ModelsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  19. LLM+AL: Bridging Large Language Models and Action Languages for Complex Reasoning about ActionsLLM reasoning → Reasoning benchmarks and evaluation
  20. LLM-Powered Multi-Agent System for Automated Crypto Portfolio ManagementLLM agents and tool use → Financial trading and forecasting agents
  21. Reasoning-Oriented and Analogy-Based Methods for Locating and Editing in Zero-Shot Event-Relational ReasoningLLM reasoning → Prompting and chain-of-thought reasoning
  22. VoiceRestore: Flow-Matching Transformers for Speech Recording Quality RestorationDiffusion models → Audio, speech and music
  23. LENS-XAI: Redefining Lightweight and Explainable Network Security through Knowledge Distillation and Variational Autoencoders for Scalable Intrusion Detection in CybersecurityKnowledge distillation → Detection and dense prediction distillation
  24. Decoding the Flow: CauseMotion for Emotional Causality Analysis in Long-form ConversationsLLM reasoning → Audio-language model reasoning
  25. HCMA-UNet: A Hybrid CNN-Mamba UNet with Axial Self-Attention for Efficient Breast Cancer SegmentationState-space sequence models (S4, Mamba) → Mamba for medical image analysis
  26. Beyond Text: Implementing Multimodal Large Language Model-Powered Multi-Agent Systems Using a No-Code PlatformMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning +1
  27. DIVE: Diversified Iterative Self-ImprovementSynthetic data and self-improvement for LLMs → Self-rewarding alignment and self-training
  28. Rethinking Addressing in Language Models via Contexualized Equivariant Positional EncodingLLM reasoning → Test-time compute and efficient thinking
  29. Advancing Trustworthy AI for Sustainable Development: Recommendations for Standardising AI Incident Reporting
  30. Enhancing Supply Chain Resilience with Metaverse and ChatGPT Technologies
  31. VERITAS: Verifying the Performance of AI-native Transceiver Actions in Base-Stations
  32. Boosting the Accuracy of Stock Market Prediction via Multi-Layer Hybrid MTL Structure
  33. Breaking Through the Spike: Spike Window Decoding for Accelerated and Precise Automatic Speech Recognition
  34. AI-ANNE: (A) (N)eural (N)et for (E)xploration: Transferring Deep Learning Models onto Microcontrollers and Embedded Systems
  35. SurfPatch: Enabling Patch Matching for Exploratory Stream Surface Visualization
  36. HMM-LSTM Fusion Model for Economic Forecasting
  37. Communication Efficient Cooperative Edge AI via Event-Triggered Computation Offloading
  38. Multi-Center Study on Deep Learning-Assisted Detection and Classification of Fetal Central Nervous System Anomalies Using Ultrasound Imaging
  39. Probing Equivariance and Symmetry Breaking in Convolutional Networks
  40. Unraveling Indirect In-Context Learning Using Influence Functions
  41. Augmented Contrastive Clustering with Uncertainty-Aware Prototyping for Time Series Test Time Adaptation
  42. Balance-aware Sequence Sampling Makes Multi-modal Learning Better
  43. CoordFlow: Coordinate Flow for Pixel-wise Neural Video Representation
  44. Optimal Sampling for Generalized Linear Model under Measurement Constraint with Surrogate Variables
  45. On the Implementation of a Bayesian Optimization Framework for Interconnected Systems
  46. OASIS Uncovers: High-Quality T2I Models, Same Old Stereotypes
  47. Uncovering Memorization Effect in the Presence of Spurious Correlations
  48. Enhancing Early Diabetic Retinopathy Detection through Synthetic DR1 Image Generation: A StyleGAN3 Approach
  49. Prior Lessons of Incremental Dialogue and Robot Action Management for the Age of Language Models
  50. Efficient Unsupervised Shortcut Learning Detection and Mitigation in Transformers
  51. Multiscaled Multi-Head Attention-based Video Transformer Network for Hand Gesture Recognition
  52. Tight Constraint Prediction of Six-Degree-of-Freedom Transformer-based Powered Descent Guidance
  53. On the Low-Complexity of Fair Learning for Combinatorial Multi-Armed Bandit
  54. Aligning Netlist to Source Code using SynAlign
  55. Geometry matters: insights from Ollivier Ricci Curvature and Ricci Flow into representational alignment through Ollivier-Ricci Curvature and Ricci Flow
  56. AutoPresent: Designing Structured Visuals from Scratch
  57. U-GIFT: Uncertainty-Guided Firewall for Toxic Speech in Few-Shot Scenario
  58. Text2Earth: Unlocking Text-driven Remote Sensing Image Generation with a Global-Scale Dataset and a Foundation Model
  59. Demystifying Online Clustering of Bandits: Enhanced Exploration Under Stochastic and Smoothed Adversarial Contexts
  60. Spatial Temporal Attention based Target Vehicle Trajectory Prediction for Internet of Vehicles
  61. Evaluating Time Series Foundation Models on Noisy Periodic Time Series
  62. Unfolding the Headline: Iterative Self-Questioning for News Retrieval and Timeline Summarization
  63. Representation in large language models
  64. FullTransNet: Full Transformer with Local-Global Attention for Video Summarization
  65. Improving Autoregressive Visual Generation with Cluster-Oriented Token Prediction
  66. FGAseg: Fine-Grained Pixel-Text Alignment for Open-Vocabulary Semantic Segmentation
  67. A Novel Approach using CapsNet and Deep Belief Network for Detection and Identification of Oral Leukopenia
  68. LUSIFER: Language Universal Space Integration for Enhanced Multilingual Embeddings with Large Language Models
  69. Large Language Models Are Read/Write Policy-Makers for Simultaneous Generation
  70. Negative to Positive Co-learning with Aggressive Modality Dropout
  71. DiffETM: Diffusion Process Enhanced Embedded Topic Model
  72. What is a Social Media Bot? A Global Comparison of Bot and Human Characteristics
  73. A Graphical Approach to State Variable Selection in Off-policy Learning
  74. Scale-wise Bidirectional Alignment Network for Referring Remote Sensing Image Segmentation
  75. FusionSORT: Fusion Methods for Online Multi-object Visual Tracking
  76. Distilled Lifelong Self-Adaptation for Configurable Systems
  77. Spatially-guided Temporal Aggregation for Robust Event-RGB Optical Flow Estimation
  78. Recognizing Artistic Style of Archaeological Image Fragments Using Deep Style Extrapolation
  79. An LLM-Empowered Adaptive Evolutionary Algorithm For Multi-Component Deep Learning Systems
  80. Embedding Style Beyond Topics: Analyzing Dispersion Effects Across Different Language Models
  81. Decoupling Knowledge and Reasoning in Transformers: A Modular Architecture with Generalized Cross-Attention
  82. SPARNet: Continual Test-Time Adaptation via Sample Partitioning Strategy and Anti-Forgetting Regularization
  83. Hardness of Learning Fixed Parities with Neural Networks
  84. MixSA: Training-free Reference-based Sketch Extraction via Mixture-of-Self-Attention
  85. Regression Guided Strategy to Automated Facial Beauty Optimization through Image Synthesis
  86. SLIDE: Integrating Speech Language Model with LLM for Spontaneous Spoken Dialogue Generation
  87. Automatic Text Pronunciation Correlation Generation and Application for Contextual Biasing
  88. Follow The Approximate Sparse Leader for No-Regret Online Sparse Linear Approximation
  89. Make Shuffling Great Again: A Side-Channel Resistant Fisher-Yates Algorithm for Protecting Neural Networks
  90. Multimodal Large Models Are Effective Action Anticipators
  91. Navigating Nuance: In Quest for Political Truth
  92. REM: A Scalable Reinforced Multi-Expert Framework for Multiplex Influence Maximization
  93. FitCF: A Framework for Automatic Feature Importance-guided Counterfactual Example Generation
  94. OpenGLT: A Comprehensive Benchmark of Graph Neural Networks for Graph-Level Tasks
  95. Beyond Words: AuralLLM and SignMST-C for Sign Language Production and Bidirectional Accessibility
  96. Residual connections provably mitigate oversmoothing in graph neural networks
  97. Enhancing Transformers for Generalizable First-Order Logical Entailment
  98. Less is More: Token Context-aware Learning for Object Tracking
  99. Beyond Static Datasets: A Behavior-Driven Entity-Specific Simulation to Overcome Data Scarcity and Train Effective Crypto Anti-Money Laundering Models
  100. FasterSTS: A Faster Spatio-Temporal Synchronous Graph Convolutional Networks for Traffic flow Forecasting
All 127
  1. An AI-powered Bayesian generative modeling approach for causal inference in observational studies
  2. Ensuring superior learning outcomes and data security for authorized learner
  3. Foreground-Covering Prototype Generation and Matching for SAM-Aided Few-Shot Segmentation
  4. Dynamics of Adversarial Attacks on Large Language Model-Based Search Engines
  5. Assessing the Distributional Fidelity of Synthetic Chest X-rays using the Embedded Characteristic Score
  6. AttriReBoost: A Gradient-Free Propagation Optimization Method for Cold Start Mitigation in Attribute Missing Graphs
  7. Experimental Demonstration of an Optical Neural PDE Solver via On-Chip PINN Training
  8. Towards End-to-End Neuromorphic Event-based 3D Object Reconstruction Without Physical Priors
  9. RORem: Training a Robust Object Remover with Human-in-the-Loop
  10. Learning Physically Interpretable Atmospheric Models from Data with WSINDy
  11. DDD: Discriminative Difficulty Distance for plant disease diagnosis
  12. On Importance of Layer Pruning for Smaller BERT Models and Low Resource Languages
  13. Enhancing Unsupervised Feature Selection via Double Sparsity Constrained Optimization
  14. Automatic Construction of Pattern Classifiers Capable of Continuous Incremental Learning and Unlearning Tasks Based on Compact-Sized Probabilistic Neural Network
  15. eRevise+RF: A Writing Evaluation System for Assessing Student Essay Revisions and Providing Formative Feedback
  16. CODEOFCONDUCT at Multilingual Counterspeech Generation: A Context-Aware Model for Robust Counterspeech Generation in Low-Resource Languages
  17. KAN KAN Buff Signed Graph Neural Networks?
  18. Everywhere Attack: Attacking Locally and Globally to Boost Targeted Transferability
  19. Kolmogorov GAM Networks are all you need!
  20. ResKoopNet: Learning Koopman Representations for Complex Dynamics with Spectral Residuals
  21. Knowledge-Guided Prompt Learning for Deepfake Facial Image Detection
  22. PANDA -- Paired Anti-hate Narratives Dataset from Asia: Using an LLM-as-a-Judge to Create the First Chinese Counterspeech Dataset
  23. Cost and Reward Infused Metric Elicitation
  24. Beyond Model Scale Limits: End-Edge-Cloud Federated Learning with Self-Rectified Knowledge Agglomeration
  25. Adjoint sharding for very long context training of state space models
  26. Labels Generated by Large Language Models Help Measure People's Empathy in Vitro
  27. IGC: Integrating a Gated Calculator into an LLM to Solve Arithmetic Tasks Reliably and Efficiently