mlsanityData to 14 Oct 2026

Papers

New on arXiv

Sun 6 Jul 2025

162 papers

  1. Enhancing Spatial Reasoning in Vision-Language Models via Chain-of-Thought Prompting and Reinforcement LearningLLM reasoning → Spatial and embodied reasoning +1
  2. LoRA Is Slower Than You ThinkLLM reasoning → Test-time compute and efficient thinking
  3. Mass-Scale Analysis of In-the-Wild Conversations Reveals Complexity Bounds on LLM JailbreakingLLM safety and security → Jailbreaking
  4. FB-Diff: Fourier Basis-guided Diffusion for Temporal Interpolation of 4D Medical ImagingDiffusion models → Medical imaging and segmentation
  5. DP-Fusion: Token-Level Differentially Private Inference for Large Language ModelsLLM safety and security → Membership inference attacks
  6. VLM-TDP: VLM-guided Trajectory-conditioned Diffusion Policy for Robust Long-Horizon ManipulationDiffusion models → Diffusion and flow policies for robotics
  7. FA: Forced Prompt Learning of Vision-Language Models for Out-of-Distribution DetectionMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  8. MVL-Loc: Leveraging Vision-Language Model for Generalizable Multi-Scene Camera RelocalizationMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  9. Unveiling the Potential of Diffusion Large Language Model in Controllable GenerationLLM agents and tool use → General LLM agent frameworks and benchmarks
  10. README: Robust Error-Aware Digital Signature Framework via Deep Watermarking ModelLLM safety and security → Watermarking generated content and models
  11. Source Attribution in Retrieval-Augmented GenerationRetrieval-augmented generation → RAG robustness and adaptive retrieval
  12. Anomalous Decision Discovery using Inverse Reinforcement LearningOffline RL and imitation learning from data → Imitation and offline RL for driving +1
  13. Agentic Distributed ComputingLLM agents and tool use → General LLM agent frameworks and benchmarks
  14. Think Twice Before You Judge: Mixture of Dual Reasoning Experts for Multimodal Sarcasm DetectionLLM reasoning → Multimodal reasoning
  15. ESSA: Evolutionary Strategies for Scalable AlignmentLLM reasoning → Reinforcement learning for reasoning +1
  16. SimLauncher: Launching Sample-Efficient Real-world Robotic Reinforcement Learning via Simulation Pre-trainingDeep reinforcement learning methods → RL for robot locomotion and manipulation
  17. DreamVLA: A Vision-Language-Action Model Dreamed with Comprehensive World KnowledgeVision-language-action models → World model-based VLA
  18. Street design and driving behavior: evidence from a large-scale study in Milan, Amsterdam, and DubaiEnd-to-end autonomous driving → VLMs for autonomous driving
  19. Multimedia Verification Through Multi-Agent Deep Research Multimodal Large Language ModelsMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness +1
  20. MVNet: Hyperspectral Remote Sensing Image Classification Based on Hybrid Mamba-Transformer Vision Backbone ArchitectureState-space sequence models (S4, Mamba) → Hyperspectral image analysis with Mamba
  21. Convergence and Sample Complexity of First-Order Methods for Agnostic Reinforcement LearningDeep reinforcement learning methods → RL theory and sample complexity
  22. Sat2City: 3D City Generation from A Single Satellite Image with Cascaded Latent DiffusionDiffusion models → 3D, point cloud and scene generation
  23. The Agency Gap in AI-Supported Writing: How Reactive and Proactive Agent Designs Shape Multimodal ReasoningLLM reasoning → Reasoning benchmarks and evaluation
  24. Inverse Reinforcement Learning using Revealed Preferences and Passive Stochastic OptimizationOffline RL and imitation learning from data → Inverse reinforcement learning +1
  25. Does Learning Mathematical Problem-Solving Generalize to Broader Reasoning?LLM reasoning → Mathematical reasoning
  26. DC-Mamber: A Dual Channel Prediction Model based on Mamba and Linear Transformer for Multivariate Time Series ForecastingState-space sequence models (S4, Mamba) → Time series forecasting with SSMs
  27. Multi-Modal Semantic Parsing for the Interpretation of Tombstone InscriptionsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  28. Hierarchical Reinforcement Learning with Targeted Causal InterventionsDeep reinforcement learning methods → Deep RL algorithms and representations
  29. WebSynthesis: World-Model-Guided MCTS for Efficient WebUI-Trajectory SynthesisWorld models → World models for language agents +1
  30. MambaFusion: Height-Fidelity Dense Global Fusion for Multi-modal 3D Object DetectionState-space sequence models (S4, Mamba) → Point clouds, detection and remote sensing
  31. Long-Context Modeling Networks for Monaural Speech Enhancement: A Comparative StudyState-space sequence models (S4, Mamba) → Speech and audio SSMs
  32. Attention Slipping: A Mechanistic Understanding of Jailbreak Attacks and Defenses in LLMsLLM safety and security → Jailbreaking
  33. MLLM-Fabric: Multimodal Large Language Model-Driven Robotic Framework for Fabric Sorting and SelectionMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  34. SmartThinker: Learning to Compress and Preserve Reasoning by Step-Level Length ControlLLM reasoning → Test-time compute and efficient thinking
  35. Efficient Perplexity Bound and Ratio Matching in Discrete Diffusion Language ModelsDiffusion models → Discrete and text diffusion
  36. Interactive Groupwise Comparison for Reinforcement Learning from Human FeedbackLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF +1
  37. AutoLayout: Closed-Loop Layout Synthesis via Slow-Fast Collaborative ReasoningLLM reasoning → Spatial and embodied reasoning
  38. MPQ-DMv2: Flexible Residual Mixed Precision Quantization for Low-Bit Diffusion Models with Temporal DistillationDiffusion models → Diffusion foundations and sampling
  39. M3-Med: A Benchmark for Multi-lingual, Multi-modal, and Multi-hop Reasoning in Medical Instructional Video UnderstandingLLM reasoning → Clinical and biomedical applications
  40. Clustering via Self-Supervised DiffusionDiffusion models → Diffusion foundations and sampling
  41. Just Enough Shifts: Mitigating Over-Refusal in Aligned Language Models with Targeted Representation Fine-TuningLLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks +1
  42. Soft Actor-Critic with Backstepping-Pretrained DeepONet for control of PDEsDeep reinforcement learning methods → RL theory and sample complexity
  43. Mobile GUI Agents under Real-world Threats: Are We There Yet?LLM agents and tool use → GUI and mobile agents
  44. Model Collapse Is Not a Bug but a Feature in Machine Unlearning for LLMsSynthetic data and self-improvement for LLMs → Model collapse from synthetic data +1
  45. Quick Bypass Mechanism of Zero-Shot Diffusion-Based Image RestorationDiffusion models → Inverse problems and image restoration
  46. An explicit formulation of the learned noise predictor εθ(bf xt, t) via the forward-process noise εt in denoising diffusion probabilistic models (DDPMs)Diffusion models → Diffusion foundations and sampling
  47. Gaze-Aware AI: Mathematical modeling of epistemic experience of the Marginalized for Human-Computer Interaction & AI Systems
  48. OmniVec2 -- A Novel Transformer based Network for Large Scale Multimodal and Multitask Learning
  49. Just Add Geometry: Gradient-Free Open-Vocabulary 3D Detection Without Human-in-the-Loop
  50. A Hybrid Machine Learning Framework for Optimizing Crop Selection via Agronomic and Economic Forecasting
  51. Assessing the Capabilities and Limitations of FinGPT Model in Financial NLP Applications
  52. MedicalBERT: enhancing biomedical natural language processing using pretrained BERT-based model
  53. Emergent misalignment as prompt sensitivity: A research note
  54. Continuous Classification Aggregation
  55. Integrating Generative AI in BIM Education: Insights from Classroom Implementation
  56. Lilith: Developmental Modular LLMs with Chemical Signaling
  57. Nile-Chat: Egyptian Language Models for Arabic and Latin Scripts
  58. Evaluating LLMs on Real-World Forecasting Against Expert Forecasters
  59. MambaVideo for Discrete Video Tokenization with Channel-Split Quantization
  60. Self-supervised learning of speech representations with Dutch archival data
  61. AL-SPCE - Reliability analysis for nondeterministic models using stochastic polynomial chaos expansions and active learning
  62. SPIRA: Building an Intelligent System for Respiratory Insufficiency Detection
  63. da4ml: Distributed Arithmetic for Real-time Neural Networks on FPGAs
  64. A Data-Driven Novelty Score for Diverse In-Vehicle Data Recording
  65. Towards integration of Privacy Enhancing Technologies in Explainable Artificial Intelligence
  66. Verification of Visual Controllers via Compositional Geometric Transformations
  67. Grounded Gesture Generation: Language, Motion, and Space
  68. DOTResize: Reducing LLM Width via Discrete Optimal Transport-based Neuron Merging
  69. Churn-Aware Recommendation Planning under Aggregated Preference Feedback
  70. Dynamic Frequency Feature Fusion Network for Multi-Source Remote Sensing Data Classification
  71. Adapter-state Sharing CLIP for Parameter-efficient Multimodal Sarcasm Detection
  72. U-ViLAR: Uncertainty-Aware Visual Localization for Autonomous Driving via Differentiable Association and Registration
  73. Thousand-Brains Systems: Sensorimotor Intelligence for Rapid, Robust Learning and Inference
  74. Machine Learning-Based Prediction of Metal-Organic Framework Materials: A Comparative Analysis of Multiple Models
  75. A validity-guided workflow for robust large language model research in psychology
  76. Dealing with Uncertainty in Contextual Anomaly Detection
  77. LoSiA: Efficient High-Rank Fine-Tuning via Subnet Localization and Optimization
  78. A Training-Free Style-Personalization via SVD-Based Feature Decomposition
  79. Does Overnight News Explain Overnight Returns?
  80. Model Inversion Attacks on Llama 3: Extracting PII from Large Language Models
  81. The role of large language models in UI/UX design: A systematic literature review
  82. Dual Modality-Aware Gated Prompt Tuning for Few-Shot Multimodal Sarcasm Detection
  83. Visual Hand Gesture Recognition with Deep Learning: A Comprehensive Review of Methods, Datasets, Challenges and Future Research Directions
  84. BiVM: Accurate Binarized Neural Network for Efficient Video Matting
  85. GradOT: Training-free Gradient-preserving Offsite-tuning for Large Language Models
  86. Dude, where's my utterance? Evaluating the effects of automatic segmentation and transcription on CPS detection
  87. CoT-lized Diffusion: Let's Reinforce T2I Generation Step-by-step
  88. Transfer Learning in Infinite Width Feature Learning Networks
  89. Sampling-aware Adversarial Attacks Against Large Language Models
  90. A Category-Theoretic Analysis of Conformal Prediction
  91. A Linguistic Analysis of Spontaneous Thoughts: Investigating Experiences of D'ej`a Vu, Unexpected Thoughts, and Involuntary Autobiographical Memories
  92. Quantum Algorithms for Bandits with Knapsacks with Improved Regret and Time Complexities
  93. Reconstructing Biological Pathways by Applying Selective Incremental Learning to (Very) Small Language Models
  94. MedGellan: LLM-Generated Medical Guidance to Support Physicians
  95. ARMR: Adaptively Responsive Network for Medication Recommendation
  96. Learning Software Bug Reports: A Systematic Literature Review
  97. Neural Networks for Tamed Milstein Approximation of SDEs with Additive Symmetric Jump Noise Driven by a Poisson Random Measure
  98. RAT: Bridging RNN Efficiency and Attention Accuracy via Chunk-based Sequence Modeling
  99. MOMENTS: A Comprehensive Multimodal Benchmark for Theory of Mind
  100. THM@SimpleText 2025 -- Task 1.1: Revisiting Text Simplification based on Complex Terms for Non-Experts
All 162
  1. Enhancing Text-Based Hierarchical Multilabel Classification for Mobile Applications via Contrastive Learning
  2. SFOOD: A Multimodal Benchmark for Comprehensive Food Attribute Analysis Beyond RGB with Spectral Insights
  3. A View-consistent Sampling Method for Regularized Training of Neural Radiance Fields
  4. LayerCake: Token-Aware Contrastive Decoding within Large Language Model Layers
  5. Multi-Expert Learning Framework with the State Space Model for Optical and SAR Image Registration
  6. SpiritRAG: A Q&A System for Religion and Spirituality in the United Nations Archive
  7. Comprehensive Information Bottleneck for Unveiling Universal Attribution to Interpret Vision Transformers
  8. Tractable Representation Learning with Probabilistic Circuits
  9. ViTaL: A Multimodality Dataset and Benchmark for Multi-pathological Ovarian Tumor Recognition
  10. Transferring Visual Explainability of Self-Explaining Models to Prediction-Only Models without Additional Training
  11. MOD-X: A Modular Open Decentralized eXchange Framework proposal for Heterogeneous Interoperable Artificial Intelligence Agents
  12. Adaptive Malware Detection using Sequential Feature Selection: A Dueling Double Deep Q-Network (D3QN) Framework for Intelligent Classification
  13. Time2Agri: Temporal Pretext Tasks for Agricultural Monitoring
  14. Large Language Models' Varying Accuracy in Recognizing Risk-Promoting and Health-Supporting Sentiments in Public Health Discourse: The Cases of HPV Vaccination and Heated Tobacco Products
  15. Information-theoretic Quantification of High-order Feature Effects in Classification Problems
  16. Mission-Aligned Learning-Informed Control of Autonomous Systems: Formulation and Foundations
  17. AI-washing: The Asymmetric Effects of Its Two Types on Consumer Moral Judgments
  18. HatePRISM: Policies, Platforms, and Research Integration. Advancing NLP for Hate Speech Proactive Mitigation
  19. Temporally smoothed incremental model-based heuristic dynamic programming for command-filtered cascaded online learning flight control
  20. Voltage Mode Winner-Take-All Circuit for Neuromorphic Systems
  21. Computed Tomography Visual Question Answering with Cross-modal Feature Graphing
  22. Consistent Labeling Across Group Assignments: Variance Reduction in Conditional Average Treatment Effect Estimation
  23. A note on the unique properties of the Kullback--Leibler divergence for sampling via gradient flows
  24. No Language Data Left Behind: A Comparative Study of CJK Language Datasets in the Hugging Face Ecosystem
  25. TinyProto: Communication-Efficient Federated Learning with Sparse Prototypes in Resource-Constrained Environments
  26. DMAT: An End-to-End Framework for Joint Atmospheric Turbulence Mitigation and Object Detection
  27. CLIP-RL: Surgical Scene Segmentation Using Contrastive Language-Vision Pretraining & Reinforcement Learning
  28. Heterogeneous Federated Learning with Prototype Alignment and Upscaling
  29. Domain Adaptation of Drag Reduction Policy to Partial Measurements
  30. Exploring Remote Physiological Signal Measurement under Dynamic Lighting Conditions at Night: Dataset, Experiment, and Analysis
  31. Surg-SegFormer: A Dual Transformer-Based Model for Holistic Surgical Scene Segmentation
  32. Adversarial Data Augmentation for Single Domain Generalization via Lyapunov Exponent-Guided Optimization
  33. QF: Quick Feedforward AI Model Training without Gradient Back Propagation
  34. Answer Set Programming Modulo Theories and Reasoning about Continuous Changes
  35. LearnLens: LLM-Enabled Personalised, Curriculum-Grounded Feedback with Educators in the Loop
  36. SeqTex: Generate Mesh Textures in Video Sequence
  37. Towards Lightest Low-Light Image Enhancement Architecture for Mobile Devices
  38. VOLTRON: Detecting Unknown Malware Using Graph-Based Zero-Shot Learning
  39. ZERO: Industry-ready Vision Foundation Model with Multi-modal Prompts
  40. Efficient Training of Deep Networks using Guided Spectral Data Selection: A Step Toward Learning What You Need
  41. An Explainable Transformer Model for Alzheimer's Disease Detection Using Retinal Imaging
  42. MoReMouse: Monocular Reconstruction of Laboratory Mouse
  43. Bandit Pareto Set Identification in a Multi-Output Linear Model
  44. Deep-Learning-Assisted Highly-Accurate COVID-19 Diagnosis on Lung Computed Tomography Images
  45. ATwo-Stage Ensemble Feature Selection and Particle Swarm Optimization Approach for Micro-Array Data Classification in Distributed Computing Environments
  46. Inertial Quadratic Majorization Minimization with Application to Kernel Regularized Learning
  47. Domain Generalizable Portrait Style Transfer
  48. Scaling Context Requires Rethinking Attention
  49. Structural Classification of Locally Stationary Time Series Based on Second-order Characteristics
  50. Design Optimization of Three-Dimensional Wire Arrangement Considering Wire Crossings for Tendon-driven Robots
  51. Grid-Reg: Detector-Free Gridized Feature Learning and Matching for Large-Scale SAR-Optical Image Registration
  52. High-Resolution Sustain Pedal Depth Estimation from Piano Audio Across Room Acoustics
  53. Normalized Iterative Hard Thresholding for Tensor Recovery
  54. Zero-Shot Cyclic Peptide Design via Composable Geometric Constraints
  55. Fairness Evaluation of Large Language Models in Academic Library Reference Services
  56. Context Tuning for In-Context Optimization
  57. DreamPoster: A Unified Framework for Image-Conditioned Generative Poster Design
  58. Normalizing Flow to Augmented Posterior: Conditional Density Estimation with Interpretable Dimension Reduction for High Dimensional Data
  59. Mpemba Effect in Large-Language Model Training Dynamics: A Minimal Analysis of the Valley-River model
  60. Predicting Air Pollution in Cork, Ireland Using Machine Learning
  61. Mixed-Sample SGD: an End-to-end Analysis of Supervised Transfer Learning
  62. JAX-MPM: A Learning-Augmented Differentiable Meshfree Framework for GPU-Accelerated Lagrangian Simulation and Geophysical Inverse Modeling