mlsanityData to 14 Oct 2026

Papers

New on arXiv

Sat 2 Aug 2025

207 papers

  1. Categorical Construction of Logically Verifiable Neural ArchitecturesLLM reasoning → Reasoning benchmarks and evaluation
  2. Agentic TinyML for Intent-aware Handover in 6G Wireless NetworksLLM agents and tool use → Agentic AI for wireless networks
  3. PiKV: KV Cache Management System for Mixture of ExpertsMixture-of-experts → Efficient MoE training and inference systems +1
  4. Large Language Models Facilitate Vision Reflection in Image ClassificationMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  5. Large Language Model-based Data Science Agent: A SurveyLLM agents and tool use → Web, search, and research agents
  6. AgentSight: System-Level Observability for AI Agents Using eBPFLLM agents and tool use → Agent threats, guardrails and governance
  7. A Reward-Directed Diffusion Framework for Generative Design OptimizationDiffusion models → Flow matching, time series and science
  8. A Theory of Adaptive Scaffolding for LLM-Based Pedagogical AgentsLLM agents and tool use → Educational agents and math problem solving
  9. WinkTPG: An Execution Framework for Multi-Agent Path Finding Using Temporal ReasoningLLM reasoning → Reasoning for agents, planning and code
  10. The Homogenizing Effect of Large Language Models on Human Expression and ThoughtLLM reasoning → Reasoning benchmarks and evaluation
  11. Think Broad, Act Narrow: CWE Identification with Multi-Agent Large Language ModelsLLM reasoning → Reasoning for agents, planning and code +1
  12. Towards Efficient Medical Reasoning with Minimal Fine-Tuning DataLLM reasoning → Clinical and biomedical applications +1
  13. TripTailor: A Real-World Benchmark for Personalized Travel PlanningLLM reasoning → Reasoning for agents, planning and code
  14. From Query to Logic: Ontology-Driven Multi-Hop Reasoning in LLMsLLM reasoning → Knowledge- and tool-augmented reasoning
  15. RoboMemory: A Brain-inspired Multi-memory Agentic Framework for Interactive Environmental Learning in Physical Embodied SystemsLLM agents and tool use → Multimodal and embodied agents
  16. MoRe-ERL: Learning Motion Residuals using Episodic Reinforcement LearningDeep reinforcement learning methods → Deep RL algorithms and representations
  17. Balancing the Blend: An Experimental Analysis of Trade-offs in Hybrid SearchRetrieval-augmented generation → RAG pipeline design and evaluation
  18. ForenX: Towards Explainable AI-Generated Image Detection with Multimodal Large Language ModelsMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness
  19. Effective Damage Data Generation by Fusing Imagery with Human Knowledge Using Vision-Language ModelsMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  20. MaRGen: Multi-Agent LLM Approach for Self-Directed Market Research and AnalysisLLM agents and tool use → Financial trading and forecasting agents
  21. ConfGuard: A Simple and Effective Backdoor Detection for Large Language ModelsLLM safety and security → Backdoor and data poisoning attacks
  22. StyleSentinel: Reliable Artistic Copyright Verification via Stylistic FingerprintsDiffusion models → Image generation, text-to-image and editing +1
  23. Zero-shot Segmentation of Skin Conditions: Erythema with Edit-Friendly InversionDiffusion models → Medical imaging and segmentation
  24. BlockA2A: Towards Secure and Verifiable Agent-to-Agent InteroperabilityLLM agents and tool use → Agent threats, guardrails and governance
  25. NaturalGAIA: A Verifiable Benchmark and Hierarchical Framework for Long-Horizon GUI TasksLLM agents and tool use → GUI and mobile agents
  26. Is Exploration or Optimization the Problem for Deep Reinforcement Learning?Deep reinforcement learning methods → Deep RL algorithms and representations
  27. Towards Evaluation for Real-World LLM UnlearningLLM safety and security → Machine unlearning
  28. D-SCoRE: Document-Centric Segmentation and CoT Reasoning with Structured Export for QA-CoT Data GenerationLLM reasoning → Reasoning benchmarks and evaluation
  29. PUZZLED: Jailbreaking LLMs through Word-Based PuzzlesLLM safety and security → Jailbreaking
  30. Aligning Language Models with Real-time Knowledge EditingLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  31. Prompting Large Language Models with Partial Knowledge for Answering Questions with Unseen EntitiesRetrieval-augmented generation → Knowledge-graph and structured-knowledge RAG
  32. Exploitation Is All You Need... for ExplorationDeep reinforcement learning methods → Deep RL algorithms and representations
  33. BioDisco: Multi-agent hypothesis generation with dual-mode evidence, iterative feedback and temporal evaluationLLM agents and tool use → Medical and scientific domain agents
  34. Multi-TW: Benchmarking Multimodal Models on Traditional Chinese Question Answering in TaiwanMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  35. Disentangling Reasoning Logic to Resolve Explicit Knowledge ConflictsLLM reasoning → Reasoning benchmarks and evaluation
  36. Win-k: Improved Membership Inference Attacks on Small Language ModelsLLM safety and security → Membership inference attacks
  37. Enhancing Diffusion-based Dataset Distillation via Adversary-Guided Curriculum SamplingDiffusion models → Diffusion foundations and sampling
  38. Bridging LLMs and Symbolic Reasoning in Educational QA Systems: Insights from the XAI Challenge at IJCNN 2025LLM reasoning → Reasoning benchmarks and evaluation
  39. Unifying Mixture of Experts and Multi-Head Latent Attention for Efficient Language ModelsMixture-of-experts → MoE large language models +1
  40. AgentArmor: Enforcing Program Analysis on Agent Runtime Trace to Defend Against Prompt InjectionLLM agents and tool use → Agent threats, guardrails and governance +1
  41. NS-Net: Decoupling CLIP Semantic Information through NULL-Space for Generalizable AI-Generated Image DetectionDiffusion models → Image generation, text-to-image and editing
  42. Coordinated Humanoid Robot Locomotion with Symmetry Equivariant Reinforcement Learning PolicyDeep reinforcement learning methods → RL for robot locomotion and manipulation
  43. Mitigating Information Loss under High Pruning Rates for Efficient Large Vision Language ModelsMultimodal LLMs / vision-language models → Visual token pruning and efficiency
  44. Point-wise Diffusion Models for Physical Systems with Shape Variations: Application to Spatio-temporal and Large-scale systemDiffusion models → 3D, point cloud and scene generation
  45. Multi-Cache Enhanced Prototype Learning for Test-Time Generalization of Vision-Language ModelsMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  46. StyDeco: Unsupervised Style Transfer with Distilling Priors and Semantic DecouplingDiffusion models → Image generation, text-to-image and editing
  47. RoadMamba: A Dual Branch Visual State Space Model for Road Surface ClassificationState-space sequence models (S4, Mamba) → Point clouds, detection and remote sensing
  48. Unified Generation-Refinement Planning: Bridging Guided Flow Matching and Sampling-Based MPC for Social NavigationDiffusion models → Diffusion and flow policies for robotics
  49. Is Chain-of-Thought Reasoning of LLMs a Mirage? A Data Distribution LensLLM reasoning → Prompting and chain-of-thought reasoning
  50. A Survey on Agent Workflow -- Status and FutureLLM agents and tool use → Software engineering coding agents
  51. Benchmarking and Bridging Emotion Conflicts for Multimodal Emotion ReasoningLLM reasoning → Audio-language model reasoning +1
  52. T2S: Tokenized Skill Scaling for Lifelong Imitation LearningOffline RL and imitation learning from data → Robot manipulation imitation learning
  53. RoboLinker: A Diffusion-model-based Matching Clothing Generator Between Humans and Companion RobotsDiffusion models → 3D, point cloud and scene generation
  54. Personalized Safety Alignment for Text-to-Image Diffusion ModelsDiffusion models → Robustness, privacy and adversarial aspects +2
  55. Dataset Condensation with Color CompensationDiffusion models → Image generation, text-to-image and editing
  56. DBAIOps: A Reasoning LLM-Enhanced Database Operation and Maintenance System using Knowledge GraphsLLM reasoning → Reasoning for agents, planning and code
  57. COLLAGE: Adaptive Fusion-based Retrieval for Augmented Policy LearningOffline RL and imitation learning from data → Robot manipulation imitation learning
  58. Motif 2.6B Technical Report
  59. RMT-PPAD: Real-time Multi-task Learning for Panoptic Perception in Autonomous Driving
  60. A Framework Combining 3D CNN and Transformer for Video-Based Behavior Recognition
  61. CarbonScaling: Extending Neural Scaling Laws for Carbon Footprint in Large Language Models
  62. Data-Driven Discovery of Mobility Periodicity for Understanding Urban Systems
  63. Classifying Epistemic Relationships in Human-AI Interaction: An Exploratory Approach
  64. Considering Spatial Structure of the Road Network in Pavement Deterioration Modeling
  65. A Novel cVAE-Augmented Deep Learning Framework for Pan-Cancer RNA-Seq Classification
  66. SpectrumFM: Redefining Spectrum Cognition via Foundation Modeling
  67. DeepGB-TB: A Risk-Balanced Cross-Attention Gradient-Boosted Convolutional Network for Rapid, Interpretable Tuberculosis Screening
  68. Who Gets Cited? Gender- and Majority-Bias in LLM-Driven Reference Selection
  69. Kronos: A Foundation Model for the Language of Financial Markets
  70. CreditARF: A Framework for Corporate Credit Rating with Annual Report and Financial Feature Integration
  71. Embedding-Enhanced Probabilistic Modeling of Ferroelectric Field Effect Transistors (FeFETs)
  72. Recovering Individual-Level Activity Sequences from Location-Based Service Data Using a Novel Transformer-Based Model
  73. Decentralized Aerial Manipulation of a Cable-Suspended Load using Multi-Agent Reinforcement Learning
  74. Prototype Learning to Create Refined Interpretable Digital Phenotypes from ECGs
  75. The Vanishing Gradient Problem for Stiff Neural Differential Equations
  76. Central Limit Theorems for Transition Probabilities of Controlled Markov Chains
  77. SimDeep: Federated 3D Indoor Localization via Similarity-Aware Aggregation
  78. End-to-End Personalization: Unifying Recommender Systems with Large Language Models
  79. Canoe Paddling Quality Assessment Using Smart Devices: Preliminary Machine Learning Study
  80. Frequency-Constrained Learning for Long-Term Forecasting
  81. FlashSVD: Memory-Efficient Inference with Streaming for Low-Rank Models
  82. ESM: A Framework for Building Effective Surrogate Models for Hardware-Aware Neural Architecture Search
  83. Instruction-based Time Series Editing
  84. ShrutiSense: Microtonal Modeling and Correction in Indian Classical Music
  85. Translation-Equivariant Self-Supervised Learning for Pitch Estimation with Optimal Transport
  86. A Large-Scale Benchmark of Cross-Modal Learning for Histology and Gene Expression in Spatial Transcriptomics
  87. PESTO: Real-Time Pitch Estimation with Self-supervised Transposition-equivariant Objective
  88. Human-Centered Supervision for Sentiment Analysis in Telugu: A Systematic Inquiry Beyond Accuracy
  89. Training Dynamics of the Cooldown Stage in Warmup-Stable-Decay Learning Rate Scheduler
  90. Harnessing Collective Intelligence of LLMs for Robust Biomedical QA: A Multi-Model Approach
  91. Reconstructing Trust Embeddings from Siamese Trust Scores: A Direct-Sum Approach with Fixed-Point Semantics
  92. Hyperparameter-Free Neurochaos Learning Algorithm for Classification
  93. CARGO: A Co-Optimization Framework for EV Charging and Routing in Goods Delivery Logistics
  94. R2-CoD: Understanding Text-Graph Complementarity in Relational Reasoning via Knowledge Co-Distillation
  95. HT-Transformer: Event Sequences Classification by Accumulating Prefix Information with History Tokens
  96. TreeDiff: AST-Guided Code Generation with Diffusion LLMs
  97. EfficientGFormer: Multimodal Brain Tumor Segmentation via Pruned Graph-Augmented Transformer
  98. Can3Tok: Canonical 3D Tokenization and Latent Modeling of Scene-Level 3D Gaussians
  99. Uncertainty-Aware Segmentation Quality Prediction via Deep Learning Bayesian Modeling: Comprehensive Evaluation and Interpretation on Skin Cancer and Liver Segmentation
  100. Fast and scalable retrosynthetic planning with a transformer neural network and speculative beam search
All 207
  1. NICE^k Metrics: Unified and Multidimensional Framework for Evaluating Deterministic Solar Forecasting Accuracy
  2. Regression Augmentation With Data-Driven Segmentation
  3. Kernel-Based Sparse Additive Nonlinear Model Structure Detection through a Linearization Approach
  4. Tuning LLM-based Code Optimization via Meta-Prompting: An Industrial Perspective
  5. Hyperspectral Image Recovery Constrained by Multi-Granularity Non-Local Self-Similarity Priors
  6. Capturing More: Learning Multi-Domain Representations for Robust Online Handwriting Verification
  7. UniExtreme: A Universal Foundation Model for Extreme Weather Forecasting
  8. 3DRot: Rediscovering the Missing Primitive for RGB-Based 3D Augmentation
  9. Cryptocurrency Price Forecasting Using Machine Learning: Building Intelligent Financial Prediction Models
  10. Bias Association Discovery Framework for Open-Ended LLM Generations
  11. ArzEn-MultiGenre: An aligned parallel dataset of Egyptian Arabic song lyrics, novels, and subtitles, with English translations
  12. Signals, Concepts, and Laws: Toward Universal, Explainable Time-Series Forecasting
  13. MedSynth: Realistic, Synthetic Medical Dialogue-Note Pairs
  14. Spatial-Frequency Aware for Object Detection in RAW Image
  15. Effects of Feature Correlations on Associative Memory Capacity
  16. Via Score to Performance: Efficient Human-Controllable Long Song Generation with Bar-Level Symbolic Notation
  17. Quenched large deviations for Monte Carlo integration with Coulomb gases
  18. Recognising, Anticipating, and Mitigating LLM Pollution of Online Behavioural Research
  19. Open-Attribute Person Retrieval: Finding People Through Distinctive and Novel Attributes
  20. Video-based Vehicle Surveillance in the Wild: License Plate, Make, and Model Recognition with Self Reflective Vision-Language Models
  21. Construction of Digital Terrain Maps from Multi-view Satellite Imagery using Neural Volume Rendering
  22. Lightweight Backbone Networks Only Require Adaptive Lightweight Self-Attention Mechanisms
  23. A Full-Stage Refined Proposal Algorithm for Suppressing False Positives in Two-Stage CNN-Based Detection Methods
  24. ReMu: Reconstructing Multi-layer 3D Clothed Human from Image Layers
  25. Prompt to Pwn: Automated Exploit Generation for Smart Contracts
  26. Relation-Aware LNN-Transformer for Intersection-Centric Next-Step Prediction
  27. Predicting EGFR Mutation in LUAD from Histopathological Whole-Slide Images Using Pretrained Foundation Model and Transfer Learning: An Indian Cohort Study
  28. Classification of Brain Tumors using Hybrid Deep Learning Models
  29. Convergence Analysis of Aggregation-Broadcast in LoRA-enabled Distributed Fine-Tuning
  30. Predicting Video Slot Attention Queries from Random Slot-Feature Pairs
  31. UEChecker: Detecting Unchecked External Call Vulnerabilities in DApps via Graph Analysis
  32. Debiasing Machine Learning Predictions for Causal Inference Without Additional Ground Truth Data: "One Map, Many Trials" in Satellite-Driven Poverty Analysis
  33. SBP-YOLO:A Lightweight Real-Time Model for Detecting Speed Bumps and Potholes toward Intelligent Vehicle Suspension Systems
  34. Weakly-Supervised Image Forgery Localization via Vision-Language Collaborative Reasoning Framework
  35. Referring Remote Sensing Image Segmentation with Cross-view Semantics Interaction Network
  36. Large-Scale Diverse Synthesis for Mid-Training
  37. Fusion Sampling Validation in Data Partitioning for Machine Learning
  38. Idempotent Equilibrium Analysis of Hybrid Workflow Allocation: A Mathematical Schema for Future Work
  39. SWAN: Synergistic Wavelet-Attention Network for Infrared Small Target Detection
  40. Flow IV: Counterfactual Inference In Nonseparable Outcome Models Using Instrumental Variables
  41. LinkQA: Synthesizing Diverse QA from Multiple Seeds Strongly Linked by Knowledge Points
  42. Multimodal Attention-Aware Fusion for Diagnosing Distal Myopathy: Evaluating Model Interpretability and Clinician Trust
  43. Physics-Informed Neural Network Approaches for Sparse Data Flow Reconstruction of Unsteady Flow Around Complex Geometries
  44. P3P Made Easy
  45. C3D-AD: Toward Continual 3D Anomaly Detection via Kernel Attention with Learnable Advisor
  46. GraphVSSM: Graph Variational State-Space Model for Probabilistic Spatiotemporal Inference of Dynamic Exposure and Vulnerability for Regional Disaster Resilience Assessment
  47. Domain Generalized Stereo Matching with Uncertainty-guided Data Augmentation
  48. How Far Are LLMs from Symbolic Planners? An NLP-Based Perspective
  49. FedCD: A Fairness-aware Federated Cognitive Diagnosis Framework
  50. GMAT: Grounded Multi-Agent Clinical Description Generation for Text Encoder in Vision-Language MIL for Whole Slide Image Classification
  51. CoCoLIT: ControlNet-Conditioned Latent Image Translation for MRI to Amyloid PET Synthesis
  52. A graph neural network based on feature network for identifying influential nodes
  53. Foundation Models for Bioacoustics -- a Comparative Review
  54. Defending Against Beta Poisoning Attacks in Machine Learning Models
  55. Integrating Disparity Confidence Estimation into Relative Depth Prior-Guided Unsupervised Stereo Matching
  56. PromptSafe: Gated Prompt Tuning for Safe Text-to-Image Generation
  57. SGCap: Decoding Semantic Group for Zero-shot Video Captioning
  58. ModelNet40-E: An Uncertainty-Aware Benchmark for Point Cloud Classification
  59. SpatioTemporal Difference Network for Video Depth Super-Resolution
  60. Self-Enhanced Image Clustering with Cross-Modal Semantic Consistency
  61. ODOV: Benchmark the Open-Domain Open-Vocabulary Object Detection
  62. Soft Separation and Distillation: Toward Global Uniformity in Federated Unsupervised Learning
  63. DisFaceRep: Representation Disentanglement for Co-occurring Facial Components in Weakly Supervised Face Parsing
  64. WarriorMath: Enhancing the Mathematical Ability of Large Language Models with a Defect-aware Framework
  65. MeshLLM: Empowering Large Language Models to Progressively Understand and Generate 3D Mesh
  66. RelMap: Reliable Spatiotemporal Sensor Data Visualization via Imputative Spatial Interpolation
  67. OCSplats: Observation Completeness Quantification and Label Noise Separation in 3DGS
  68. SketchAgent: Generating Structured Diagrams from Hand-Drawn Sketches
  69. Inferring processes within dynamic forest models using hybrid modeling
  70. Enhancing Multi-view Open-set Learning via Ambiguity Uncertainty Calibration and View-wise Debiasing
  71. ParaRevSNN: A Parallel Reversible Spiking Neural Network for Efficient Training and Inference
  72. WebDS: An End-to-End Benchmark for Web-based Data Science
  73. Eigen Neural Network: Unlocking Generalizable Vision with Eigenbasis
  74. MoGaFace: Momentum-Guided and Texture-Aware Gaussian Avatars for Consistent Facial Geometry
  75. Uncertainty Quantification for Large-Scale Deep Networks via Post-StoNet Modeling
  76. Perspective from a Broader Context: Can Room Style Knowledge Help Visual Floorplan Localization?
  77. Show or Tell? Modeling the evolution of request-making in Human-LLM conversations
  78. Multi-Operator Few-Shot Learning for Generalization Across PDE Families
  79. Oldie but Goodie: Re-illuminating Label Propagation on Graphs with Partially Observed Features
  80. Calibrated Prediction Set in Fault Detection with Risk Guarantees via Significance Tests
  81. Deep Learning for Pavement Condition Evaluation Using Satellite Imagery
  82. Conquering High Packet-Loss Erasure: MoE Swin Transformer-Based Video Semantic Communication
  83. Importance Sampling is All You Need: Predict LLM's performance on new benchmark by reusing existing benchmark
  84. Adaptive Content Restriction for Large Language Models via Suffix Optimization
  85. A Coarse-to-Fine Approach to Multi-Modality 3D Occupancy Grounding
  86. BSL: A Unified and Generalizable Multitask Learning Platform for Virtual Drug Discovery from Design to Synthesis
  87. SpectrumWorld: Artificial Intelligence Foundation for Spectroscopy
  88. Object Affordance Recognition and Grounding via Multi-scale Cross-modal Representation Learning
  89. Advancing the Foundation Model for Music Understanding
  90. From Taylor Series to Fourier Synthesis: The Periodic Linear Unit
  91. RSPO: Risk-Seeking Policy Optimization for Pass@k and Max@k Metrics in Large Language Models
  92. MARS: A Meta-Adaptive Reinforcement Learning Framework for Risk-Aware Multi-Agent Portfolio Management
  93. GeHirNet: A Gender-Aware Hierarchical Model for Voice Pathology Classification
  94. No Pose at All: Self-Supervised Pose-Free 3D Gaussian Splatting from Sparse Views
  95. DELTAv2: Accelerating Dense 3D Tracking
  96. CSIRO-LT at SemEval-2025 Task 11: Adapting LLMs for Emotion Recognition for Multiple Languages
  97. Asking the Right Questions: Benchmarking Large Language Models in the Development of Clinical Consultation Templates
  98. H2C: Hippocampal Circuit-inspired Continual Learning for Lifelong Trajectory Prediction in Autonomous Driving
  99. TEACH: Text Encoding as Curriculum Hints for Scene Text Recognition
  100. LawDIS: Language-Window-based Controllable Dichotomous Image Segmentation
  101. OpenGS-Fusion: Open-Vocabulary Dense Mapping with Hybrid 3D Gaussian Splatting for Refined Object-Level Understanding
  102. DisTaC: Conditioning Task Vectors via Distillation for Robust Model Merging
  103. Semi-Supervised Anomaly Detection in Brain MRI Using a Domain-Agnostic Deep Reinforcement Learning Approach
  104. Transformers in Pseudo-Random Number Generation: A Dual Perspective on Theory and Practice
  105. Human-Robot Red Teaming for Safety-Aware Reasoning
  106. Towards Bridging Review Sparsity in Recommendation with Textual Edge Graph Representation
  107. UniEgoMotion: A Unified Model for Egocentric Motion Reconstruction, Forecasting, and Generation