mlsanityData to 14 Oct 2026

Papers

New on arXiv

Wed 29 Jan 2025

201 papers

  1. Empirical Research on Utilizing LLM-based Agents for Automated Bug Fixing via LangGraphLLM agents and tool use → Software engineering coding agents
  2. Multimodal Large Language Models for Image, Text, and Speech Data Augmentation: A SurveyMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  3. Layered Chain-of-Thought Prompting for Multi-Agent LLM Systems: A Comprehensive Approach to Explainable Large Language ModelsLLM reasoning → Prompting and chain-of-thought reasoning +1
  4. SAeUron: Interpretable Concept Unlearning in Diffusion Models with Sparse AutoencodersDiffusion models → Robustness, privacy and adversarial aspects +2
  5. Digital Twin Synchronization: Bridging the Sim-RL Agent to a Real-Time Robotic Additive Manufacturing ControlDeep reinforcement learning methods → RL for robot locomotion and manipulation
  6. Large Language Models Think Too Fast To Explore EffectivelyLLM reasoning → Reasoning benchmarks and evaluation
  7. Agentic Workflows for Conversational Human-AI Interaction DesignLLM agents and tool use → General LLM agent frameworks and benchmarks
  8. InnerThoughts: Disentangling Representations and Predictions in Large Language ModelsLLM reasoning → Reasoning benchmarks and evaluation
  9. Reinforcement-Learning Portfolio Allocation with Dynamic Embedding of Market InformationDeep reinforcement learning methods → Adversarial robustness and RL in finance
  10. Think Smarter not Harder: Adaptive Reasoning with Inference Aware OptimizationLLM reasoning → Test-time compute and efficient thinking
  11. Free Agent in Agent-Based Mixture-of-Experts Generative AI FrameworkMixture-of-experts → MoE in reinforcement learning and robotics
  12. From Sparse to Dense: Toddler-inspired Reward Transition in Goal-Oriented Reinforcement LearningDeep reinforcement learning methods → Deep RL algorithms and representations
  13. Langevin Soft Actor-Critic: Efficient Exploration through Uncertainty-Driven Critic LearningDeep reinforcement learning methods → RL theory and sample complexity
  14. International AI Safety ReportLLM reasoning → Reasoning for agents, planning and code
  15. Consensus Based Stochastic ControlDeep reinforcement learning methods → RL theory and sample complexity
  16. Reasoning Over the Glyphs: Evaluation of LLM's Decipherment of Rare ScriptsLLM reasoning → Reasoning benchmarks and evaluation
  17. Early External Safety Testing of OpenAI's o3-mini: Insights from the Pre-Deployment EvaluationLLM reasoning → Reasoning for agents, planning and code
  18. Automated Interpretability Metrics Do Not Distinguish Trained and Random TransformersMechanistic interpretability → Sparse autoencoder training and evaluation
  19. VICCA: Visual Interpretation and Comprehension of Chest X-ray Anomalies in Generated Report Without Human FeedbackDiffusion models → Medical imaging and segmentation
  20. RICoTA: Red-teaming of In-the-wild Conversation with Test AttemptsLLM safety and security → Jailbreaking
  21. Critique Fine-Tuning: Learning to Critique is More Effective than Learning to ImitateLLM reasoning → Test-time compute and efficient thinking
  22. Distinguished Quantized Guidance for Diffusion-based Sequence RecommendationDiffusion models → Diffusion recommenders
  23. CAMP in the Odyssey: Provably Robust Reinforcement Learning with Certified Radius MaximizationDeep reinforcement learning methods → Adversarial robustness and RL in finance
  24. Planning with Vision-Language Models and a Use Case in Robot-Assisted TeachingMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  25. Exploring Vision Language Models for Multimodal and Multilingual Stance DetectionMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  26. VoicePrompter: Robust Zero-Shot Voice Conversion with Voice Prompt and Conditional Flow MatchingDiffusion models → Audio, speech and music
  27. Boosting Weak Positives for Text Based Person SearchMultimodal LLMs / vision-language models → Document understanding and multimodal RAG
  28. Music2Latent2: Audio Compression with Summary Embeddings and Autoregressive DecodingDiffusion models → Audio, speech and music
  29. Heuristic-Informed Mixture of Experts for Link Prediction in Multilayer NetworksMixture-of-experts → Expert routing strategies
  30. Query-Aware Learnable Graph Pooling Tokens as Prompt for Large Language ModelsLLM reasoning → Knowledge- and tool-augmented reasoning
  31. How Much Do Code Language Models Remember? An Investigation on Data Extraction Attacks before and after Fine-tuningLLM safety and security → Membership inference attacks
  32. Solving Inverse Problems using Diffusion with Iterative Colored RenoisingDiffusion models → Inverse problems and image restoration
  33. Virus: Harmful Fine-tuning Attack for Large Language Models Bypassing Guardrail ModerationLLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks +1
  34. Human-Aligned Skill Discovery: Balancing Behaviour Exploration and AlignmentLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
  35. Certificated Actor-Critic: Hierarchical Reinforcement Learning with Control Barrier Functions for Safe NavigationDeep reinforcement learning methods → Safe and constrained RL
  36. Actions Speak Louder than Words: Agent Decisions Reveal Implicit Biases in Language ModelsLLM agents and tool use → Social simulation and multi-agent debate
  37. Leveraging In-Context Learning and Retrieval-Augmented Generation for Automatic Question Generation in Educational DomainsRetrieval-augmented generation → RAG robustness and adaptive retrieval
  38. Poisoning Attacks and Defenses to Federated UnlearningLLM safety and security → Federated unlearning and poisoning
  39. LFTR: Learning-Free Token Reduction for Multimodal Large Language ModelsMultimodal LLMs / vision-language models → Visual token pruning and efficiency +1
  40. A Dual-Agent Adversarial Framework for Robust Generalization in Deep Reinforcement LearningDeep reinforcement learning methods → Adversarial robustness and RL in finance
  41. ASAP: Exploiting the Satisficing Generalization Edge in Neural Combinatorial OptimizationDeep reinforcement learning methods → RL for games and combinatorial optimization
  42. The M-factor: A Novel Metric for Evaluating Neural Architecture Search in Resource-Constrained EnvironmentsDeep reinforcement learning methods → Deep RL algorithms and representations
  43. Interpretable Dual-Filter Fuzzy Neural Networks for Affective Brain-Computer Interfaces
  44. Bankruptcy analysis using images and convolutional neural networks (CNN)
  45. Evidence for Phenotype-Driven Disparities in Freezing of Gait Detection and Approaches to Bias Mitigation
  46. Transformer Based Time-Series Forecasting for Stock
  47. Prompt-Aware Scheduling for Efficient Text-to-Image Inferencing System
  48. A finite element-based machine learning model for hydro-mechanical analysis of swelling behavior in clay-sulfate rocks
  49. Safeguarding Privacy in Edge Speech Understanding with Tiny Foundation Models
  50. Towards Recommender Systems LLMs Playground (RecSysLLMsP): Exploring Polarization and Engagement in Simulated Social Networks
  51. Differentiable Projection-based Learn to Optimize in Wireless Network-Part I: Convex Constrained (Non-)Convex Programming
  52. Constructing Cell-type Taxonomy by Optimal Transport with Relaxed Marginal Constraints
  53. Fake News Detection After LLM Laundering: Measurement and Explanation
  54. Prompt-oriented Output of Culture-Specific Items in Translated African Poetry by Large Language Model: An Initial Multi-layered Tabular Review
  55. 3D Reconstruction of Shoes for Augmented Reality
  56. Real Time Scheduling Framework for Multi Object Detection via Spiking Neural Networks
  57. Noise-Adaptive Conformal Classification with Marginal Coverage
  58. Learning the Optimal Stopping for Early Classification within Finite Horizons via Sequential Probability Ratio Test
  59. Current Pathology Foundation Models are unrobust to Medical Center Differences
  60. Online Pricing and Allocation with Demand Learning and Fulfillment Cost
  61. From tools to thieves: Measuring and understanding public perceptions of AI through crowdsourced metaphors
  62. Generative AI for Vision: A Comprehensive Study of Frameworks and Applications
  63. KNN and K-means in Gini Prametric Spaces
  64. Perforated Backpropagation: A Neuroscience Inspired Extension to Artificial Neural Networks
  65. A Proximal Operator for Inducing 2:4-Sparsity
  66. Growing Neural Networks: Dynamic Evolution through Gradient Descent
  67. Anatomy Might Be All You Need: Forecasting What to Do During Surgery
  68. Topological Signatures of Adversaries in Multimodal Alignments
  69. Fault Localization via Fine-tuning Large Language Models with Mutation Generated Stack Traces
  70. Investigating the Monte-Carlo Tree Search Approach for the Job Shop Scheduling Problem
  71. Pressure Field Reconstruction with SIREN: A Mesh-Free Approach for Image Velocimetry in Complex Noisy Environments
  72. Efficient Feature Fusion for UAV Object Detection
  73. Belief Roadmaps with Uncertain Landmark Evanescence
  74. Limits to AI Growth: The Ecological and Social Consequences of Scaling
  75. VoD-3DGS: View-opacity-Dependent 3D Gaussian Splatting
  76. TransRAD: Retentive Vision Transformer for Enhanced Radar Object Detection
  77. KoopAGRU: A Koopman-based Anomaly Detection in Time-Series using Gated Recurrent Units
  78. Variational Combinatorial Sequential Monte Carlo for Bayesian Phylogenetics in Hyperbolic Space
  79. Deep Ensembles Secretly Perform Empirical Bayes
  80. Unsupervised Patch-GAN with Targeted Patch Ranking for Fine-Grained Novelty Detection in Medical Imaging
  81. DReSS: Data-driven Regularized Structured Streamlining for Large Language Models
  82. A Robust Support Vector Machine Approach for Raman COVID-19 Data Classification
  83. Molecular Fingerprints Are Strong Models for Peptide Function Prediction
  84. Shared DIFF Transformer
  85. The Right to AI
  86. Distilling Knowledge for Designing Computational Imaging Systems
  87. Visualization of Organ Movements Using Automatic Region Segmentation of Swallowing CT
  88. Explainable Machine Learning: An Illustration of Kolmogorov-Arnold Network Model for Airfoil Lift Prediction
  89. Progress in Artificial Intelligence and its Determinants
  90. Dialogue is Better Than Monologue: Instructing Medical LLMs via Strategical Conversations
  91. rEGGression: an Interactive and Agnostic Tool for the Exploration of Symbolic Regression Models
  92. Improving Your Model Ranking on Chatbot Arena by Vote Rigging
  93. GRACE: Generalizing Robot-Assisted Caregiving with User Functionality Embeddings
  94. Improving Genetic Programming for Symbolic Regression with Equality Graphs
  95. acoupi: An Open-Source Python Framework for Deploying Bioacoustic AI Models on Edge Devices
  96. Learning Beyond the Surface: How Far Can Continual Pre-Training with LoRA Enhance LLMs' Domain-Specific Insight Learning?
  97. Matrix Product Sketching via Coordinated Sampling
  98. Hierarchical Fallback Architecture for High Risk Online Machine Learning Inference
  99. A Comprehensive Survey on Legal Summarization: Challenges and Future Directions
  100. Robust Multimodal Learning via Cross-Modal Proxy Tokens
All 201
  1. Aggregation Schemes for Single-Vector WSI Representation Learning in Digital Pathology
  2. SSF: Sparse Long-Range Scene Flow for Autonomous Driving
  3. P-TAME: Explain Any Image Classifier with Trained Perturbations
  4. Janus-Pro: Unified Multimodal Understanding and Generation with Data and Model Scaling
  5. LEKA:LLM-Enhanced Knowledge Augmentation
  6. CrowdSplat: Exploring Gaussian Splatting For Crowd Rendering
  7. BreezyVoice: Adapting TTS for Taiwanese Mandarin with Enhanced Polyphone Disambiguation -- Challenges and Insights
  8. Detecting Anomalies Using Rotated Isolation Forest
  9. AdditiveLLM: Large Language Models Predict Defects in Additive Manufacturing
  10. Picard-KKT-hPINN: Enforcing Nonlinear Enthalpy Balances for Physically Consistent Neural Networks
  11. Long-term prediction of El Ni~no-Southern Oscillation using reservoir computing with data-driven realtime filter
  12. Self-Supervised Frameworks for Speaker Verification via Bootstrapped Positive Sampling
  13. 2SSP: A Two-Stage Framework for Structured Pruning of LLMs
  14. Generative Unordered Flow for Set-Structured Data Generation
  15. Hybrid Graphs for Table-and-Text based Question Answering using LLMs
  16. Improving Privacy Benefits of Redaction
  17. Yin-Yang: Developing Motifs With Long-Term Structure And Controllability
  18. Glioma Multimodal MRI Analysis System for Tumor Layered Diagnosis via Multi-task Semi-supervised Learning
  19. AI Governance through Markets
  20. Dynamics of Transient Structure in In-Context Linear Regression Transformers
  21. Sparser, Better, Faster, Stronger: Sparsity Detection for Efficient Automatic Differentiation
  22. Exact characterization of ε-Safe Decision Regions for exponential family distributions and Multi Cost SVM approximation
  23. Using Code Generation to Solve Open Instances of Combinatorial Design Problems
  24. Learning Semantic Facial Descriptors for Accurate Face Animation
  25. STGCN-LSTM for Olympic Medal Prediction: Dynamic Power Modeling and Causal Policy Optimization
  26. Inferring Implicit Goals Across Differing Task Models
  27. Decision-Theoretic Approaches for Improved Learning-Augmented Algorithms
  28. PulmoFusion: Advancing Pulmonary Health with Efficient Multi-Modal Fusion
  29. Segmentation-Aware Generative Reinforcement Network (GRN) for Tissue Layer Segmentation in 3-D Ultrasound Images for Chronic Low-back Pain (cLBP) Assessment
  30. Machine-Learning-Enhanced Optimization of Noise-Resilient Variational Quantum Eigensolvers
  31. ContourFormer: Real-Time Contour-Based End-to-End Instance Segmentation Transformer
  32. Temperature-Free Loss Function for Contrastive Learning
  33. Explainable Artificial Intelligence for identifying profitability predictors in Financial Statements
  34. Landscape Features in Single-Objective Continuous Optimization: Have We Hit a Wall in Algorithm Selection Generalization?
  35. FeatureGS: Eigenvalue-Feature Optimization in 3D Gaussian Splatting for Geometrically Accurate and Artifact-Reduced Reconstruction
  36. Drivetrain simulation using variational autoencoders
  37. Tonguescape: Exploring Language Models Understanding of Vowel Articulation
  38. Efficient Redundancy Reduction for Open-Vocabulary Semantic Segmentation
  39. HOMER: Homography-Based Efficient Multi-view 3D Object Removal
  40. In-Context Meta LoRA Generation
  41. Federated Learning With Individualized Privacy Through Client Sampling
  42. Uncertainty Quantification and Decomposition for LLM-based Recommendation
  43. A Rigorous Turing Test: a Foundation for Evaluating Artificial General Intelligence
  44. Dual Invariance Self-training for Reliable Semi-supervised Surgical Phase Recognition
  45. Structured Context Recomposition for Large Language Models Using Probabilistic Layer Realignment
  46. Cross-lingual Embedding Clustering for Hierarchical Softmax in Low-Resource Multilingual Speech Recognition
  47. nabqr: Python package for improving probabilistic forecasts
  48. RegionGCN: Spatial-Heterogeneity-Aware Graph Convolutional Networks
  49. Semantic Consistency Regularization with Large Language Models for Semi-supervised Sentiment Analysis
  50. Technical report on label-informed logit redistribution for better domain generalization in low-shot classification with foundation models
  51. Watch Your STEPP: Semantic Traversability Estimation using Pose Projected Features
  52. Extracting Inter-Protein Interactions Via Multitasking Graph Structure Learning
  53. GLLM: Self-Corrective G-Code Generation using Large Language Models with User Feedback
  54. CSEval: Towards Automated, Multi-Dimensional, and Reference-Free Counterspeech Evaluation using Auto-Calibrated LLMs
  55. Trustworthy image-to-image translation: evaluating uncertainty calibration in unpaired training scenarios
  56. A linguistically-motivated evaluation methodology for unraveling model's abilities in reading comprehension tasks
  57. Histogram Approaches for Imbalanced Data Streams Regression
  58. Exploring the Potential of Wireless-enabled Multi-Chip AI Accelerators
  59. GraphChase: A Platform and Benchmark for Urban Network Security Games
  60. An Exceptional Dataset For Rare Pancreatic Tumor Segmentation
  61. Closing the Gap Between Synthetic and Ground Truth Time Series Distributions via Neural Mapping
  62. Action Recognition Using Temporal Shift Module and Ensemble Learning
  63. Towards Training-Free Open-World Classification with 3D Generative Models
  64. Is Conversational XAI All You Need? Human-AI Decision Making With a Conversational XAI Assistant
  65. 3DSES: an indoor Lidar point cloud segmentation dataset with real and pseudo-labels from a 3D model
  66. RegD: Hierarchical Embeddings via Dissimilarity between Arbitrary Euclidean Regions
  67. Sequential Learning of the Pareto Front for Multi-objective Bandits
  68. A survey on Clustered Federated Learning: Taxonomy, Analysis and Applications
  69. LLM Assistance for Pediatric Depression
  70. Reflections on "Can AI Understand Our Universe?"
  71. A Sampling Complexity-aware Framework for Discrete-time Fractional-Order Dynamical System Identification
  72. SemML: Enhancing Automata-Theoretic LTL Synthesis with Machine Learning
  73. Certifying Pareto-Optimality in Multi-Objective Maximum Satisfiability
  74. Neural Spelling: A Spell-Based BCI System for Language Neural Decoding
  75. DINT Transformer
  76. DFPE: A Diverse Fingerprint Ensemble for Enhancing LLM Performance
  77. Large Language Models for Single-Step and Multi-Step Flight Trajectory Prediction
  78. A review on the novelty measurements of academic papers
  79. A Constraint-Preserving Neural Network Approach for Solving Mean-Field Games Equilibrium
  80. Cross-Language Approach for Quranic QA
  81. Gradual Domain Adaptation for Graph Learning
  82. Towards Making Flowchart Images Machine Interpretable
  83. Algorithmic Segmentation and Behavioral Profiling for Ransomware Detection Using Temporal-Correlation Graphs
  84. WCDT: Systematic WCET Optimization for Decision Tree Implementations
  85. SIGN: A Statistically-Informed Gaze Network for Gaze Time Prediction
  86. si4onnx: A Python package for Selective Inference in Deep Learning Models
  87. Reqo: A Comprehensive Learning-Based Cost Model for Robust and Explainable Query Optimization
  88. A Genetic Algorithm-Based Approach for Automated Optimization of Kolmogorov-Arnold Networks in Classification Tasks
  89. General Scene Adaptation for Vision-and-Language Navigation
  90. MultiChallenge: A Realistic Multi-Turn Conversation Evaluation Benchmark Challenging to Frontier LLMs
  91. Intensional Inheritance Between Concepts: An Information-Theoretic Interpretation
  92. Byzantine-Robust Federated Learning over Ring-All-Reduce Distributed Computing
  93. Assessing the Capability of YOLO- and Transformer-based Object Detectors for Real-time Weed Detection
  94. Context-Aware Semantic Recomposition Mechanism for Large Language Models
  95. Do We Really Need to Design New Byzantine-robust Aggregation Rules?
  96. A Geometric Perspective for High-Dimensional Multiplex Graphs
  97. Data-Informed Model Complexity Metric for Optimizing Symbolic Regression Models
  98. Breaking the log(1/Delta2) Barrier: Better Batched Best Arm Identification with Adaptive Grids
  99. Forecasting S&P 500 Using LSTM Models
  100. On the Coexistence and Ensembling of Watermarks
  101. Fundamental Computational Limits in Pursuing Invariant Causal Prediction and Invariance-Guided Regularization