mlsanityData to 14 Oct 2026

Papers

New on arXiv

Sun 24 Aug 2025

178 papers

  1. Less Is More: Elevating RAG via Performance-Driven Context CompressionRetrieval-augmented generation → Generation and context integration +1
  2. FLAIRR-TS -- Forecasting LLM-Agents with Iterative Refinement and Retrieval for Time SeriesLLM agents and tool use → Financial trading and forecasting agents
  3. LLMs Can't Handle Peer Pressure: Crumbling under Multi-Agent Social InteractionsLLM agents and tool use → Social simulation and multi-agent debate
  4. LodeStar: Long-horizon Dexterity via Synthetic Data Augmentation from Human DemonstrationsSynthetic data and self-improvement for LLMs → Self-evolving LLM agents
  5. Debate or Vote: Which Yields Better Decisions in Multi-Agent Large Language Models?LLM reasoning → Reasoning for agents, planning and code +1
  6. Benchmarking Retrieval-Augmented Generation Strategies for Large Language Model-Based Travel Mode Choice PredictionRetrieval-augmented generation → RAG for recommendation
  7. GateTS: Versatile and Efficient Forecasting via Attention-Inspired routed Mixture-of-ExpertsMixture-of-experts → MoE for time series and graphs
  8. School of Reward Hacks: Hacking harmless tasks generalizes to misaligned behavior in LLMsLLM alignment / RLHF / preference optimisation → Reward hacking and misspecification
  9. DinoTwins: Combining DINO and Barlow Twins for Robust, Label-Efficient Vision TransformersKnowledge distillation → General knowledge distillation methods
  10. T2I-ReasonBench: Benchmarking Reasoning-Informed Text-to-Image GenerationLLM reasoning → Multimodal reasoning
  11. MoE-Inference-Bench: Performance Evaluation of Mixture of Expert Large Language and Vision ModelsMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning +1
  12. Bias Amplification in Stable Diffusion's Representation of Stigma Through Skin Tones and Their HomogeneityDiffusion models → Image generation, text-to-image and editing
  13. ReviBranch: Deep Reinforcement Learning for Branch-and-Bound with Revived TrajectoriesDeep reinforcement learning methods → Deep RL algorithms and representations
  14. Robotic Manipulation via Imitation Learning: Taxonomy, Evolution, Benchmark, and ChallengesOffline RL and imitation learning from data → Robot manipulation imitation learning
  15. Rectified Robust Policy Optimization for Model-Uncertain Constrained Reinforcement Learning without Strong DualityDeep reinforcement learning methods → RL theory and sample complexity
  16. TreePO: Bridging the Gap of Policy Optimization and Efficacy and Inference Efficiency with Heuristic Tree-based ModelingLLM reasoning → Reinforcement learning for reasoning +1
  17. An LLM-LVLM Driven Agent for Iterative and Fine-Grained Image EditingLLM agents and tool use → Multimodal and embodied agents
  18. TinySR: Pruning Diffusion for Real-World Image Super-ResolutionDiffusion models → Inverse problems and image restoration
  19. Constrained Prompt Enhancement for Improving Zero-Shot Generalization of Vision-Language ModelsMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  20. DashboardQA: Benchmarking Multimodal Agents for Question Answering on Interactive DashboardsLLM agents and tool use → Multimodal and embodied agents
  21. LVLM-Aware Multimodal Retrieval for RAG-Based Medical Diagnosis with General-Purpose ModelsRetrieval-augmented generation → Medical and biomedical RAG
  22. Agent-Testing Agent: A Meta-Agent for Automated Testing and Evaluation of Conversational AI AgentsLLM agents and tool use → General LLM agent frameworks and benchmarks
  23. Graph-R1: Incentivizing the Zero-Shot Graph Learning Capability in LLMs via Explicit ReasoningLLM reasoning → Knowledge- and tool-augmented reasoning
  24. Computational Multi-Agents Society Experiments: Social Modeling Framework Based on Generative AgentsLLM agents and tool use → Social simulation and multi-agent debate
  25. DiCache: Let Diffusion Model Determine Its Own CacheDiffusion models → Diffusion foundations and sampling
  26. Agentic AI for Software: thoughts from Software Engineering communityLLM agents and tool use → Software engineering coding agents
  27. Capturing Legal Reasoning Paths from Facts to Law in Court Judgments using Knowledge GraphsLLM reasoning → Reasoning for agents, planning and code
  28. Mind the (Language) Gap: Towards Probing Numerical and Cross-Lingual Limits of LVLMsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  29. Omne-R1: Learning to Reason with Memory for Multi-hop Question AnsweringLLM reasoning → Knowledge- and tool-augmented reasoning
  30. Chinese Court Simulation with LLM-Based Agent SystemLLM agents and tool use → Social simulation and multi-agent debate
  31. AdaptiveK: Complexity-Driven Sparse Autoencoders for Interpretable Language Model RepresentationsMechanistic interpretability → SAE features and their applications
  32. Handling Students Dropouts in an LLM-driven Interactive Online Course Using Language ModelsLLM agents and tool use → Educational agents and math problem solving
  33. FoundDiff: Foundational Diffusion Model for Generalizable Low-Dose CT DenoisingDiffusion models → Medical imaging and segmentation
  34. Explain Before You Answer: A Survey on Compositional Visual ReasoningLLM reasoning → Multimodal reasoning
  35. Meta-R1: Empowering Large Reasoning Models with MetacognitionLLM reasoning → Test-time compute and efficient thinking
  36. MEENA (PersianMMMU): Multimodal-Multilingual Educational Exams for N-level AssessmentMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  37. From Language to Action: A Review of Large Language Models as Autonomous Agents and Tool UsersLLM agents and tool use → General LLM agent frameworks and benchmarks
  38. AdaGAT: Adaptive Guidance Adversarial Training for the Robustness of Deep Neural NetworksKnowledge distillation → Federated, robust and private distillation
  39. Federated Reinforcement Learning for Runtime Optimization of AI Applications in Smart EyewearsDeep reinforcement learning methods → RL for energy, networks and operations
  40. Are You Sure You're Positive? Consolidating Chain-of-Thought Agents with Uncertainty Quantification for Aspect-Category Sentiment AnalysisLLM reasoning → Audio-language model reasoning
  41. Routing Distilled Knowledge via Mixture of LoRA Experts for Large Language Model based Bundle GenerationKnowledge distillation → Knowledge distillation for LLMs
  42. Uncovering and Mitigating Destructive Multi-Embedding Attacks in Deepfake Proactive ForensicsLLM safety and security → Watermarking generated content and models
  43. CoViPAL: Layer-wise Contextualized Visual Token Pruning for Large Vision-Language ModelsMultimodal LLMs / vision-language models → Visual token pruning and efficiency +1
  44. Module-Aware Parameter-Efficient Machine Unlearning on TransformersLLM safety and security → Machine unlearning
  45. 4D Visual Pre-training for Robot LearningDiffusion models → Diffusion and flow policies for robotics
  46. Multi-Metric Preference Alignment for Generative Speech RestorationLLM alignment / RLHF / preference optimisation → Preference alignment for recommenders and RAG
  47. SSFO: Self-Supervised Faithfulness Optimization for Retrieval-Augmented GenerationRetrieval-augmented generation → RAG robustness and adaptive retrieval +1
  48. Exposing Privacy Risks in Graph Retrieval-Augmented GenerationRetrieval-augmented generation → Privacy and security of RAG
  49. TokenLake: A Unified Segment-level Prefix Cache Pool for Fine-grained Elastic Long-Context LLM ServingEfficient LLM inference and serving → KV cache optimization
  50. How to make Medical AI Systems safer? Simulating Vulnerabilities, and Threats in Multimodal Medical RAG SystemMultimodal LLMs / vision-language models → Medical vision-language models +1
  51. Reinforcement Learning enhanced Online Adaptive Clinical Decision Support via Digital Twin powered Policy and Treatment Effect optimized RewardDeep reinforcement learning methods → RL for clinical treatment and surgery
  52. Multi-Agent Visual-Language Reasoning for Comprehensive Highway Scene UnderstandingLLM reasoning → Chain-of-thought reasoning for driving +2
  53. From reactive to cognitive: brain-inspired spatial intelligence for embodied agentsLLM agents and tool use → Multimodal and embodied agents
  54. BudgetThinker: Empowering Budget-aware LLM Reasoning with Control TokensLLM reasoning → Test-time compute and efficient thinking
  55. PosterGen: Aesthetic-Aware Multi-Modal Paper-to-Poster Generation via Multi-Agent LLMsLLM agents and tool use → Multimodal and embodied agents
  56. Linear Dynamics meets Linear MDPs: Closed-Form Optimal Policies via Reinforcement LearningDeep reinforcement learning methods → RL theory and sample complexity
  57. Towards Alignment-Centric Paradigm: A Survey of Instruction Tuning in Large Language ModelsLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  58. LLM Assertiveness can be Mechanistically Decomposed into Emotional and Logical ComponentsMechanistic interpretability → Probing deception, bias and beliefs
  59. MaRVL-QA: A Benchmark for Mathematical Reasoning over Visual LandscapesLLM reasoning → Spatial and embodied reasoning +1
  60. Impact of Neuron Models on Spiking Neural Networks performance. A Complexity Based Classification Approach
  61. Association of Timing and Duration of Moderate-to-Vigorous Physical Activity with Cognitive Function and Brain Aging: A Population-Based Study Using the UK Biobank
  62. Speech-Based Cognitive Screening: A Systematic Evaluation of LLM Adaptation Strategies
  63. The Lifecycle Principle: Stabilizing Dynamic Neural Networks with State Memory
  64. Applying Deep Learning to Anomaly Detection of Russian Satellite Activity for Indications Prior to Military Activity
  65. Adaptive Physics-Informed Neural Networks with Multi-Category Feature Engineering for Hydrogen Sorption Prediction in Clays, Shales, and Coals
  66. Teaching AI to Remember: Insights from Brain-Inspired Replay in Continual Learning
  67. Exploring and Reshaping the Weight Distribution in LLM
  68. Performance is not All You Need: Sustainability Considerations for Algorithms
  69. Normalisation of SWIFT Message Counterparties with Feature Extraction and Clustering
  70. Improving Liver Disease Diagnosis with SNNDeep: A Custom Spiking Neural Network Using Diverse Learning Algorithms
  71. Towards Better Correctness and Efficiency in Code Generation
  72. Particle swarm optimization for online sparse streaming feature selection under uncertainty
  73. CORTEX: Composite Overlay for Risk Tiering and Exposure in Operational AI Systems
  74. Facilitating Matches on Allocation Platforms
  75. Structures Meet Semantics: Multimodal Fusion via Graph Contrastive Learning
  76. ZTFed-MAS2S: A Zero-Trust Federated Learning Framework with Verifiable Privacy and Trust-Aware Aggregation for Wind Power Data Imputation
  77. Boltzina: Efficient and Accurate Virtual Screening via Docking-Guided Binding Prediction with Boltz-2
  78. Bridging Graph and State-Space Modeling for Intensive Care Unit Length of Stay Prediction
  79. In-Context Algorithm Emulation in Fixed-Weight Transformers
  80. High-Order Langevin Monte Carlo Algorithms
  81. Activation Transport Operators
  82. Minimal Solvers for Full DoF Motion Estimation from Asynchronous Tracks
  83. Gumbel-MPNN: Graph Rewiring with Gumbel-Softmax
  84. OmniMRI: A Unified Vision--Language Foundation Model for Generalist MRI Interpretation
  85. Modeling Irregular Astronomical Time Series with Neural Stochastic Delay Differential Equations
  86. An experimental approach: The graph of graphs
  87. TANDEM: Temporal Attention-guided Neural Differential Equations for Missingness in Time Series Classification
  88. Learning Interpretable Differentiable Logic Networks for Time-Series Classification
  89. Social-MAE: A Transformer-Based Multimodal Autoencoder for Face and Voice
  90. Multimodal Representation Learning Conditioned on Semantic Relations
  91. Improving French Synthetic Speech Quality via SSML Prosody Control
  92. Efficient Zero-Shot Long Document Classification by Reducing Context Through Sentence Ranking
  93. Optimizing Multi-Modality Trackers via Significance-Regularized Tuning
  94. GraphMMP: A Graph Neural Network Model with Mutual Information and Global Fusion for Multimodal Medical Prognosis
  95. A Human-In-The-Loop Approach for Improving Fairness in Predictive Business Process Monitoring
  96. A Synthetic Dataset for Manometry Recognition in Robotic Applications
  97. Optimizing Grasping in Legged Robots: A Deep Learning Approach to Loco-Manipulation
  98. Evaluating the Impact of Verbal Multiword Expressions on Machine Translation
  99. Adversarial Examples Are Not Bugs, They Are Superposition
  100. A Systematic Literature Review on Multi-label Data Stream Classification
All 178
  1. Persuasion Dynamics in LLMs: Investigating Robustness and Adaptability in Knowledge and Safety with DuET-PD
  2. Solving Constrained Stochastic Shortest Path Problems with Scalarisation
  3. MahaParaphrase: A Marathi Paraphrase Detection Corpus and BERT-based Models
  4. Multi-Level LVLM Guidance for Untrimmed Video Action Recognition
  5. Programmable k-local Ising interactions and shallow optical Kolmogorov--Arnold networks through repeated data encounters
  6. Investigating Domain Gaps for Indoor 3D Object Detection
  7. Disentangled Geometry and Appearance for Efficient Multi-View Surface Reconstruction and Rendering
  8. FedKLPR: KL-Guided Pruning-Aware Federated Learning for Person Re-Identification
  9. GMOR: A Lightweight Robust Point Cloud Registration Framework via Geometric Maximum Overlapping
  10. Modular MeanFlow: Towards Stable and Scalable One-Step Generative Modeling
  11. Data Leakage in Visual Datasets
  12. A Ridge Too Far: Correcting Over-Shrinkage via Negative Regularization
  13. E-BayesSAM: Efficient Bayesian Adaptation of SAM with Self-Optimizing KAN-Based Interpretation for Uncertainty-Aware Ultrasonic Segmentation
  14. FRAME : Comprehensive Risk Assessment Framework for Adversarial Machine Learning Threats
  15. MoSA: Motion-Coherent Human Video Generation via Structure-Appearance Decoupling
  16. Mutual Information Surprise: Rethinking Unexpectedness in Autonomous Systems
  17. DS@GT at CheckThat! 2025: A Simple Retrieval-First, LLM-Backed Framework for Claim Normalization
  18. Retrieval Capabilities of Large Language Models Scale with Pretraining FLOPs
  19. Enhancing Underwater Images via Deep Learning: A Comparative Study of VGG19 and ResNet50-Based Approaches
  20. Large Language Models as Universal Predictors? An Empirical Study on Small Tabular Datasets
  21. Neural Proteomics Fields for Super-resolved Spatial Proteomics Prediction
  22. Effective Clustering for Large Multi-Relational Graphs
  23. DART: A Server-side Plug-in for Resource-efficient Robust Federated Learning
  24. Mimicking the Physicist's Eye:A VLM-centric Approach for Physics Formula Discovery
  25. UI-Level Evaluation of ALLaM 34B: Measuring an Arabic-Centric LLM via HUMAIN Chat
  26. ShaLa: Multimodal Shared Latent Space Modelling
  27. Condition Weaving Meets Expert Modulation: Towards Universal and Controllable Image Generation
  28. Trust Me, I Know This Function: Hijacking LLM Static Analysis using Bias
  29. Detecting Struggling Student Programmers using Proficiency Taxonomies
  30. The Arabic Generality Score: Another Dimension of Modeling Arabic Dialectness
  31. No Pixel Left Behind: A Detail-Preserving Architecture for Robust High-Resolution AI-Generated Image Detection
  32. ShortListing Model: A Streamlined SimplexDiffusion for Discrete Variable Generation
  33. Who Wins the Race? (R Vs Python) - An Exploratory Study on Energy Consumption of Machine Learning Algorithms
  34. DanceEditor: Towards Iterative Editable Music-driven Dance Generation with Open-Vocabulary Descriptions
  35. MetaFed: Advancing Privacy, Performance, and Sustainability in Federated Metaverse Systems
  36. DropLoRA: Sparse Low-Rank Adaptation for Parameter-Efficient Fine-Tuning
  37. Modality-Specific Speech Enhancement and Noise-Adaptive Fusion for Acoustic and Body-Conduction Microphone Framework
  38. Semantic Diffusion Posterior Sampling for Cardiac Ultrasound Dehazing
  39. CultranAI at PalmX 2025: Data Augmentation for Cultural Knowledge Representation
  40. Is the Frequency Principle always valid?
  41. SpecGen: Neural Spectral BRDF Generation via Spectral-Spatial Tri-plane Aggregation
  42. Defending Deepfake via Texture Feature Perturbation
  43. Bine Trees: Enhancing Collective Operations by Optimizing Communication Locality
  44. First Place Solution to the MLCAS 2025 GWFSS Challenge: The Devil is in the Detail and Minority
  45. Physics-informed neural network for predicting fatigue life of unirradiated and irradiated austenitic and ferritic/martensitic steels under reactor-relevant conditions
  46. PosBridge: Multi-View Positional Embedding Transplant for Identity-Aware Image Editing
  47. Explainable AI (XAI) for Arrhythmia detection from electrocardiograms
  48. Quickly Tuning Foundation Models for Image Segmentation
  49. ERF-BA-TFD+: A Multimodal Model for Audio-Visual Deepfake Detection
  50. MTNet: Learning modality-aware representation with transformer for RGBT tracking
  51. DeepCFD: Efficient near-ground airfoil lift coefficient approximation with deep convolutional neural networks
  52. Deep Learning-Assisted Detection of Sarcopenia in Cross-Sectional Computed Tomography Imaging
  53. Spatial-Temporal Human-Object Interaction Detection
  54. CLIFF: Continual Learning for Incremental Flake Features in 2D Material Identification
  55. ResLink: A Novel Deep Learning Architecture for Brain Tumor Classification with Area Attention and Residual Connections
  56. Provable Generalization in Overparameterized Neural Nets
  57. SEER-VAR: Semantic Egocentric Environment Reasoner for Vehicle Augmented Reality
  58. A biological vision inspired framework for machine perception of abutting grating illusory contours
  59. L-XAIDS: A LIME-based eXplainable AI framework for Intrusion Detection Systems
  60. PersPose: 3D Human Pose Estimation with Perspective Encoding and Perspective Rotation
  61. Learning Short-Term and Long-Term Patterns of High-Order Dynamics in Real-World Networks
  62. ClaimGen-CN: A Large-scale Chinese Dataset for Legal Claim Generation
  63. Curvature Learning for Generalization of Hyperbolic Neural Networks
  64. Deep Learning Architectures for Medical Image Denoising: A Comparative Study of CNN-DAE, CADTra, and DCMIEDNet
  65. MC3G: Model Agnostic Causally Constrained Counterfactual Generation
  66. Learning Graph-Indexed Trajectory Patterns for Stochastic On-Time Arrival Routing
  67. Deep Learning with Self-Attention and Enhanced Preprocessing for Precise Diagnosis of Acute Lymphoblastic Leukemia from Bone Marrow Smears in Hemato-Oncology
  68. Multi-modal Knowledge Decomposition based Online Distillation for Biomarker Prediction in Breast Cancer Histopathology
  69. Explainable Counterfactual Reasoning in Depression Medication Selection at Multi-Levels (Personalized and Population)
  70. Active Domain Knowledge Acquisition with 100-Dollar Budget: Enhancing LLMs via Cost-Efficient, Expert-Involved Interaction in Sensitive Domains
  71. Large Language Model-Based Automatic Formulation for Stochastic Optimization Models
  72. MMCIG: Multimodal Cover Image Generation for Text-only Documents and Its Dataset Construction via Pseudo-labeling
  73. Advancing Weakly-Supervised Change Detection in Satellite Images via Adversarial Class Prompting
  74. Scaling Graph Transformers: A Comparative Study of Sparse and Dense Attention
  75. Sharpness-Aware Geometric Defense for Robust Out-Of-Distribution Detection
  76. VROOM - Visual Reconstruction over Onboard Multiview
  77. Achieving detailed medial temporal lobe segmentation with upsampled isotropic training from implicit neural representation
  78. ONG: Orthogonal Natural Gradient Descent