mlsanityData to 14 Oct 2026

Papers

New on arXiv

Fri 16 Aug 2024

230 papers

  1. VERA: Validation and Evaluation of Retrieval-Augmented SystemsRetrieval-augmented generation → RAG pipeline design and evaluation
  2. DivDiff: A Conditional Diffusion Model for Diverse Human Motion PredictionDiffusion models → Video generation
  3. Gradient Reduction Convolutional Neural Network Policy for Financial Deep Reinforcement LearningDeep reinforcement learning methods → Adversarial robustness and RL in finance
  4. SEAL: Systematic Error Analysis for Value ALignmentLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  5. Diffusion Model for Planning: A Systematic Literature ReviewDiffusion models → Diffusion and flow policies for robotics
  6. Improving VTE Identification through Language Models from Radiology Reports: A Comparative Study of Mamba, Phi-3 Mini, and BERTState-space sequence models (S4, Mamba) → Mamba for medical image analysis
  7. Multi Teacher Privileged Knowledge Distillation for Multimodal Expression RecognitionKnowledge distillation → Multimodal distillation
  8. Efficient Autoregressive Audio Modeling via Next-Scale PredictionDiffusion models → Audio, speech and music
  9. Meta Knowledge for Retrieval Augmented Large Language ModelsRetrieval-augmented generation → RAG pipeline design and evaluation
  10. Classifier-Free Guidance is a Predictor-CorrectorDiffusion models → Diffusion foundations and sampling
  11. On the Undecidability of Artificial Intelligence Alignment: Machines that HaltLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
  12. Model-based RL as a Minimalist Approach to Horizon-Free and Second-Order BoundsDeep reinforcement learning methods → RL theory and sample complexity
  13. Trust-Oriented Adaptive Guardrails for Large Language ModelsLLM safety and security → Safety alignment, refusal and guardrails
  14. xGen-MM (BLIP-3): A Family of Open Large Multimodal ModelsMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  15. PEDAL: Enhancing Greedy Decoding with Large Language Models using Diverse ExemplarsLLM reasoning → Test-time compute and efficient thinking
  16. Visual Agents as Fast and Slow ThinkersLLM reasoning → Multimodal reasoning +1
  17. DPA: Dual Prototypes Alignment for Unsupervised Adaptation of Vision-Language ModelsMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  18. FLEXTAF: Enhancing Table Reasoning with Flexible Tabular FormatsLLM reasoning → Knowledge- and tool-augmented reasoning
  19. RGBT Tracking via All-layer Multimodal Interactions with Progressive Fusion MambaState-space sequence models (S4, Mamba) → Point clouds, detection and remote sensing
  20. PFDiff: Training-Free Acceleration of Diffusion Models Combining Past and Future ScoresDiffusion models → Diffusion foundations and sampling
  21. TRAM: Test-Time Risk Adaptation with Mixture of AgentsLLM agents and tool use → Agent threats, guardrails and governance
  22. Mitigating Information Loss in Tree-Based Reinforcement Learning via Direct OptimizationDeep reinforcement learning methods → Interpretable and logic-guided RL
  23. Comparative Analysis of Generative Models: Enhancing Image Synthesis with VAEs, GANs, and Stable DiffusionDiffusion models → Diffusion foundations and sampling
  24. Efficient Multi-Policy Evaluation for Reinforcement LearningDeep reinforcement learning methods → RL theory and sample complexity
  25. Beyond the Hype: A dispassionate look at vision-language models in medical scenarioMultimodal LLMs / vision-language models → Medical vision-language models
  26. Med-PMC: Medical Personalized Multi-modal Consultation with a Proactive Ask-First-Observe-Next ParadigmMultimodal LLMs / vision-language models → Medical vision-language models
  27. The Fellowship of the LLMs: Multi-Model Workflows for Synthetic Preference Optimization Dataset GenerationLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
  28. Neural Reward MachinesDeep reinforcement learning methods → Interpretable and logic-guided RL
  29. Chain of Thought Still Thinks Fast: APriCoT Helps with Thinking SlowLLM reasoning → Prompting and chain-of-thought reasoning
  30. Math-PUMA: Progressive Upward Multimodal Alignment to Enhance Mathematical ReasoningLLM reasoning → Multimodal reasoning +1
  31. A Survey on Benchmarks of Multimodal Large Language ModelsMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  32. Persona is a Double-edged Sword: Mitigating the Negative Impact of Role-playing Prompts in Zero-shot Reasoning TasksLLM reasoning → Reasoning benchmarks and evaluation
  33. Reference-free Axial Super-resolution of 3D Microscopy Images using Implicit Neural Representation with a 2D Diffusion PriorDiffusion models → Inverse problems and image restoration
  34. Generative Dataset Distillation Based on Diffusion ModelDiffusion models → Diffusion foundations and sampling
  35. RadioDiff: An Effective Generative Diffusion Model for Sampling-Free Dynamic Radio Map ConstructionDiffusion models → Diffusion for compression and wireless
  36. Reasoning Circuits in Language Models: A Mechanistic Interpretation of Syllogistic InferenceLLM reasoning → Reasoning benchmarks and evaluation +1
  37. Tell Codec What Worth Compressing: Semantically Disentangled Image Coding for Machine with LMMsMultimodal LLMs / vision-language models → Visual token pruning and efficiency
  38. A New Chinese Landscape Paintings Generation Model based on Stable Diffusion using DreamBoothDiffusion models → Image generation, text-to-image and editing
  39. Computational Complexity of Standpoint LTLLLM reasoning → Reasoning benchmarks and evaluation
  40. ABQ-LLM: Arbitrary-Bit Quantized Inference Acceleration for Large Language ModelsEfficient LLM inference and serving → KV cache quantization
  41. CommunityKG-RAG: Leveraging Community Structures in Knowledge Graphs for Advanced Retrieval-Augmented Generation in Fact-CheckingRetrieval-augmented generation → Knowledge-graph and structured-knowledge RAG
  42. Inverse design with conditional cascaded diffusion modelsDiffusion models → Diffusion foundations and sampling
  43. MuRAR: A Simple and Effective Multimodal Retrieval and Answer Refinement Framework for Multimodal Question AnsweringRetrieval-augmented generation → Multimodal RAG
  44. Visual-Friendly Concept Protection via Selective Adversarial PerturbationsDiffusion models → Robustness, privacy and adversarial aspects
  45. Efficient Image-to-Image Diffusion Classifier for Adversarial RobustnessDiffusion models → Robustness, privacy and adversarial aspects
  46. FunEditor: Achieving Complex Image Edits via Function Aggregation with Diffusion ModelsDiffusion models → Image generation, text-to-image and editing
  47. Parallel Unlearning in Inherited Model NetworksLLM safety and security → Machine unlearning
  48. Context-Aware Assistant Selection for Improved Inference Acceleration with Large Language ModelsEfficient LLM inference and serving → Early exit and edge inference
  49. textitMMJ-Bench: A Comprehensive Study on Jailbreak Attacks and Defenses for Multimodal Large Language ModelsLLM safety and security → Vision-language and text-to-image safety
  50. A Novel Approach to Classify Power Quality Signals Using Vision Transformers
  51. Detecting Misinformation in Multimedia Content through Cross-Modal Entity Consistency: A Dual Learning Approach
  52. TACOS: Task Agnostic Continual Learning in Spiking Neural Networks
  53. A novel fusion of Sentinel-1 and Sentinel-2 with climate data for crop phenology estimation using Machine Learning
  54. Navigating the sociotechnical labyrinth: Dynamic certification for responsible embodied AI
  55. Using large language models to estimate features of multi-word expressions: Concreteness, valence, arousal
  56. Brownian Motion with a Pulse: A Biostatistician's Guide to Diffusions, Bridges, Functional PCA, and First-Passage Models
  57. Handling abort commands for household kitchen robots
  58. Efficient Task Transfer for HLS DSE
  59. Bayesian Network Modeling of Causal Influence within Cognitive Domains and Clinical Dementia Severity Ratings for Western and Indian Cohorts
  60. Speaking the Same Language: Leveraging LLMs in Standardizing Clinical Data for AI
  61. Risks and NLP Design: A Case Study on Procedural Document QA
  62. Convexity-based Pruning of Speech Representation Models
  63. Data-Driven Fire Modeling: Learning First Arrival Times and Model Parameters with Neural Networks
  64. OpenCity: Open Spatio-Temporal Foundation Models for Traffic Prediction
  65. Generating Streamlining Constraints with Large Language Models
  66. Towards Efficient Machine Learning Method for IoT DDoS Attack Detection
  67. Distributed and Secure Kernel-Based Quantum Machine Learning
  68. Learning to Route for Dynamic Adapter Composition in Continual Learning with Language Models
  69. Inertia in Moral and Value Judgments of Large Language Models
  70. mRNA2vec: mRNA Embedding with Language Model in the 5'UTR-CDS for mRNA Design
  71. Keep Calm and Relax -- HMI for Autonomous Vehicles
  72. ADen: Adaptive Density Representations for Sparse-view Camera Pose Estimation
  73. Error Bounds For Gaussian Process Regression Under Bounded Support Noise With Applications To Safety Certification
  74. Effects of Collaboration on the Performance of Interactive Theme Discovery Systems
  75. On the Completeness of Conflict-Based Search: Temporally-Relative Duplicate Pruning
  76. AdaRank: Disagreement Based Module Rank Prediction for Low-rank Adaptation
  77. An optimal pairwise merge algorithm improves the quality and consistency of nonnegative matrix factorization
  78. Comparative Performance Analysis of Transformer-Based Pre-Trained Models for Detecting Keratoconus Disease
  79. Controlling Statistical, Discretization, and Truncation Errors in Learning Fourier Linear Operators
  80. A Confidence Interval for the ℓ2 Expected Calibration Error
  81. Adaptive Uncertainty Quantification for Generative AI
  82. Ask, Attend, Attack: A Effective Decision-Based Black-Box Targeted Attack for Image-to-Text Models
  83. Fire Dynamic Vision: Image Segmentation and Tracking for Multi-Scale Fire and Plume Behavior
  84. Deep Generative Classification of Blood Cell Morphology
  85. From Lazy to Prolific: Tackling Missing Labels in Open Vocabulary Extreme Classification by Positive-Unlabeled Sequence Learning
  86. Electroencephalogram Emotion Recognition via AUC Maximization
  87. See What LLMs Cannot Answer: A Self-Challenge Framework for Uncovering LLM Weaknesses
  88. Enhancing Object Detection with Hybrid dataset in Manufacturing Environments: Comparing Federated Learning to Conventional Techniques
  89. Image class translation: visual inspection of class-specific hypotheticals and classification based on translation distance
  90. ASGM-KG: Unveiling Alluvial Gold Mining Through Knowledge Graphs
  91. A Multi-Task and Multi-Label Classification Model for Implicit Discourse Relation Recognition
  92. Differentiable Edge-based OPC
  93. Online SLA Decomposition: Enabling Real-Time Adaptation to Evolving Network Systems
  94. BnSentMix: A Diverse Bengali-English Code-Mixed Dataset for Sentiment Analysis
  95. Information-Theoretic Progress Measures reveal Grokking is an Emergent Phase Transition
  96. A Factored MDP Approach To Moving Target Defense With Dynamic Threat Modeling and Cost Efficiency
  97. RoarGraph: A Projected Bipartite Graph for Efficient Cross-Modal Approximate Nearest Neighbor Search
  98. Personalized Federated Collaborative Filtering: A Variational AutoEncoder Approach
  99. DePrompt: Desensitization and Evaluation of Personal Identifiable Information in Large Language Model Prompts
  100. Imprecise Belief Fusion Facing a DST benchmark problem
All 230
  1. Accelerating Giant Impact Simulations with Machine Learning
  2. SAM2-UNet: Segment Anything 2 Makes Strong Encoder for Natural and Medical Image Segmentation
  3. A Hassle-free Algorithm for Private Learning in Practice: Don't Use Tree Aggregation, Use BLTs
  4. Stochastic Bandits Robust to Adversarial Attacks
  5. A Unified Framework for Next-Gen Urban Forecasting via LLM-driven Dependency Retrieval and GeoTransformer
  6. PsychoLex: Unveiling the Psychological Mind of Large Language Models
  7. HistoGym: A Reinforcement Learning Environment for Histopathological Image Analysis
  8. Shapley Marginal Surplus for Strong Models
  9. Entropy Coding of Unordered Data Structures
  10. LEVIS: Large Exact Verifiable Input Spaces for Neural Networks
  11. Optimal Symmetries in Binary Classification
  12. EasyRec: Simple yet Effective Language Models for Recommendation
  13. An Empirical Examination of Balancing Strategy for Counterfactual Estimation on Time Series
  14. Retrieval-augmented Few-shot Medical Image Segmentation with Foundation Models
  15. Constructing Domain-Specific Evaluation Sets for LLM-as-a-judge
  16. CIKMar: A Dual-Encoder Approach to Prompt-Based Reranking in Educational Dialogue Systems
  17. FourierKAN outperforms MLP on Text Classification Head Fine-tuning
  18. PriorMapNet: Enhancing Online Vectorized HD Map Construction with Priors
  19. Representation Learning of Geometric Trees
  20. Backward-Compatible Aligned Representations via an Orthogonal Transformation Layer
  21. Assessing Generalization Capabilities of Malaria Diagnostic Models from Thin Blood Smears
  22. A Disease-Specific Foundation Model Using Over 100K Fundus Images: Release and Validation for Abnormality and Multi-Disease Classification on Downstream Tasks
  23. Neighbor Overlay-Induced Graph Attention Network
  24. A Transparency Paradox? Investigating the Impact of Explanation Specificity and Autonomous Vehicle Perceptual Inaccuracies on Passengers
  25. Multi-task Learning Approach for Intracranial Hemorrhage Prognosis
  26. EmoDynamiX: Emotional Support Dialogue Strategy Prediction by Modelling MiXed Emotions and Discourse Dynamics
  27. Evaluating the Evaluator: Measuring LLMs' Adherence to Task Evaluation Instructions
  28. Large Language Models Might Not Care What You Are Saying: Prompt Format Beats Descriptions
  29. DAC: Decomposed Automation Correction for Text-to-SQL
  30. NEAR: A Training-Free Pre-Estimator of Machine Learning Model Performance
  31. Speckle Noise Analysis for Synthetic Aperture Radar (SAR) Space Data
  32. Pessimistic Iterative Planning with RNNs for Robust POMDPs
  33. Lower Layers Matter: Alleviating Hallucination via Multi-Layer Fusion Contrastive Decoding with Truthfulness Refocused
  34. VF-NeRF: Learning Neural Vector Fields for Indoor Scene Reconstruction
  35. Self-Explainable Graph Transformer for Link Sign Prediction
  36. PCP-MAE: Learning to Predict Centers for Point Masked Autoencoders
  37. ML Study of MaliciousTransactions in Ethereum
  38. MicroSSIM: Improved Structural Similarity for Comparing Microscopy Data
  39. A lifted Bregman strategy for training unfolded proximal neural network Gaussian denoisers
  40. ASVspoof 5: Crowdsourced Speech Data, Deepfakes, and Adversarial Attacks at Scale
  41. Task-Aware Dynamic Transformer for Efficient Arbitrary-Scale Image Super-Resolution
  42. Symbolic Parameter Learning in Probabilistic Answer Set Programming
  43. ConcateNet: Dialogue Separation Using Local And Global Feature Concatenation
  44. ChatZero:Zero-shot Cross-Lingual Dialogue Generation via Pseudo-Target Language
  45. Correspondence-Guided SfM-Free 3D Gaussian Splatting for NVS
  46. Beyond KAN: Introducing KarSein for Adaptive High-Order Feature Interaction Modeling in CTR Prediction
  47. Decoupling Feature Representations of Ego and Other Modalities for Incomplete Multi-modal Brain Tumor Segmentation
  48. Beam Prediction based on Large Language Models
  49. TsCA: On the Semantic Consistency Alignment via Conditional Transport for Compositional Zero-Shot Learning
  50. HyCoT: A Transformer-Based Autoencoder for Hyperspectral Image Compression
  51. RBLA: Rank-Based-LoRA-Aggregation for Fine-tuning Heterogeneous Models in FLaaS
  52. NFDI4DSO: Towards a BFO Compliant Ontology for Data Science
  53. Turning Trash into Treasure: Accelerating Inference of Large Language Models with Token Recycling
  54. Quantifying the Effectiveness of Student Organization Activities using Natural Language Processing
  55. Explore-then-Commit Algorithms for Decentralized Two-Sided Matching Markets
  56. MVIGER: Multi-View Variational Integration of Complementary Knowledge for Generative Recommender
  57. Can Large Language Models Improve the Adversarial Robustness of Graph Neural Networks?
  58. Research on Personalized Compression Algorithm for Pre-trained Models Based on Homomorphic Entropy Increase
  59. LLM-PCGC: Large Language Model-based Point Cloud Geometry Compression
  60. A Mean Field Ansatz for Zero-Shot Weight Transfer
  61. Fine-tuning LLMs for Autonomous Spacecraft Control: A Case Study Using Kerbal Space Program
  62. Misclassification excess risk bounds for PAC-Bayesian classification via convexified loss
  63. MAT-SED: A Masked Audio Transformer with Masked-Reconstruction Based Pre-training for Sound Event Detection
  64. Towards Physical World Backdoor Attacks against Skeleton Action Recognition
  65. Adaptive Layer Selection for Efficient Vision Transformer Fine-Tuning
  66. Robust Stochastic Shortest-Path Planning via Risk-Sensitive Incremental Sampling
  67. A Multivocal Literature Review on Privacy and Fairness in Federated Learning
  68. QMambaBSR: Burst Image Super-Resolution with Query State Space Model
  69. A new perspective on Bayesian Operational Modal Analysis
  70. MIA-Tuner: Adapting Large Language Models as Pre-training Text Detector
  71. LLMs Are Biased Towards Output Formats! Systematically Evaluating and Mitigating Output Format Bias of LLMs
  72. FLAIN: Mitigating Backdoor Attacks in Federated Learning via Flipping Weight Updates of Low-Activation Input Neurons
  73. TextCAVs: Debugging vision models using text
  74. An End-to-End Model for Photo-Sharing Multi-modal Dialogue Generation
  75. Understanding Enthymemes in Argument Maps: Bridging Argument Mining and Logic-based Argumentation
  76. Modeling the Neonatal Brain Development Using Implicit Neural Representations
  77. PolyFootNet: Extracting Polygonal Building Footprints in Off-Nadir Remote Sensing Images
  78. The Power of Bias: Optimizing Client Selection in Federated Learning with Heterogeneous Differential Privacy
  79. Solving The Quantum Many-Body Hamiltonian Learning Problem with Neural Differential Equations
  80. Magazine Supply Optimization: a Case-study
  81. Historical Printed Ornaments: Dataset and Tasks
  82. Navigating Uncertainties in Machine Learning for Structural Dynamics: A Comprehensive Survey of Probabilistic and Non-Probabilistic Approaches in Forward and Inverse Problems
  83. A survey on secure decentralized optimization and learning
  84. RealMedQA: A pilot biomedical question answering dataset containing realistic clinical questions
  85. SketchRef: a Multi-Task Evaluation Benchmark for Sketch Synthesis
  86. DeepDFA: Automata Learning through Neural Probabilistic Relaxations
  87. PatUntrack: Automated Generating Patch Examples for Issue Reports without Tracked Insecure Code
  88. Bi-Directional Deep Contextual Video Compression
  89. Learning A Low-Level Vision Generalist via Visual Task Prompt
  90. MM-UNet: A Mixed MLP Architecture for Improved Ophthalmic Image Segmentation
  91. Zero-Shot Dual-Path Integration Framework for Open-Vocabulary 3D Instance Segmentation
  92. OptDist: Learning Optimal Distribution for Customer Lifetime Value Prediction
  93. S-RAF: A Simulation-Based Robustness Assessment Framework for Responsible Autonomous Driving
  94. GrassNet: State Space Model Meets Graph Neural Network
  95. TAMER: Tree-Aware Transformer for Handwritten Mathematical Expression Recognition
  96. Tuning a SAM-Based Model with Multi-Cognitive Visual Adapter to Remote Sensing Instance Segmentation
  97. AgentSimulator: An Agent-based Approach for Data-driven Business Process Simulation
  98. EraW-Net: Enhance-Refine-Align W-Net for Scene-Associated Driver Attention Estimation
  99. DV-Matcher: Deformation-based Non-Rigid Point Cloud Matching Guided by Pre-trained Visual Features
  100. S3Attention: Improving Long Sequence Attention with Smoothed Skeleton Sketching
  101. Overview of the BioLaySumm 2024 Shared Task on the Lay Summarization of Biomedical Research Articles
  102. Collaborative Cross-modal Fusion with Large Language Model for Recommendation
  103. A training regime to learn unified representations from complementary breast imaging modalities
  104. Linear combinations of latents in generative models: subspaces and beyond
  105. Detection and Tracking of MAVs Using a Rosette Scanning Pattern LiDAR
  106. Integrating Multi-view Analysis: Multi-view Mixture-of-Expert for Textual Personality Detection
  107. String Diagram of Optimal Transports
  108. SelectLLM: Query-Aware Efficient Selection Algorithm for Large Language Models
  109. Scaling up Multimodal Pre-training for Sign Language Understanding
  110. Language-Driven Interactive Shadow Detection
  111. Where is the signal in tokenization space?
  112. Blockchain-Enabled Accountability in Data Supply Chain: A Data Bill of Materials Approach
  113. Adv-SSL: Adversarial Self-Supervised Representation Learning with Theoretical Guarantees
  114. Detecting Unsuccessful Students in Cybersecurity Exercises in Two Different Learning Environments
  115. Privacy-Preserving Vision Transformer Using Images Encrypted with Restricted Random Permutation Matrices
  116. Focus on Focus: Focus-oriented Representation Learning and Multi-view Cross-modal Alignment for Glioma Grading
  117. GS-ID: Illumination Decomposition on Gaussian Splatting via Adaptive Light Aggregation and Diffusion-Guided Material Priors
  118. Mitigating Degree Bias in Signed Graph Neural Networks
  119. Ex3: Automatic Novel Writing by Extracting, Excelsior and Expanding
  120. CoSEC: A Coaxial Stereo Event Camera Dataset for Autonomous Driving
  121. The Limitations of Model Retraining in the Face of Performativity
  122. Optimal Sketching for Residual Error Estimation for Matrix and Vector Norms
  123. DFT-Based Adversarial Attack Detection in MRI Brain Imaging: Enhancing Diagnostic Accuracy in Alzheimer's Case Studies
  124. PITN: Physics-Informed Temporal Networks for Cuffless Blood Pressure Estimation
  125. An Unsupervised Learning Framework Combined with Heuristics for the Maximum Minimal Cut Problem
  126. Enhancement of price trend trading strategies via image-induced importance weights
  127. Enhancing Events in Neutrino Telescopes through Deep Learning-Driven Super-Resolution
  128. Fairness Issues and Mitigations in (Differentially Private) Socio-Demographic Data Processes
  129. A theory of understanding for artificial intelligence: composability, catalysts, and learning
  130. Style-Editor: Text-driven object-centric style editing