mlsanityData to 14 Oct 2026

Papers

New on arXiv

Wed 19 Jul 2023

205 papers

  1. Abusing Images and Sounds for Indirect Instruction Injection in Multi-Modal LLMsMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness
  2. What can we learn from Data Leakage and Unlearning for Law?LLM safety and security → Machine unlearning
  3. PreDiff: Precipitation Nowcasting with Latent Diffusion ModelsDiffusion models → Flow matching, time series and science
  4. Explaining Autonomous Driving Actions with Visual Question AnsweringEnd-to-end autonomous driving → VLMs for autonomous driving
  5. Improving Multimodal Datasets with Image CaptioningMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  6. Polyffusion: A Diffusion Model for Polyphonic Score Generation with Internal and External ControlsDiffusion models → Audio, speech and music
  7. Rethinking Backdoor AttacksLLM safety and security → Backdoor and data poisoning attacks
  8. Robust Driving Policy Learning with Guided Meta Reinforcement LearningEnd-to-end autonomous driving → Cooperative and V2X driving
  9. FABRIC: Personalizing Diffusion Models with Iterative FeedbackDiffusion models → Image generation, text-to-image and editing +1
  10. Make-A-Volume: Leveraging Latent Diffusion Models for Cross-Modality 3D Brain MRI SynthesisDiffusion models → Medical imaging and segmentation
  11. Controlling Equational Reasoning in Large Language Models with Prompt InterventionsLLM reasoning → Mathematical reasoning
  12. XSkill: Cross Embodiment Skill DiscoveryOffline RL and imitation learning from data → Robot manipulation imitation learning
  13. BSDM: Background Suppression Diffusion Model for Hyperspectral Anomaly DetectionDiffusion models → Inverse problems and image restoration
  14. Near-Linear Time Projection onto the ℓ1,∞ Ball; Application to Sparse AutoencodersMechanistic interpretability → Sparse autoencoder training and evaluation
  15. DiffDP: Radiotherapy Dose Prediction via a Diffusion ModelDiffusion models → Medical imaging and segmentation
  16. Text2Layer: Layered Image Generation using Latent Diffusion ModelDiffusion models → Image generation, text-to-image and editing
  17. Mechanical Artifacts in Optical Projection Tomography: Classification and Automatic Calibration
  18. Self-Supervised Learning for WiFi CSI-Based Human Activity Recognition: A Systematic Study
  19. The importance of feature preprocessing for differentially private linear optimization
  20. Technical Challenges of Deploying Reinforcement Learning Agents for Game Testing in AAA Games
  21. Eye Disease Classification Using Deep Learning Techniques
  22. Mining Conditional Part Semantics with Occluded Extrapolation for Human-Object Interaction Detection
  23. A Competitive Learning Approach for Specialized Models: A Solution for Complex Physical Systems with Distinct Functional Regimes
  24. Novel Batch Active Learning Approach and Its Application to Synthetic Aperture Radar Datasets
  25. Blockchain-Based Federated Learning: Incentivizing Data Sharing and Penalizing Dishonest Behavior
  26. Markov Decision Processes with Time-Varying Geometric Discounting
  27. SPRINT: A Unified Toolkit for Evaluating and Demystifying Zero-shot Neural Sparse Retrieval
  28. Attacking by Aligning: Clean-Label Backdoor Attacks on Object Detection
  29. FinGPT: Democratizing Internet-scale Data for Financial Large Language Models
  30. Findings of Factify 2: Multimodal Fake News Detection
  31. Can Instruction Fine-Tuned Language Models Identify Social Bias through Prompting?
  32. Classification of Visualization Types and Perspectives in Patents
  33. A data science axiology: the nature, value, and risks of data science
  34. A New Computationally Simple Approach for Implementing Neural Networks with Output Hard Constraints
  35. Complying with the EU AI Act
  36. Improving the Reusability of Pre-trained Language Models in Real-world Applications
  37. Determination of the critical points for systems of directed percolation class using machine learning
  38. A Step Towards Worldwide Biodiversity Assessment: The BIOSCAN-1M Insect Dataset
  39. Integrating a Heterogeneous Graph with Entity-aware Self-attention using Relative Position Labels for Reading Comprehension Model
  40. Thrust: Adaptively Propels Large Language Models with External Knowledge
  41. Confidence Estimation Using Unlabeled Data
  42. Uncertainty Quantification for Molecular Property Predictions with Graph Neural Architecture Search
  43. A Bayesian Programming Approach to Car-following Model Calibration and Validation using Limited Data
  44. A Matrix Ensemble Kalman Filter-based Multi-arm Neural Network to Adequately Approximate Deep Neural Networks
  45. Learning Formal Specifications from Membership and Preference Queries
  46. PharmacyGPT: The AI Pharmacist
  47. DP-TBART: A Transformer-based Autoregressive Model for Differentially Private Tabular Data Generation
  48. GOOSE Algorithm: A Powerful Optimization Tool for Real-World Engineering Challenges and Beyond
  49. Interpreting and Correcting Medical Image Classification with PIP-Net
  50. POV-Surgery: A Dataset for Egocentric Hand and Tool Pose Estimation During Surgical Activities
  51. TokenFlow: Consistent Diffusion Features for Consistent Video Editing
  52. Selection functions of strong lens finding neural networks
  53. Properties of Discrete Sliced Wasserstein Losses
  54. Code Detection for Hardware Acceleration Using Large Language Models
  55. ProtiGeno: a prokaryotic short gene finder using protein language models
  56. Mitigating Viewer Impact from Disturbing Imagery using AI Filters: A User-Study
  57. IncDSI: Incrementally Updatable Document Retrieval
  58. Reproducibility in Machine Learning-Driven Research
  59. Eliminating Label Leakage in Tree-Based Vertical Federated Learning
  60. FedBug: A Bottom-Up Gradual Unfreezing Framework for Federated Learning
  61. CPCM: Contextual Point Cloud Modeling for Weakly-supervised Point Cloud Semantic Segmentation
  62. Absolutist AI
  63. Mood Classification of Bangla Songs Based on Lyrics
  64. DNA-Rendering: A Diverse Neural Actor Repository for High-Fidelity Human-centric Rendering
  65. DialogStudio: Towards Richest and Most Diverse Unified Dataset Collection for Conversational AI
  66. LightPath: Lightweight and Scalable Path Representation Learning
  67. Challenges and Applications of Large Language Models
  68. LLMs as Workers in Human-Computational Algorithms? Replicating Crowdsourcing Pipelines with LLMs
  69. VITS : Variational Inference Thompson Sampling for contextual bandits
  70. Adversarial Latent Autoencoder with Self-Attention for Structural Image Synthesis
  71. Drone navigation and license place detection for vehicle location in indoor spaces
  72. A Unified Framework for Pattern Recovery in Penalized and Thresholded Estimation and its Geometry
  73. Leveraging Visemes for Better Visual Speech Representation and Lip Reading
  74. Exploring Transformer Extrapolation
  75. Curvature-based Clustering on Graphs
  76. Benchmarking Potential Based Rewards for Learning Humanoid Locomotion
  77. A Hierarchical Architecture for Neural Materials
  78. General vs. Long-Tailed Age Estimation: An Approach to Kill Two Birds with One Stone
  79. Two Approaches to Supervised Image Segmentation
  80. Memory Efficient And Minimax Distribution Estimation Under Wasserstein Distance Using Bayesian Histograms
  81. Gradient Sparsification For Masked Fine-Tuning of Transformers
  82. Boundary-Refined Prototype Generation: A General End-to-End Paradigm for Semi-Supervised Semantic Segmentation
  83. Revisiting invariances and introducing priors in Gromov-Wasserstein distances
  84. Android in the Wild: A Large-Scale Dataset for Android Device Control
  85. A Decision Making Framework for Recommended Maintenance of Road Segments
  86. A Dual Formulation for Probabilistic Principal Component Analysis
  87. Entropy regularization in probabilistic clustering
  88. Unsupervised Accuracy Estimation of Deep Visual Models using Domain-Adaptive Adversarial Perturbation without Source Samples
  89. Accurate deep learning sub-grid scale models for large eddy simulations
  90. Stochastic Subgradient Methods with Guaranteed Global Stability in Nonsmooth Nonconvex Optimization
  91. Divert More Attention to Vision-Language Object Tracking
  92. Class Attention to Regions of Lesion for Imbalanced Medical Image Recognition
  93. Automatic Conversion of MiniZinc Programs to QUBO
  94. Contextual Reliability: When Different Features Matter in Different Contexts
  95. An Empirical Study on Fertility Proposals Using Multi-Grained Topic Analysis Methods
  96. Europepolls: A Dataset of Country-Level Opinion Polling Data for the European Union and the UK
  97. RoboCIn Small Size League Extended Team Description Paper for RoboCup 2023
  98. When Dialects Collide: How Socioeconomic Mixing Affects Language Use
  99. Towards Fair Face Verification: An In-depth Analysis of Demographic Biases
  100. MODA: Mapping-Once Audio-driven Portrait Animation with Dual Attentions
All 205
  1. 6G Network Business Support System
  2. TbExplain: A Text-based Explanation Method for Scene Classification Models with the Statistical Prediction Correction
  3. As large as it gets: Learning infinitely large Filters via Neural Implicit Functions in the Fourier Domain
  4. TUNeS: A Temporal U-Net with Self-Attention for Video-based Surgical Phase Recognition
  5. Impact of Disentanglement on Pruning Neural Networks
  6. UniMatch: A Unified User-Item Matching Framework for the Multi-purpose Merchant Marketing
  7. TinyTrain: Resource-Aware Task-Adaptive Sparse Training of DNNs at the Data-Scarce Edge
  8. Our Model Achieves Excellent Performance on MovieLens: What Does it Mean?
  9. Lazy Visual Localization via Motion Averaging
  10. Learner Referral for Cost-Effective Federated Learning Over Hierarchical IoT Networks
  11. Towards green AI-based software systems: an architecture-centric approach (GAISSA)
  12. GUIDO: A Hybrid Approach to Guideline Discovery & Ordering from Natural Language Texts
  13. U-CE: Uncertainty-aware Cross-Entropy for Semantic Segmentation
  14. ProtoCaps: A Fast and Non-Iterative Capsule Network Routing Method
  15. Impatient Bandits: Optimizing Recommendations for the Long-Term Without Delay
  16. TREEMENT: Interpretable Patient-Trial Matching via Personalized Dynamic Tree-Based Memory Network
  17. AGAR: Attention Graph-RNN for Adaptative Motion Prediction of Point Clouds of Deformable Objects
  18. Spuriosity Didn't Kill the Classifier: Using Invariant Predictions to Harness Spurious Features
  19. DISA: DIfferentiable Similarity Approximation for Universal Multimodal Registration
  20. Measuring and Modeling Uncertainty Degree for Monocular Depth Estimation
  21. Large Language Models can accomplish Business Process Management Tasks
  22. TimeTuner: Diagnosing Time Representations for Time-Series Forecasting with Counterfactual Explanations
  23. Embedded Heterogeneous Attention Transformer for Cross-lingual Image Captioning
  24. Exploring Non-Regular Extensions of Propositional Dynamic Logic with Description-Logics Features
  25. Learning invariant representations of time-homogeneous stochastic dynamical systems
  26. Chit-Chat or Deep Talk: Prompt Engineering for Process Mining
  27. Implicit Identity Representation Conditioned Memory Compensation Network for Talking Head video Generation
  28. PyTAG: Challenges and Opportunities for Reinforcement Learning in Tabletop Games
  29. An analysis on the effects of speaker embedding choice in non auto-regressive TTS
  30. Repeated Observations for Classification
  31. Learning from Abstract Images: on the Importance of Occlusion in a Minimalist Encoding of Human Poses
  32. 3Deformer: A Common Framework for Image-Guided Mesh Deformation
  33. Amortised Design Optimization for Item Response Theory
  34. A reinforcement learning approach for VQA validation: an application to diabetic macular edema grading
  35. Test-takers have a say: understanding the implications of the use of AI in language tests
  36. Symmetric Equilibrium Learning of VAEs
  37. Adversarial Likelihood Estimation With One-Way Flows
  38. A3D: Adaptive, Accurate, and Autonomous Navigation for Edge-Assisted Drones
  39. Amortised Experimental Design and Parameter Estimation for User Models of Pointing
  40. Detecting Vulnerable Nodes in Urban Infrastructure Interdependent Network
  41. Towards a population-informed approach to the definition of data-driven models for structural dynamics
  42. Towards Reliable Rare Category Analysis on Graphs via Individual Calibration
  43. Blind Image Quality Assessment Using Multi-Stream Architecture with Spatial and Channel Attention
  44. Hierarchical Spatio-Temporal Representation Learning for Gait Recognition
  45. Cryo-forum: A framework for orientation recovery with uncertainty measure with the application in cryo-EM image analysis
  46. Reinforcement Learning for Credit Index Option Hedging
  47. Compressive Image Scanning Microscope
  48. Deep Operator Network Approximation Rates for Lipschitz Operators
  49. A Fast and Map-Free Model for Trajectory Prediction in Traffics
  50. What do neural networks learn in image classification? A frequency shortcut perspective
  51. Online Continual Learning for Robust Indoor Object Recognition
  52. Multi-modal Learning based Prediction for Disease
  53. A Siamese-based Verification System for Open-set Architecture Attribution of Synthetic Images
  54. Hierarchical Semantic Perceptual Listener Head Video Generation: A High-performance Pipeline
  55. Deep unrolling Shrinkage Network for Dynamic MR imaging
  56. Manifold Learning with Sparse Regularised Optimal Transport
  57. LDP: Language-driven Dual-Pixel Image Defocus Deblurring Network
  58. DAPrompt: Deterministic Assumption Prompt Learning for Event Causality Identification
  59. GenKL: An Iterative Framework for Resolving Label Ambiguity and Label Non-conformity in Web Images Via a New Generalized KL Divergence
  60. Fix your downsampling ASAP! Be natively more robust via Aliasing and Spectral Artifact free Pooling
  61. Graph Federated Learning Based on the Decentralized Framework
  62. clubsuit CLOVER clubsuit: Probabilistic Forecasting with Coherent Learning Objective Reparameterization
  63. Forecasting Early with Meta Learning
  64. From West to East: Who can understand the music of the others better?
  65. On the Origin of LLMs: An Evolutionary Tree and Graph for 15,821 Large Language Models
  66. A Note on Hardness of Computing Recursive Teaching Dimension
  67. Density-invariant Features for Distant Point Cloud Registration
  68. DVPT: Dynamic Visual Prompt Tuning of Large Pre-trained Models for Medical Image Analysis
  69. ZeroQuant-FP: A Leap Forward in LLMs Post-Training W4A8 Quantization Using Floating-Point Formats
  70. Beyond Single-Feature Importance with ICECREAM
  71. Generating Redstone Style Cities in Minecraft
  72. A Novel Spatial-Temporal Variational Quantum Circuit to Enable Deep Learning on NISQ Devices
  73. Perturbing a Neural Network to Infer Effective Connectivity: Evidence from Synthetic EEG Data
  74. Source-Free Domain Adaptation for Medical Image Segmentation via Prototype-Anchored Feature Alignment and Contrastive Learning
  75. How Curvature Enhance the Adaptation Power of Framelet GCNs
  76. Sig-Splines: universal approximation and convex calibration of time series generative models
  77. Towards Building More Robust Models with Frequency Bias
  78. Improving Surrogate Model Robustness to Perturbations for Dynamical Systems Through Machine Learning and Data Assimilation
  79. Constructing Extreme Learning Machines with zero Spectral Bias
  80. Longitudinal Data and a Semantic Similarity Reward for Chest X-Ray Report Generation
  81. Generative Prompt Model for Weakly Supervised Object Localization
  82. Space Engage: Collaborative Space Supervision for Contrastive-based Semi-Supervised Semantic Segmentation
  83. Information Retrieval Meets Large Language Models: A Strategic Report from Chinese IR Community
  84. Towards Robust Scene Text Image Super-resolution via Explicit Location Enhancement
  85. Watch out Venomous Snake Species: A Solution to SnakeCLEF2023
  86. Enhancing conversational quality in language learning chatbots: An evaluation of GPT4 for ASR error correction
  87. Improved Distribution Matching for Dataset Condensation
  88. ClickSeg: 3D Instance Segmentation with Click-Level Weak Annotations
  89. NTIRE 2023 Quality Assessment of Video Enhancement Challenge
  90. Uncertainty-Driven Multi-Scale Feature Fusion Network for Real-time Image Deraining
  91. SAMConvex: Fast Discrete Optimization for CT Registration using Self-supervised Anatomical Embedding and Correlation Pyramid
  92. AesPA-Net: Aesthetic Pattern-Aware Style Transfer Networks
  93. Multi-Grained Multimodal Interaction Network for Entity Linking
  94. Semantic-Aware Dual Contrastive Learning for Multi-label Image Classification
  95. Two Tales of Platoon Intelligence for Autonomous Mobility Control: Enabling Deep Learning Recipes
  96. RaTE: a Reproducible automatic Taxonomy Evaluation by Filling the Gap
  97. CValues: Measuring the Values of Chinese Large Language Models from Safety to Responsibility
  98. Efficient Guided Generation for Large Language Models
  99. Efficiency Pentathlon: A Standardized Arena for Efficiency Evaluation
  100. The Connection Between R-Learning and Inverse-Variance Weighting for Estimation of Heterogeneous Treatment Effects
  101. Towards Saner Deep Image Registration
  102. GlobalMapper: Arbitrary-Shaped Urban Layout Generation
  103. STRAPPER: Preference-based Reinforcement Learning via Self-training Augmentation and Peer Regularization
  104. Joint Service Caching, Communication and Computing Resource Allocation in Collaborative MEC Systems: A DRL-based Two-timescale Approach
  105. Amazon-M2: A Multilingual Multi-locale Shopping Session Dataset for Recommendation and Text Generation