mlsanityData to 14 Oct 2026

Papers

New on arXiv

Fri 29 Mar 2024

232 papers

  1. Constructing Multilingual Visual-Text Datasets Revealing Visual Multilingual Ability of Vision Language ModelsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  2. Facilitating Human Feedback for GenAI Prompt OptimizationLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
  3. Uncovering Bias in Large Vision-Language Models with CounterfactualsMultimodal LLMs / vision-language models → Social bias and fairness in VLMs
  4. FetalDiffusion: Pose-Controllable 3D Fetal MRI Synthesis with Conditional Diffusion ModelDiffusion models → Medical imaging and segmentation
  5. Unsolvable Problem Detection: Robust Understanding Evaluation for Large Multimodal ModelsMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  6. Are We on the Right Way for Evaluating Large Vision-Language Models?Multimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  7. Learn "No" to Say "Yes" Better: Improving Vision-Language Models via NegationsMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  8. Draw-and-Understand: Leveraging Visual Prompts to Enable MLLMs to Comprehend What You WantMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  9. Relation Rectification in Diffusion ModelDiffusion models → Image generation, text-to-image and editing
  10. VHM: Versatile and Honest Vision Language Model for Remote Sensing Image AnalysisMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  11. ConvBench: A Multi-Turn Conversation Evaluation Benchmark with Hierarchical Capability for Large Vision-Language ModelsMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  12. HARMamba: Efficient and Lightweight Wearable Sensor Human Activity Recognition Based on Bidirectional MambaState-space sequence models (S4, Mamba) → Video, motion and generative Mamba models
  13. Unsupervised Tumor-Aware Distillation for Multi-Modal Brain Image TranslationKnowledge distillation → Distillation for medical imaging
  14. Biologically-Plausible Topology Improved Spiking Actor Network for Efficient Deep Reinforcement LearningDeep reinforcement learning methods → Spiking and neuromorphic RL
  15. CAESAR: Enhancing Federated RL in Heterogeneous MDPs through Convergence-Aware Sampling with ScreeningDeep reinforcement learning methods → RL for energy, networks and operations
  16. Accurate Block Quantization in LLMs with OutliersEfficient LLM inference and serving → KV cache quantization
  17. LeGo-Drive: Language-enhanced Goal-oriented Closed-Loop End-to-End Autonomous DrivingMultimodal LLMs / vision-language models → Driving VLMs and open-vocabulary detection +1
  18. Mol-AIR: Molecular Reinforcement Learning with Adaptive Intrinsic Rewards for Goal-directed Molecular GenerationDeep reinforcement learning methods → RL for energy, networks and operations
  19. Learning Enriched Features via Selective State Spaces Model for Efficient Image DeblurringState-space sequence models (S4, Mamba) → Mamba for image restoration
  20. FreeSeg-Diff: Training-Free Open-Vocabulary Segmentation with Diffusion ModelsDiffusion models → Medical imaging and segmentation
  21. ITCMA: A Generative Agent Based on a Computational Consciousness StructureLLM agents and tool use → Multimodal and embodied agents
  22. SGD: Street View Synthesis with Gaussian Splatting and Diffusion PriorWorld models → World models for autonomous driving +1
  23. Negative Label Guided OOD Detection with Pretrained Vision-Language ModelsMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  24. Revolutionizing Disease Diagnosis with simultaneous functional PET/MR and Deeply Integrated Brain Metabolic, Hemodynamic, and Perfusion NetworksMixture-of-experts → Medical and biomedical MoE
  25. Can LLMs Learn from Previous Mistakes? Investigating LLMs' Errors to Boost for ReasoningLLM reasoning → Reasoning benchmarks and evaluation
  26. UltraLight VM-UNet: Parallel Vision Mamba Significantly Reduces Parameters for Skin Lesion SegmentationState-space sequence models (S4, Mamba) → Mamba for medical image analysis
  27. FSMR: A Feature Swapping Multi-modal Reasoning Approach with Joint Textual and Visual CluesLLM reasoning → Multimodal reasoning
  28. Psychometry: An Omnifit Model for Image Reconstruction from Human Brain ActivityMixture-of-experts → Medical and biomedical MoE
  29. Nonparametric Bellman Mappings for Reinforcement Learning: Application to Robust Adaptive FilteringDeep reinforcement learning methods → RL theory and sample complexity
  30. EnCoMP: Enhanced Covert Maneuver Planning with Adaptive Threat-Aware Visibility Estimation using Offline Reinforcement LearningOffline RL and imitation learning from data → Diffusion and flow policies for offline RL
  31. Adaptive Energy Regularization for Autonomous Gait Transition and Energy-Efficient Quadruped LocomotionDeep reinforcement learning methods → RL for robot locomotion and manipulation
  32. Enhancing the General Agent Capabilities of Low-Parameter LLMs through Tuning and Multi-Branch ReasoningLLM reasoning → Reasoning for agents, planning and code +1
  33. Diverse Feature Learning by Self-distillation and ResetKnowledge distillation → General knowledge distillation methods
  34. Decision Mamba: Reinforcement Learning via Sequence Modeling with Selective State SpacesState-space sequence models (S4, Mamba) → Video, motion and generative Mamba models +2
  35. CtRL-Sim: Reactive and Controllable Driving Agents with Offline Reinforcement LearningEnd-to-end autonomous driving → Imitation-learning end-to-end planners +1
  36. Fusion Dynamical Systems with Machine Learning in Imitation Learning: A Comprehensive OverviewOffline RL and imitation learning from data → Imitation learning methods +1
  37. Structure Matters: Tackling the Semantic Discrepancy in Diffusion Models for Image InpaintingDiffusion models → 3D, point cloud and scene generation
  38. Towards a Robust Retrieval-Based Summarization SystemRetrieval-augmented generation → RAG pipeline design and evaluation
  39. MambaMixer: Efficient Selective State Space Models with Dual Token and Channel SelectionState-space sequence models (S4, Mamba) → Core SSM architectures for language
  40. A Survey of Machine Learning Techniques for Improving Global Navigation Satellite Systems
  41. Generative AI Adoption in Classroom in Context of Technology Acceptance Model (TAM) and the Innovation Diffusion Theory (IDT)
  42. LooPIN: A PinFi protocol for decentralized computing
  43. Label-Efficient Sleep Staging Using Transformers Pre-trained with Position Prediction
  44. DCAE-SR: Design of a Denoising Convolutional Autoencoder for reconstructing Electrocardiograms signals at Super Resolution
  45. SelfReplay: Adapting Self-Supervised Sensory Models via Adaptive Meta-Task Replay
  46. Real-time Lane-wise Traffic Monitoring in Optimal ROIs
  47. LACS: Learning-Augmented Algorithms for Carbon-Aware Resource Scaling with Uncertain Demand
  48. Identifying Banking Transaction Descriptions via Support Vector Machine Short-Text Classification Based on a Specialized Labelled Corpus
  49. Detection of financial opportunities in micro-blogging data with a stacked classification system
  50. Optimal navigation of magnetic artificial microswimmers in blood capillaries with deep reinforcement learning
  51. Explaining Large Language Models Decisions Using Shapley Values
  52. LLaVA-Gemma: Accelerating Multimodal Foundation Models with a Compact Language Model
  53. P-Hologen: An End-to-End Generative Framework for Phase-Only Holograms
  54. Entertainment chatbot for the digital inclusion of elderly people without abstraction capabilities
  55. Multiple-policy Evaluation via Density Estimation
  56. Optimal Blackjack Strategy Recommender: A Comprehensive Study on Computer Vision Integration for Enhanced Gameplay
  57. GPTA: Generative Prompt Tuning Assistant for Synergistic Downstream Neural Network Enhancement with LLMs
  58. DataAgent: Evaluating Large Language Models' Ability to Answer Zero-Shot, Natural Language Queries
  59. On Inherent Adversarial Robustness of Active Vision Systems
  60. Word Ladders: A Mobile Application for Semantic Data Collection
  61. Multi-Region Transfer Learning for Segmentation of Crop Field Boundaries in Satellite Images with Limited Labels
  62. Beyond Suspension: A Two-phase Methodology for Concluding Sports Leagues
  63. The LSCD Benchmark: a Testbed for Diachronic Word Meaning Tasks
  64. General Machine Learning Models for Interpreting and Predicting Efficiency Degradation in Organic Solar Cells
  65. Universal Bovine Identification via Depth Data and Deep Metric Learning
  66. Multi-Level Neural Scene Graphs for Dynamic Urban Environments
  67. Individual Text Corpora Predict Openness, Interests, Knowledge and Level of Education
  68. CT respiratory motion synthesis using joint supervised and adversarial learning
  69. Modeling Large-Scale Walking and Cycling Networks: A Machine Learning Approach Using Mobile Phone and Crowdsourced Data
  70. Fully Zeroth-Order Bilevel Programming via Gaussian Smoothing
  71. On-the-fly Definition Augmentation of LLMs for Biomedical NER
  72. VSRD: Instance-Aware Volumetric Silhouette Rendering for Weakly Supervised 3D Object Detection
  73. Fast Orthogonal Matching Pursuit through Successive Regression
  74. Verifying the Selected Completely at Random Assumption in Positive-Unlabeled Learning
  75. An Interpretable Cross-Attentive Multi-modal MRI Fusion Framework for Schizophrenia Diagnosis
  76. Accelerating Search-Based Planning for Multi-Robot Manipulation by Leveraging Online-Generated Experiences
  77. Classifying Conspiratorial Narratives At Scale: False Alarms and Erroneous Connections
  78. Does Faithfulness Conflict with Plausibility? An Empirical Study in Explainable AI across NLP Tasks
  79. Security Risks Concerns of Generative AI in the IoT
  80. Budget-aware Query Tuning: An AutoML Perspective
  81. FISBe: A real-world benchmark dataset for instance segmentation of long-range thin filamentous structures
  82. Where Are You From? Let Me Guess! Subdialect Recognition of Speeches in Sorani Kurdish
  83. AgileFormer: Spatially Agile Transformer UNet for Medical Image Segmentation
  84. Deepfake Sentry: Harnessing Ensemble Intelligence for Resilient Detection and Generalisation
  85. Robust Ensemble Person Re-Identification via Orthogonal Fusion with Occlusion Handling
  86. PikeLPN: Mitigating Overlooked Inefficiencies of Low-Precision Neural Networks
  87. Efficient and Sharp Off-Policy Evaluation in Robust Markov Decision Processes
  88. Sparse Views, Near Light: A Practical Paradigm for Uncalibrated Point-light Photometric Stereo
  89. GDA: Generalized Diffusion for Robust Test-time Adaptation
  90. DVIS-DAQ: Improving Video Segmentation via Dynamic Anchor Queries
  91. Bayesian Nonparametrics: An Alternative to Deep Learning
  92. Data-Driven Room Acoustic Modeling Via Differentiable Feedback Delay Networks With Learnable Delay Lines
  93. Molecular Generative Adversarial Network with Multi-Property Optimization
  94. A Backdoor Approach with Inverted Labels Using Dirty Label-Flipping Attacks
  95. ReALM: Reference Resolution As Language Modeling
  96. Learning Visual Quadrupedal Loco-Manipulation from Demonstrations
  97. Gecko: Versatile Text Embeddings Distilled from Large Language Models
  98. Localising the Seizure Onset Zone from Single-Pulse Electrical Stimulation Responses with a CNN Transformer
  99. Towards a Framework for Evaluating Explanations in Automated Fact Verification
  100. MTLoRA: A Low-Rank Adaptation Approach for Efficient Multi-Task Learning
All 232
  1. SeaBird: Segmentation in Bird's View with Dice Loss Improves Monocular 3D Detection of Large Objects
  2. Convolutional Prompting meets Language Models for Continual Learning
  3. InstantSplat: Sparse-view Gaussian Splatting in Seconds
  4. ChainNet: Structured Metaphor and Metonymy in WordNet
  5. Towards Greener LLMs: Bringing Energy-Efficiency to the Forefront of LLM Inference
  6. Improving Learnt Local MAPF Policies with Heuristic Search
  7. Review-Based Hyperbolic Cross-Domain Recommendation
  8. Emotion-Anchored Contrastive Learning Framework for Emotion Recognition in Conversation
  9. Can LLMs Correct Physicians, Yet? Investigating Effective Interaction Methods in the Medical Domain
  10. Benchmarking Counterfactual Image Generation
  11. LayerNorm: A key component in parameter-efficient fine-tuning
  12. Sparsely Multimodal Data Fusion
  13. LUQ: Long-text Uncertainty Quantification for LLMs
  14. Snap-it, Tap-it, Splat-it: Tactile-Informed 3D Gaussian Splatting for Reconstructing Challenging Surfaces
  15. CATSNet: a context-aware network for Height Estimation in a Forested Area based on Pol-TomoSAR data
  16. Latxa: An Open Language Model and Evaluation Suite for Basque
  17. ELITR-Bench: A Meeting Assistant Benchmark for Long-Context Language Models
  18. FABind+: Enhancing Molecular Docking through Improved Pocket Prediction and Pose Generation
  19. Prototype-based Interpretable Breast Cancer Prediction Models: Analysis and Challenges
  20. Benchmarking the Robustness of Temporal Action Detection Models Against Temporal Corruptions
  21. MedCLIP-SAM: Bridging Text and Image Towards Universal Medical Image Segmentation
  22. Using LLMs to Model the Beliefs and Preferences of Targeted Populations
  23. Latent Embedding Clustering for Occlusion Robust Head Pose Estimation
  24. Optimal Policy Learning with Observational Data in Multi-Action Scenarios: Estimation, Risk Preference, and Potential Failures
  25. Enhancing Dimension-Reduced Scatter Plots with Class and Feature Centroids
  26. Long-Tailed Anomaly Detection with Learnable Class Names
  27. Artificial Neural Networks-based Real-time Classification of ENG Signals for Implanted Nerve Interfaces
  28. Functional Bilevel Optimization for Machine Learning
  29. U-VAP: User-specified Visual Appearance Personalization via Decoupled Self Augmentation
  30. An FPGA-Based Reconfigurable Accelerator for Convolution-Transformer Hybrid EfficientViT
  31. MTMMC: A Large-Scale Real-World Multi-Modal Camera Tracking Benchmark
  32. Shallow Cross-Encoders for Low-Latency Retrieval
  33. Graph Neural Aggregation-diffusion with Metastability
  34. Distributed agency in second language learning and teaching through generative AI
  35. Advancing the Arabic WordNet: Elevating Content Quality
  36. On Size and Hardness Generalization in Unsupervised Learning for the Travelling Salesman Problem
  37. Unlock the Potential of Large Language Models for Predictive Tabular Tasks in Data Science with Table-Specific Pretraining
  38. The Future of Combating Rumors? Retrieval, Discrimination, and Generation
  39. Voice Signal Processing for Machine Learning. The Case of Speaker Isolation
  40. High-dimensional analysis of ridge regression for non-identically distributed data with a variance profile
  41. NeuraLunaDTNet: Feedforward Neural Network-Based Routing Protocol for Delay-Tolerant Lunar Communication Networks
  42. Dual Simplex Volume Maximization for Simplex-Structured Matrix Factorization
  43. Automatic Alignment of Discourse Relations of Different Discourse Annotation Frameworks
  44. Enhancing Lithological Mapping with Spatially Constrained Bayesian Network (SCB-Net): An Approach for Field Data-Constrained Predictions with Uncertainty Evaluation
  45. Motion Inversion for Video Customization
  46. Homomorphic WiSARDs: Efficient Weightless Neural Network training over encrypted data
  47. Distributed Swarm Learning for Edge Internet of Things
  48. Sketch-to-Architecture: Generative AI-aided Architectural Design
  49. Exploring Pathological Speech Quality Assessment with ASR-Powered Wav2Vec2 in Data-Scarce Context
  50. Measuring Taiwanese Mandarin Language Understanding
  51. Preliminaries to artificial consciousness: a multidimensional heuristic approach
  52. MCNet: A crowd denstity estimation network based on integrating multiscale attention module
  53. HGS-Mapping: Online Dense Mapping Using Hybrid Gaussian Representation in Urban Scenes
  54. ChatGPT v.s. Media Bias: A Comparative Study of GPT-3.5 and Fine-tuned Language Models
  55. A Systematic Analysis of Subwords and Cross-Lingual Transfer in Multilingual Translation
  56. Talk3D: High-Fidelity Talking Portrait Synthesis via Personalized 3D Generative Prior
  57. A Learning-based Incentive Mechanism for Mobile AIGC Service in Decentralized Internet of Vehicles
  58. TFB: Towards Comprehensive and Fair Benchmarking of Time Series Forecasting Methods
  59. Conformal Prediction for Stochastic Decision-Making of PV Power in Electricity Markets
  60. IndiBias: A Benchmark Dataset to Measure Social Biases in Language Models for Indian Context
  61. Leveraging language models for summarizing mental state examinations: A comprehensive evaluation and dataset release
  62. StegoGAN: Leveraging Steganography for Non-Bijective Image-to-Image Translation
  63. Designing Poisson Integrators Through Machine Learning
  64. User Modeling Challenges in Interactive AI Assistant Systems
  65. Sound event localization and classification using WASN in Outdoor Environment
  66. The Impact of Prompts on Zero-Shot Detection of AI-Generated Text
  67. ECLIPSE: Efficient Continual Learning in Panoptic Segmentation with Visual Prompt Tuning
  68. Application of Machine Learning Algorithms in Classifying Postoperative Success in Metabolic Bariatric Surgery: A Comprehensive Study
  69. Learning using granularity statistical invariants for classification
  70. Segmentation, Classification and Interpretation of Breast Cancer Medical Images using Human-in-the-Loop Machine Learning
  71. NLP for Counterspeech against Hate: A Survey and How-To Guide
  72. RealKIE: Five Novel Datasets for Enterprise Key Information Extraction
  73. Modeling Weather Uncertainty for Multi-weather Co-Presence Estimation
  74. Implications of the AI Act for Non-Discrimination Law and Algorithmic Fairness
  75. An Efficient Approach for Studying Cross-Lingual Transfer in Multilingual Language Models
  76. Selective Attention-based Modulation for Continual Learning
  77. IPA Transcription of Bengali Texts
  78. Mixed-precision Supernet Training from Vision Foundation Models using Low Rank Adapter
  79. Adaptive Decentralized Federated Learning in Energy and Latency Constrained Wireless Networks
  80. Cross-Lingual Transfer Robustness to Lower-Resource Languages on Adversarial Datasets
  81. Embracing Unknown Step by Step: Towards Reliable Sparse Training in Real World
  82. Transformer-Lite: High-efficiency Deployment of Large Language Models on Mobile Phone GPUs
  83. NeSLAM: Neural Implicit Mapping and Self-Supervised Feature Tracking With Depth Completion and Denoising
  84. A novel decision fusion approach for sale price prediction using Elastic Net and MOPSO
  85. HO-Gaussian: Hybrid Optimization of 3D Gaussian Splatting for Urban Scenes
  86. A Unified Framework for Human-centric Point Cloud Video Understanding
  87. SCINeRF: Neural Radiance Fields from a Snapshot Compressive Image
  88. Adverb Is the Key: Simple Text Data Augmentation with Adverb Deletion
  89. PURPLE: Making a Large Language Model a Better SQL Writer
  90. DerainNeRF: 3D Scene Estimation with Adhesive Waterdrop Removal
  91. Colorful Cutout: Enhancing Image Data Augmentation with Curriculum Learning
  92. On Large Language Models' Hallucination with Regard to Known Facts
  93. Large Language Model based Situational Dialogues for Second Language Learning
  94. Grounding and Enhancing Grid-based Models for Neural Fields
  95. DeepHeteroIoT: Deep Local and Global Learning over Heterogeneous IoT Sensor Data
  96. Development of Compositionality and Generalization through Interactive Learning of Language and Action of Robots
  97. MindArm: Mechanized Intelligent Non-Invasive Neuro-Driven Prosthetic Arm System
  98. Stable Surface Regularization for Fast Few-Shot NeRF
  99. A multi-stage semi-supervised learning for ankle fracture classification on CT images
  100. A Parallel Attention Network for Cattle Face Recognition
  101. Continual Adapter Tuning with Semantic Shift Compensation for Class-Incremental Learning
  102. eTraM: Event-based Traffic Monitoring Dataset
  103. Context-Aware Integration of Language and Visual References for Natural Language Tracking
  104. Separate, Dynamic and Differentiable (SMART) Pruner for Block/Output Channel Pruning on Computer Vision Tasks
  105. Rewrite the Stars
  106. Multi-task Magnetic Resonance Imaging Reconstruction using Meta-learning
  107. FairRAG: Fair Human Generation via Fair Retrieval Augmentation
  108. Efficient Modulation for Vision Networks
  109. Coverage-Guaranteed Prediction Sets for Out-of-Distribution Data
  110. FairCLIP: Harnessing Fairness in Vision-Language Learning
  111. A Peg-in-hole Task Strategy for Holes in Concrete
  112. Binarized Low-light Raw Video Enhancement
  113. TDANet: A Novel Temporal Denoise Convolutional Neural Network With Attention for Fault Diagnosis
  114. SLFNet: Generating Semantic Logic Forms from Natural Language Using Semantic Probability Graphs
  115. CP HDR: A feature point detection and description library for LDR and HDR images
  116. Are LLMs Effective Backbones for Fine-tuning? An Experimental Investigation of Supervised LLMs on Chinese Short Text Matching
  117. DiJiang: Efficient Large Language Models through Compact Kernelization
  118. Video-Based Human Pose Regression via Decoupled Space-Time Aggregation
  119. SceneTracker: Long-term Scene Flow Estimation Network
  120. MI-NeRF: Learning a Single Face NeRF from Multiple Identities
  121. Diff-Reg v1: Diffusion Matching Model for Registration Problem
  122. Using Images as Covariates: Measuring Curb Appeal with Deep Learning
  123. MANGO: A Benchmark for Evaluating Mapping and Navigation Abilities of Large Language Models
  124. Automated Identification and Segmentation of Hi Sources in CRAFTS Using Deep Learning Method
  125. Beyond the Known: Novel Class Discovery for Open-world Graph Learning
  126. Classification of Diabetic Retinopathy using Pre-Trained Deep Learning Models
  127. Fully Geometric Panoramic Localization
  128. Heterogeneous Network Based Contrastive Learning Method for PolSAR Land Cover Classification
  129. Disentangling Racial Phenotypes: Fine-Grained Control of Race-related Facial Phenotype Characteristics
  130. Nonlinearity Enhanced Adaptive Activation Functions
  131. An Information-Theoretic Framework for Out-of-Distribution Generalization with Applications to Stochastic Gradient Langevin Dynamics
  132. PLoc: A New Evaluation Criterion Based on Physical Location for Autonomous Driving Datasets