{"total":91,"rows":[{"id":"2311.01043","title":"LLM4Drive: A Survey of Large Language Models for Autonomous Driving","created":"2023-11-02","cited_by_count":136,"area":"driving"},{"id":"2504.11171","title":"TerraMind: Large-Scale Generative Multimodality for Earth Observation","created":"2025-04-15","cited_by_count":104,"area":null},{"id":"2312.12730","title":"A Closer Look at the Few-Shot Adaptation of Large Vision-Language Models","created":"2023-12-20","cited_by_count":67,"area":"mllm"},{"id":"2405.02266","title":"On the test-time zero-shot generalization of vision-language models: Do we really need prompt learning?","created":"2024-05-03","cited_by_count":67,"area":"mllm"},{"id":"2504.15376","title":"Towards Understanding Camera Motions in Any Video","created":"2025-04-21","cited_by_count":64,"area":null},{"id":"2401.12425","title":"The Neglected Tails in Vision-Language Models","created":"2024-01-23","cited_by_count":63,"area":"mllm"},{"id":"2403.17589","title":"Dual Memory Networks: A Versatile Adaptation Approach for Vision-Language Models","created":"2024-03-26","cited_by_count":52,"area":"mllm"},{"id":"2306.01879","title":"Revisiting the Role of Language Priors in Vision-Language Models","created":"2023-06-02","cited_by_count":50,"area":"mllm"},{"id":"2306.07520","title":"Instruct-ReID: A Multi-purpose Person Re-identification Task with Instructions","created":"2023-06-13","cited_by_count":46,"area":null},{"id":"2410.12790","title":"Dual Prototype Evolving for Test-Time Generalization of Vision-Language Models","created":"2024-10-16","cited_by_count":38,"area":"mllm"},{"id":"2309.05950","title":"Language Models as Black-Box Optimizers for Vision-Language Models","created":"2023-09-12","cited_by_count":36,"area":"mllm"},{"id":"2406.07544","title":"Situational Awareness Matters in 3D Vision Language Reasoning","created":"2024-06-11","cited_by_count":33,"area":null},{"id":"2401.01736","title":"Few-shot Adaptation of Multi-modal Foundation Models: A Survey","created":"2024-01-03","cited_by_count":28,"area":null},{"id":"2409.03868","title":"Few-shot Adaptation of Medical Vision-Language Models","created":"2024-09-05","cited_by_count":24,"area":"mllm"},{"id":"2501.18592","title":"Advances in Multimodal Adaptation and Generalization: From Traditional Approaches to Foundation Models","created":"2025-01-30","cited_by_count":23,"area":null},{"id":"2306.13856","title":"Learning-to-Rank Meets Language: Boosting Language-Driven Ordering Alignment for Ordinal Classification","created":"2023-06-24","cited_by_count":21,"area":null},{"id":"2308.07545","title":"Vision-Language Dataset Distillation","created":"2023-08-15","cited_by_count":19,"area":null},{"id":"2410.02131","title":"Boosting Masked ECG-Text Auto-Encoders as Discriminative Learners","created":"2024-10-03","cited_by_count":17,"area":null},{"id":"2308.06262","title":"Foundation Model is Efficient Multimodal Multitask Model Selector","created":"2023-08-11","cited_by_count":16,"area":null},{"id":"2401.00430","title":"Brain-Conditional Multimodal Synthesis: A Survey and Taxonomy","created":"2023-12-31","cited_by_count":15,"area":null},{"id":"2405.02954","title":"Source-Free Domain Adaptation Guided by Vision and Vision-Language Pre-Training","created":"2024-05-05","cited_by_count":15,"area":"mllm"},{"id":"2406.11148","title":"Few-Shot Recognition via Stage-Wise Retrieval-Augmented Finetuning","created":"2024-06-17","cited_by_count":15,"area":"rag"},{"id":"2410.22330","title":"Vision-Language Models Create Cross-Modal Task Representations","created":"2024-10-29","cited_by_count":15,"area":"mllm"},{"id":"2501.11175","title":"ProKeR: A Kernel Perspective on Few-Shot Adaptation of Large Vision-Language Models","created":"2025-01-19","cited_by_count":15,"area":"mllm"},{"id":"2505.24693","title":"Conformal Prediction for Zero-Shot Models","created":"2025-05-30","cited_by_count":15,"area":"mllm"},{"id":"2403.04294","title":"A$^{3}$lign-DFER: Pioneering Comprehensive Dynamic Affective Alignment for Dynamic Facial Expression Recognition with CLIP","created":"2024-03-07","cited_by_count":14,"area":null},{"id":"2412.06082","title":"Are foundation models for computer vision good conformal predictors?","created":"2024-12-08","cited_by_count":13,"area":"mllm"},{"id":"2507.03657","title":"Dynamic Multimodal Prototype Learning in Vision-Language Models","created":"2025-07-04","cited_by_count":13,"area":"mllm"},{"id":"2307.15460","title":"Cross-Modal Concept Learning and Inference for Vision-Language Models","created":"2023-07-28","cited_by_count":12,"area":"mllm"},{"id":"2309.14580","title":"CWCL: Cross-Modal Transfer with Continuously Weighted Contrastive Loss","created":"2023-09-26","cited_by_count":12,"area":null},{"id":"2507.14976","title":"Hierarchical Cross-modal Prompt Learning for Vision-Language Models","created":"2025-07-20","cited_by_count":12,"area":"mllm"},{"id":"2412.00142","title":"Enhancing Few-Shot Vision-Language Classification with Large Multimodal Model Features","created":"2024-11-28","cited_by_count":11,"area":"mllm"},{"id":"2305.11092","title":"Universal Domain Adaptation from Foundation Models: A Baseline Study","created":"2023-05-18","cited_by_count":10,"area":null},{"id":"2506.06076","title":"Full Conformal Adaptation of Medical Vision-Language Models","created":"2025-06-06","cited_by_count":9,"area":"mllm"},{"id":"2307.11315","title":"GIST: Generating Image-Specific Text for Fine-grained Object Classification","created":"2023-07-21","cited_by_count":8,"area":"mllm"},{"id":"2312.06401","title":"Compound Text-Guided Prompt Tuning via Image-Adaptive Cues","created":"2023-12-11","cited_by_count":7,"area":"mllm"},{"id":"2312.15571","title":"A Survey on Open-Set Image Recognition","created":"2023-12-25","cited_by_count":7,"area":null},{"id":"2504.17696","title":"Hierarchical and Multimodal Data for Daily Activity Understanding","created":"2025-04-24","cited_by_count":7,"area":null},{"id":"2506.17500","title":"Few-Shot, Now for Real: Medical VLMs Adaptation without Balanced Sets or Validation","created":"2025-06-20","cited_by_count":7,"area":"mllm"},{"id":"2309.01256","title":"BDC-Adapter: Brownian Distance Covariance for Better Vision-Language Reasoning","created":"2023-09-03","cited_by_count":6,"area":"lr"},{"id":"2311.13612","title":"Descriptor and Word Soups: Overcoming the Parameter Efficiency Accuracy Tradeoff for Out-of-Distribution Few-shot Learning","created":"2023-11-21","cited_by_count":6,"area":null},{"id":"2412.11375","title":"Text and Image Are Mutually Beneficial: Enhancing Training-Free Few-Shot Classification with CLIP","created":"2024-12-16","cited_by_count":6,"area":null},{"id":"2502.12488","title":"Enhancing Audio-Visual Spiking Neural Networks through Semantic-Alignment and Cross-Modal Residual Learning","created":"2025-02-18","cited_by_count":5,"area":null},{"id":"2505.14951","title":"MultiMAE Meets Earth Observation: Pre-training Multi-modal Multi-task Masked Autoencoders for Earth Observation Tasks","created":"2025-05-20","cited_by_count":5,"area":null},{"id":"2503.10665","title":"Small Vision-Language Models: A Survey on Compact Architectures and Techniques","created":"2025-03-09","cited_by_count":4,"area":"mllm"},{"id":"2506.03521","title":"Target Semantics Clustering via Text Representations for Robust Universal Domain Adaptation","created":"2025-06-04","cited_by_count":4,"area":null},{"id":"2308.10450","title":"COCA: Classifier-Oriented Calibration via Textual Prototype for Source-Free Universal Domain Adaptation","created":"2023-08-21","cited_by_count":3,"area":null},{"id":"2404.08915","title":"PM2: A New Prompting Multi-modal Model Paradigm for Few-shot Medical Image Classification","created":"2024-04-13","cited_by_count":3,"area":null},{"id":"2502.14889","title":"Narrowing Information Bottleneck Theory for Multimodal Image-Text Representations Interpretability","created":"2025-02-16","cited_by_count":3,"area":null},{"id":"2604.21718","title":"Building a Precise Video Language with Human-AI Oversight","created":"2026-04-22","cited_by_count":3,"area":null},{"id":"2311.00693","title":"On Task-personalized Multimodal Few-shot Learning for Visually-rich Document Entity Retrieval","created":"2023-11-01","cited_by_count":2,"area":null},{"id":"2311.18420","title":"TeG-DG: Textually Guided Domain Generalization for Face Anti-Spoofing","created":"2023-11-30","cited_by_count":2,"area":null},{"id":"2407.12879","title":"Large Visual-Language Models Are Also Good Classifiers: A Study of In-Context Multimodal Fake News Detection","created":"2024-07-16","cited_by_count":2,"area":"mllm"},{"id":"2410.10663","title":"Cross-Modal Few-Shot Learning: a Generative Transfer Learning Framework","created":"2024-10-14","cited_by_count":2,"area":null},{"id":"2503.01531","title":"Diversity Covariance-Aware Prompt Learning for Vision-Language Models","created":"2025-03-03","cited_by_count":2,"area":"mllm"},{"id":"2506.01724","title":"Active Learning via Vision-Language Model Adaptation with Open Data","created":"2025-06-02","cited_by_count":2,"area":"mllm"},{"id":"2506.04713","title":"Enabling Validation for Robust Few-Shot Recognition","created":"2025-06-05","cited_by_count":2,"area":null},{"id":"2508.03102","title":"Causal Disentanglement and Cross-Modal Alignment for Enhanced Few-Shot Learning","created":"2025-08-05","cited_by_count":2,"area":null},{"id":"2404.00675","title":"LLM meets Vision-Language Models for Zero-Shot One-Class Classification","created":"2024-03-31","cited_by_count":1,"area":"mllm"},{"id":"2406.15664","title":"Flat Posterior Does Matter For Bayesian Model Averaging","created":"2024-06-21","cited_by_count":1,"area":null},{"id":"2409.09753","title":"DARDA: Domain-Aware Real-Time Dynamic Neural Network Adaptation","created":"2024-09-15","cited_by_count":1,"area":null},{"id":"2410.05270","title":"CLIP's Visual Embedding Projector is a Few-shot Cornucopia","created":"2024-10-07","cited_by_count":1,"area":"mllm"},{"id":"2412.16654","title":"IV-tuning: Parameter-Efficient Transfer Learning for Infrared-Visible Tasks","created":"2024-12-21","cited_by_count":1,"area":null},{"id":"2412.20110","title":"Cross-Modal Mapping: Mitigating the Modality Gap for Few-Shot Image Classification","created":"2024-12-28","cited_by_count":1,"area":null},{"id":"2503.24017","title":"Crossmodal Knowledge Distillation with WordNet-Relaxed Text Embeddings for Robust Image Classification","created":"2025-03-31","cited_by_count":1,"area":"distill"},{"id":"2508.13387","title":"SPANER: Shared Prompt Aligner for Multimodal Semantic Representation","created":"2025-08-18","cited_by_count":1,"area":null},{"id":"2509.03433","title":"Decoding Visual Neural Representations by Multimodal with Dynamic Balancing","created":"2025-09-03","cited_by_count":1,"area":null},{"id":"2603.00574","title":"Decoupling Stability and Plasticity for Multi-Modal Test-Time Adaptation","created":"2026-02-28","cited_by_count":1,"area":null},{"id":"2603.16100","title":"Reevaluating the Intra-Modal Misalignment Hypothesis in CLIP","created":"2026-03-17","cited_by_count":1,"area":null},{"id":"2311.14544","title":"Inferring Latent Class Statistics from Text for Robust Visual Few-Shot Learning","created":"2023-11-24","cited_by_count":0,"area":null},{"id":"2312.10945","title":"LaViP:Language-Grounded Visual Prompts","created":"2023-12-18","cited_by_count":0,"area":"mllm"},{"id":"2403.00724","title":"Few-Shot Relation Extraction with Hybrid Visual Evidence","created":"2024-03-01","cited_by_count":0,"area":null},{"id":"2404.05183","title":"Progressive Alignment with VLM-LLM Feature to Augment Defect Classification for the ASE Dataset","created":"2024-04-08","cited_by_count":0,"area":null},{"id":"2404.10357","title":"Optimization of Prompt Learning via Multi-Knowledge Representation for Vision-Language Models","created":"2024-04-16","cited_by_count":0,"area":"mllm"},{"id":"2405.12543","title":"Like Humans to Few-Shot Learning through Knowledge Permeation of Vision and Text","created":"2024-05-21","cited_by_count":0,"area":null},{"id":"2405.16027","title":"Feature Protection For Out-of-distribution Generalization","created":"2024-05-25","cited_by_count":0,"area":null},{"id":"2411.11370","title":"Transmission Line Defect Detection Based on UAV Patrol Images and Vision-language Pretraining","created":"2024-11-18","cited_by_count":0,"area":null},{"id":"2411.15611","title":"If you can describe it, they can see it: Cross-Modal Learning of Visual Concepts from Textual Descriptions","created":"2024-11-23","cited_by_count":0,"area":null},{"id":"2504.04017","title":"A Comprehensive Survey of Challenges and Opportunities of Few-Shot Learning Across Multiple Domains","created":"2025-04-05","cited_by_count":0,"area":null},{"id":"2506.02914","title":"AutoExpert: Automating 3D LiDAR Annotation from Expert-Crafted Guidelines","created":"2025-06-03","cited_by_count":0,"area":null},{"id":"2507.07994","title":"Doodle Your Keypoints: Sketch-Based Few-Shot Keypoint Detection","created":"2025-07-10","cited_by_count":0,"area":null},{"id":"2508.00218","title":"Object-Centric Cropping for Visual Few-Shot Classification","created":"2025-07-31","cited_by_count":0,"area":null},{"id":"2512.10244","title":"Solving Semi-Supervised Few-Shot Learning from an Auto-Annotation Perspective","created":"2025-12-11","cited_by_count":0,"area":null},{"id":"2512.15748","title":"Visual Species Recognition with Large Multimodal Models as Post-Hoc Correctors","created":"2025-12-10","cited_by_count":0,"area":"mllm"},{"id":"2603.02959","title":"Semi-Supervised Few-Shot Adaptation of Vision-Language Models","created":"2026-03-03","cited_by_count":0,"area":"mllm"},{"id":"2605.01424","title":"Quantifying Multimodal Capabilities: Formal Generalization Guarantees in Pairwise Metric Learning","created":"2026-05-02","cited_by_count":0,"area":null},{"id":"2607.17820","title":"PRiSM: Prototype Regularization for Few-Shot VLMs","created":"2026-07-20","cited_by_count":0,"area":"mllm"},{"id":"2608.23634","title":"The Blending Ratio Is Not Where the Performance Is: Diagnosing Prototype Blending for Few-Shot Adaptation of Vision-Language Models","created":"2026-08-23","cited_by_count":0,"area":"mllm"},{"id":"2609.26513","title":"Virtual Encoders in Multimodal Transformers","created":"2026-09-22","cited_by_count":0,"area":"mllm"},{"id":"2609.34021","title":"Position Aware Layer Queries for Test Time Training in Vision Language Models","created":"2026-09-27","cited_by_count":0,"area":"mllm"},{"id":"2609.37298","title":"Scaling Full Conformal Image Classifiers","created":"2026-09-29","cited_by_count":0,"area":null}],"next_cursor":null}