{"total":54,"rows":[{"id":"2408.02265","title":"Explain via Any Concept: Concept Bottleneck Model with Open Vocabulary Concepts","created":"2024-08-05","cited_by_count":20,"area":null},{"id":"2406.11148","title":"Few-Shot Recognition via Stage-Wise Retrieval-Augmented Finetuning","created":"2024-06-17","cited_by_count":15,"area":"rag"},{"id":"2506.02557","title":"Kernel-based Unsupervised Embedding Alignment for Enhanced Visual Representation in Vision-language Models","created":"2025-06-03","cited_by_count":15,"area":"mllm"},{"id":"2508.19294","title":"Object Detection with Multimodal Large Vision-Language Models: An In-depth Review","created":"2025-08-25","cited_by_count":14,"area":"mllm"},{"id":"2502.19844","title":"ProAPO: Progressively Automatic Prompt Optimization for Visual Classification","created":"2025-02-27","cited_by_count":13,"area":"mllm"},{"id":"2511.05681","title":"Culture in Action: Evaluating Text-to-Image Models through Social Activities","created":"2025-11-07","cited_by_count":10,"area":"diffusion"},{"id":"2506.18378","title":"Taming Vision-Language Models for Medical Image Analysis: A Comprehensive Review","created":"2025-06-23","cited_by_count":9,"area":"mllm"},{"id":"2503.12874","title":"Evolution-based Region Adversarial Prompt Learning for Robustness Enhancement in Vision-Language Models","created":"2025-03-17","cited_by_count":6,"area":"mllm"},{"id":"2510.19555","title":"[De|Re]constructing VLMs' Reasoning in Counting","created":"2025-10-22","cited_by_count":6,"area":"lr"},{"id":"2405.15269","title":"Test-Time Multimodal Backdoor Detection by Contrastive Prompting","created":"2024-05-24","cited_by_count":5,"area":"safety"},{"id":"2411.19346","title":"CLIP meets DINO for Tuning Zero-Shot Classifier using Unlabeled Image Collections","created":"2024-11-28","cited_by_count":5,"area":null},{"id":"2508.01602","title":"Enhancing Zero-Shot Brain Tumor Subtype Classification via Fine-Grained Patch-Text Alignment","created":"2025-08-03","cited_by_count":4,"area":null},{"id":"2510.03903","title":"Zero-Shot Fine-Grained Image Classification Using Large Vision-Language Models","created":"2025-10-04","cited_by_count":4,"area":"mllm"},{"id":"2603.16737","title":"Retrieving Counterfactuals Improves Visual In-Context Learning","created":"2026-03-17","cited_by_count":4,"area":"lr"},{"id":"2504.19742","title":"EcoWikiRS: Learning Ecological Representation of Satellite Images from Weak Supervision with Species Observations and Wikipedia","created":"2025-04-28","cited_by_count":3,"area":null},{"id":"2507.06210","title":"CultureCLIP: Empowering CLIP with Cultural Awareness through Synthetic Images and Contextualized Captions","created":"2025-07-08","cited_by_count":3,"area":"mllm"},{"id":"2508.01057","title":"Edge-Based Multimodal Sensor Data Fusion with Vision Language Models (VLMs) for Real-time Autonomous Vehicle Accident Avoidance","created":"2025-08-01","cited_by_count":3,"area":"driving"},{"id":"2510.14737","title":"Free-Grained Hierarchical Visual Recognition","created":"2025-10-16","cited_by_count":3,"area":null},{"id":"2410.07173","title":"Better Language Models Exhibit Higher Visual Alignment","created":"2024-10-09","cited_by_count":2,"area":null},{"id":"2411.05357","title":"Enhancing Visual Classification using Comparative Descriptors","created":"2024-11-08","cited_by_count":2,"area":"mllm"},{"id":"2501.06031","title":"Generate, Transduct, Adapt: Iterative Transduction with VLMs","created":"2025-01-10","cited_by_count":2,"area":"mllm"},{"id":"2502.00618","title":"DesCLIP: Robust Continual Learning via General Attribute Descriptions for VLM-Based Visual Recognition","created":"2025-02-02","cited_by_count":2,"area":"mllm"},{"id":"2504.00185","title":"Self-Evolving Visual Concept Library using Vision-Language Critics","created":"2025-03-31","cited_by_count":2,"area":"synth"},{"id":"2507.08410","title":"Multi-modal Mutual-Guidance Conditional Prompt Learning for Vision-Language Models","created":"2025-07-11","cited_by_count":2,"area":"mllm"},{"id":"2509.08003","title":"An Explainable Deep Neural Network with Frequency-Aware Channel and Spatial Refinement for Flood Prediction in Sustainable Cities","created":"2025-09-07","cited_by_count":2,"area":null},{"id":"2410.11686","title":"A Survey of Low-shot Vision-Language Model Adaptation via Representer Theorem","created":"2024-10-15","cited_by_count":1,"area":"mllm"},{"id":"2412.00364","title":"LMSeg: Unleashing the Power of Large-Scale Models for Open-Vocabulary Semantic Segmentation","created":"2024-11-30","cited_by_count":1,"area":null},{"id":"2503.01169","title":"A Zero-Shot Learning Approach for Ephemeral Gully Detection from Remote Sensing using Vision Language Models","created":"2025-03-03","cited_by_count":1,"area":null},{"id":"2504.14129","title":"PVLM: Parsing-Aware Vision Language Model with Dynamic Contrastive Learning for Zero-Shot Deepfake Attribution","created":"2025-04-19","cited_by_count":1,"area":"mllm"},{"id":"2506.15084","title":"An Empirical Study of Bugs in Data Visualization Libraries","created":"2025-06-18","cited_by_count":1,"area":null},{"id":"2512.07302","title":"Towards Accurate UAV Image Perception: Guiding Vision-Language Models with Stronger Task Prompts","created":"2025-12-08","cited_by_count":1,"area":"mllm"},{"id":"2604.11576","title":"Finetune Like You Pretrain: Boosting Zero-shot Adversarial Robustness in Vision-language Models","created":"2026-04-13","cited_by_count":1,"area":"mllm"},{"id":"2606.26734","title":"Robust Onion: Peeling Open Vocab Object Detectors Under Noise","created":"2026-06-25","cited_by_count":1,"area":null},{"id":"2406.16273","title":"YouDream: Generating Anatomically Controllable Consistent Text-to-3D Animals","created":"2024-06-24","cited_by_count":0,"area":"diffusion"},{"id":"2504.21309","title":"An Evaluation of a Visual Question Answering Strategy for Zero-shot Facial Expression Recognition in Still Images","created":"2025-04-30","cited_by_count":0,"area":null},{"id":"2508.13814","title":"Unsupervised Urban Tree Biodiversity Mapping from Street-Level Imagery Using Spatially-Aware Visual Clustering","created":"2025-08-19","cited_by_count":0,"area":null},{"id":"2509.09732","title":"Decomposing Visual Classification: Assessing Tree-Based Reasoning in VLMs","created":"2025-09-10","cited_by_count":0,"area":"lr"},{"id":"2509.18938","title":"No Labels Needed: Zero-Shot Image Classification with Collaborative Self-Learning","created":"2025-09-23","cited_by_count":0,"area":null},{"id":"2510.17626","title":"CaMiT: A Time-Aware Car Model Dataset for Classification and Generation","created":"2025-10-20","cited_by_count":0,"area":null},{"id":"2512.04485","title":"Not All Birds Look The Same: Identity-Preserving Generation For Birds","created":"2025-12-04","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":"2512.17160","title":"Can Synthetic Images Serve as Effective and Efficient Class Prototypes?","created":"2025-12-19","cited_by_count":0,"area":"mllm"},{"id":"2601.12303","title":"Concepts from Representations: Post-hoc Concept Bottleneck Models via Sparse Decomposition of Visual Representations","created":"2026-01-18","cited_by_count":0,"area":null},{"id":"2601.21426","title":"MultiModal Fine-tuning with Synthetic Captions","created":"2026-01-29","cited_by_count":0,"area":null},{"id":"2603.27033","title":"RealBirdID: Benchmarking Bird Species Identification in the Era of MLLMs","created":"2026-03-27","cited_by_count":0,"area":null},{"id":"2605.17341","title":"Single-Sample Black-Box Membership Inference Attack against Vision-Language Models via Cross-modal Semantic Alignment","created":"2026-05-17","cited_by_count":0,"area":"mllm"},{"id":"2606.15134","title":"Beyond Scalar Distances: Semantic Attribute Gradients from Frozen MLLMs for Visual Embeddings","created":"2026-06-13","cited_by_count":0,"area":null},{"id":"2607.00684","title":"AdaBoosting Text Prompts for Vision-Language Models","created":"2026-07-01","cited_by_count":0,"area":"mllm"},{"id":"2608.26744","title":"G2D: Generative-to-Discriminative Collaborative Inference for Zero-Shot Image Classification","created":"2026-08-27","cited_by_count":0,"area":"lr"},{"id":"2608.31107","title":"VeriCam: A Verification Baseline for the Classification of Unknown Data","created":"2026-08-31","cited_by_count":0,"area":null},{"id":"2609.01103","title":"When Modality Gap Reduction Fails: Prediction-Level Hubness in CLIP","created":"2026-09-01","cited_by_count":0,"area":null},{"id":"2610.02718","title":"Revisiting Visual Representation Enhancement of VLMs via Kernel Canonical Correlation Analysis","created":"2026-10-02","cited_by_count":0,"area":"mllm"},{"id":"2610.05993","title":"From Transformation to Target State: Rethinking Query Representation for Zero-Shot Composed Image Retrieval","created":"2026-10-05","cited_by_count":0,"area":"lr"}],"next_cursor":null}