{"total":57,"rows":[{"id":"2201.05078","title":"CLIP-Event: Connecting Text and Images with Event Structures","created":"2022-01-13","cited_by_count":86,"area":"mllm"},{"id":"2210.01253","title":"PLOT: Prompt Learning with Optimal Transport for Vision-Language Models","created":"2022-10-03","cited_by_count":64,"area":"mllm"},{"id":"2503.18278","title":"TopV: Compatible Token Pruning with Inference Time Optimization for Fast and Low-Memory Multimodal Vision Language Model","created":"2025-03-24","cited_by_count":57,"area":"mllm"},{"id":"2304.01752","title":"Black Box Few-Shot Adaptation for Vision-Language models","created":"2023-04-04","cited_by_count":39,"area":"mllm"},{"id":"2312.04403","title":"OT-Attack: Enhancing Adversarial Transferability of Vision-Language Models via Optimal Transport Optimization","created":"2023-12-07","cited_by_count":37,"area":"mllm"},{"id":"2305.14095","title":"S-CLIP: Semi-supervised Vision-Language Learning using Few Specialist Captions","created":"2023-05-23","cited_by_count":30,"area":"mllm"},{"id":"2407.04603","title":"AWT: Transferring Vision-Language Models via Augmentation, Weighting, and Transportation","created":"2024-07-05","cited_by_count":28,"area":"mllm"},{"id":"2310.19752","title":"Intra-Modal Proxy Learning for Zero-Shot Visual Categorization with CLIP","created":"2023-10-30","cited_by_count":27,"area":"mllm"},{"id":"2309.13847","title":"Tuning Multi-mode Token-level Prompt Alignment across Modalities","created":"2023-09-25","cited_by_count":26,"area":"mllm"},{"id":"2305.08675","title":"Improved baselines for vision-language pre-training","created":"2023-05-15","cited_by_count":20,"area":"mllm"},{"id":"2409.19846","title":"Towards Open-Vocabulary Semantic Segmentation Without Semantic Labels","created":"2024-09-30","cited_by_count":19,"area":"mllm"},{"id":"2312.00096","title":"OST: Refining Text Knowledge with Optimal Spatio-Temporal Descriptor for General Video Recognition","created":"2023-11-30","cited_by_count":16,"area":"mllm"},{"id":"2505.24693","title":"Conformal Prediction for Zero-Shot Models","created":"2025-05-30","cited_by_count":15,"area":"mllm"},{"id":"2510.24038","title":"Enhancing CLIP Robustness via Cross-Modality Alignment","created":"2025-10-28","cited_by_count":15,"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":"2303.09100","title":"Patch-Prompt Aligned Bayesian Prompt Tuning for Vision-Language Models","created":"2023-03-16","cited_by_count":12,"area":"mllm"},{"id":"2403.00219","title":"Multi-modal Attribute Prompting for Vision-Language Models","created":"2024-03-01","cited_by_count":12,"area":"mllm"},{"id":"2412.01256","title":"NLPrompt: Noise-Label Prompt Learning for Vision-Language Models","created":"2024-12-02","cited_by_count":9,"area":"mllm"},{"id":"2602.24041","title":"Look Carefully: Adaptive Visual Reinforcements in Multimodal Large Language Models for Hallucination Mitigation","created":"2026-02-27","cited_by_count":7,"area":"mllm"},{"id":"2210.13591","title":"Learning by Hallucinating: Vision-Language Pre-training with Weak Supervision","created":"2022-10-24","cited_by_count":6,"area":"mllm"},{"id":"2410.02615","title":"ExGra-Med: Extended Context Graph Alignment for Medical Vision-Language Models","created":"2024-10-03","cited_by_count":6,"area":"mllm"},{"id":"2506.23822","title":"Interpretable Zero-Shot Learning with Locally-Aligned Vision-Language Model","created":"2025-06-30","cited_by_count":6,"area":"mllm"},{"id":"2606.00959","title":"Towards Understanding Modality Interaction in Multimodal Language Models via Partial Information Decomposition","created":"2026-05-31","cited_by_count":5,"area":"mllm"},{"id":"2407.04489","title":"Dude: Dual Distribution-Aware Context Prompt Learning For Large Vision-Language Model","created":"2024-07-05","cited_by_count":4,"area":"mllm"},{"id":"2603.29676","title":"A Comprehensive Information-Decomposition Analysis of Large Vision-Language Models","created":"2026-03-31","cited_by_count":4,"area":"mllm"},{"id":"2309.04158","title":"Context-Aware Prompt Tuning for Vision-Language Model with Dual-Alignment","created":"2023-09-08","cited_by_count":3,"area":"mllm"},{"id":"2411.17002","title":"Semantic Anchor Transport: Robust Test-Time Adaptation for Vision-Language Models","created":"2024-11-26","cited_by_count":3,"area":"mllm"},{"id":"2502.07409","title":"MGPATH: Vision-Language Model with Multi-Granular Prompt Learning for Few-Shot WSI Classification","created":"2025-02-11","cited_by_count":3,"area":"mllm"},{"id":"2503.01263","title":"Generalizable Prompt Learning of CLIP: A Brief Overview","created":"2025-03-03","cited_by_count":3,"area":"mllm"},{"id":"2509.22404","title":"RAU: Reference-based Anatomical Understanding with Vision Language Models","created":"2025-09-26","cited_by_count":3,"area":"mllm"},{"id":"2407.19674","title":"Advancing Prompt Learning through an External Layer","created":"2024-07-29","cited_by_count":2,"area":"mllm"},{"id":"2507.03434","title":"Unlearning the Noisy Correspondence Makes CLIP More Robust","created":"2025-07-04","cited_by_count":1,"area":"mllm"},{"id":"2508.17417","title":"Constrained Prompt Enhancement for Improving Zero-Shot Generalization of Vision-Language Models","created":"2025-08-24","cited_by_count":1,"area":"mllm"},{"id":"2509.09064","title":"Enhancing 3D Medical Image Understanding with Pretraining Aided by 2D Multimodal Large Language Models","created":"2025-09-11","cited_by_count":1,"area":"mllm"},{"id":"2601.23179","title":"Universal Adversarial Attacks against Closed-Source MLLMs via Target-View Routed Meta Optimization","created":"2026-01-30","cited_by_count":1,"area":"mllm"},{"id":"2602.24027","title":"GuardAlign: Test-time Safety Alignment in Multimodal Large Language Models","created":"2026-02-27","cited_by_count":1,"area":"mllm"},{"id":"2603.19957","title":"HiPath: Hierarchical Vision-Language Alignment for Structured Pathology Report Prediction","created":"2026-03-20","cited_by_count":1,"area":"mllm"},{"id":"2606.29462","title":"MIRROR: Aligning Semantic Relations from Language to Image via Gromov--Wasserstein","created":"2026-06-28","cited_by_count":1,"area":"mllm"},{"id":"2601.08165","title":"Representation Learning with Semantic-aware Instance and Sparse Token Alignments","created":"2026-01-13","cited_by_count":0,"area":"mllm"},{"id":"2602.01346","title":"Model Specific Task Similarity for Vision Language Model Selection via Layer Conductance","created":"2026-02-01","cited_by_count":0,"area":"mllm"},{"id":"2602.22678","title":"ViCLIP-OT: The First Foundation Vision-Language Model for Vietnamese Image-Text Retrieval with Optimal Transport","created":"2026-02-26","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":"2603.08347","title":"Local-Global Prompt Learning via Sparse Optimal Transport","created":"2026-03-09","cited_by_count":0,"area":"mllm"},{"id":"2603.11617","title":"Noise-aware few-shot learning through bi-directional multi-view prompt alignment","created":"2026-03-12","cited_by_count":0,"area":"mllm"},{"id":"2604.06614","title":"Holistic Optimal Label Selection for Robust Prompt Learning under Partial Labels","created":"2026-04-08","cited_by_count":0,"area":"mllm"},{"id":"2604.16067","title":"AEGIS: Anchor-Enforced Gradient Isolation for Knowledge-Preserving Vision-Language-Action Fine-Tuning","created":"2026-04-17","cited_by_count":0,"area":"mllm"},{"id":"2605.04882","title":"FairEnc: A Fair Vision-Language Model with Fair Vision and Text Encoders for Glaucoma Detection","created":"2026-05-06","cited_by_count":0,"area":"mllm"},{"id":"2605.13352","title":"GeoFlowVLM: Geometry-Aware Joint Uncertainty for Frozen Vision-Language Embedding","created":"2026-05-13","cited_by_count":0,"area":"mllm"},{"id":"2606.04385","title":"Geometry-Preserving Unsupervised Alignment for Heterogeneous Foundation Models","created":"2026-06-03","cited_by_count":0,"area":"mllm"},{"id":"2606.29464","title":"Rank-Aware Hyperbolic Alignment for Vision-Language Dataset Distillation","created":"2026-06-28","cited_by_count":0,"area":"mllm"},{"id":"2607.12787","title":"Do We Really Need Multimodal Emotion Language Models Larger Than 1B Parameters?","created":"2026-07-14","cited_by_count":0,"area":"mllm"},{"id":"2608.00279","title":"Learning to See Locally and Align Clinically with Pathology Semantics for Radiology Report Generation","created":"2026-07-31","cited_by_count":0,"area":"mllm"},{"id":"2608.08418","title":"Learning Deep Modality-Shared Self-Expressiveness for Image Clustering with Textual Information","created":"2026-08-09","cited_by_count":0,"area":"mllm"},{"id":"2609.03085","title":"Solving the Needle-in-a-Haystack Problem in Mammography Vision-Language Model with Differentiable Subset Sampling","created":"2026-09-02","cited_by_count":0,"area":"mllm"},{"id":"2609.10224","title":"UOT-Gap: A Variational Principle for the Modality Gap in Vision-Language Models via Unbalanced Optimal Transport","created":"2026-09-09","cited_by_count":0,"area":"mllm"},{"id":"2609.16858","title":"TecoPrompt: Temporal-Conservative Prompt Learning for Vision-Language Models","created":"2026-09-15","cited_by_count":0,"area":"mllm"},{"id":"2609.34899","title":"ColNanoVDR: Document-Free Query Distillation for Multi-Vector Visual Document Retrieval via Optimal Transport","created":"2026-09-28","cited_by_count":0,"area":"mllm"}],"next_cursor":null}