{"total":18,"rows":[{"id":"2502.04263","title":"Cross the Gap: Exposing the Intra-modal Misalignment in CLIP via Modality Inversion","created":"2025-02-06","cited_by_count":43,"area":"mllm"},{"id":"2305.18010","title":"Test-Time Adaptation with CLIP Reward for Zero-Shot Generalization in Vision-Language Models","created":"2023-05-29","cited_by_count":38,"area":"mllm"},{"id":"2401.06129","title":"Distilling Vision-Language Models on Millions of Videos","created":"2024-01-11","cited_by_count":20,"area":"mllm"},{"id":"2408.10202","title":"SANER: Annotation-free Societal Attribute Neutralizer for Debiasing CLIP","created":"2024-08-19","cited_by_count":19,"area":"mllm"},{"id":"2402.09816","title":"Mind the Modality Gap: Towards a Remote Sensing Vision-Language Model via Cross-modal Alignment","created":"2024-02-15","cited_by_count":15,"area":"mllm"},{"id":"2602.07026","title":"Modality Gap-Driven Subspace Alignment Training Paradigm For Multimodal Large Language Models","created":"2026-02-02","cited_by_count":10,"area":"mllm"},{"id":"2502.16427","title":"Fine-Grained Captioning of Long Videos through Scene Graph Consolidation","created":"2025-02-23","cited_by_count":8,"area":"mllm"},{"id":"2601.09385","title":"SLAM-LLM: A Modular, Open-Source Multimodal Large Language Model Framework and Best Practice for Speech, Language, Audio and Music Processing","created":"2026-01-14","cited_by_count":8,"area":"mllm"},{"id":"2403.13756","title":"Enhancing Gait Video Analysis in Neurodegenerative Diseases by Knowledge Augmentation in Vision Language Model","created":"2024-03-20","cited_by_count":4,"area":"mllm"},{"id":"2503.05204","title":"Data-Efficient Generalization for Zero-shot Composed Image Retrieval","created":"2025-03-07","cited_by_count":2,"area":"mllm"},{"id":"2409.09362","title":"Generating Event-oriented Attribution for Movies via Two-Stage Prefix-Enhanced Multimodal LLM","created":"2024-09-14","cited_by_count":1,"area":"mllm"},{"id":"2410.09365","title":"Debiasing Vison-Language Models with Text-Only Training","created":"2024-10-12","cited_by_count":1,"area":"mllm"},{"id":"2512.03463","title":"Text-Printed Image: Bridging the Image-Text Modality Gap for Text-centric Training of Large Vision-Language Models","created":"2025-12-03","cited_by_count":1,"area":"mllm"},{"id":"2307.05591","title":"Linear Alignment of Vision-language Models for Image Captioning","created":"2023-07-10","cited_by_count":0,"area":"mllm"},{"id":"2604.00279","title":"The Geometry of Compromise: Unlocking Generative Capabilities via Controllable Modality Alignment","created":"2026-03-31","cited_by_count":0,"area":"mllm"},{"id":"2605.22484","title":"Supervised Classification Heads as Semantic Prototypes: Unlocking Vision-Language Alignment via Weight Recycling","created":"2026-05-21","cited_by_count":0,"area":"mllm"},{"id":"2608.24142","title":"What Does Prompt Learning Change? -A Natural-Language Concept Analysis of Vision-Language Models","created":"2026-08-25","cited_by_count":0,"area":"mllm"},{"id":"2608.28218","title":"Focus Where It Counts: A Salience-Driven Vision-Language Model for Low Vision Assistance","created":"2026-08-28","cited_by_count":0,"area":"mllm"}],"next_cursor":null}