{"total":81,"rows":[{"id":"2410.02713","title":"LLaVA-Video: Video Instruction Tuning With Synthetic Data","created":"2024-10-03","cited_by_count":583,"area":"mllm"},{"id":"2312.03700","title":"OneLLM: One Framework to Align All Modalities with Language","created":"2023-12-06","cited_by_count":187,"area":"mllm"},{"id":"2202.09061","title":"VLP: A Survey on Vision-Language Pre-training","created":"2022-02-18","cited_by_count":159,"area":"mllm"},{"id":"2204.03649","title":"Unsupervised Prompt Learning for Vision-Language Models","created":"2022-04-07","cited_by_count":127,"area":"mllm"},{"id":"2308.11681","title":"VadCLIP: Adapting Vision-Language Models for Weakly Supervised Video Anomaly Detection","created":"2023-08-22","cited_by_count":123,"area":"mllm"},{"id":"2210.09263","title":"Vision-Language Pre-training: Basics, Recent Advances, and Future Trends","created":"2022-10-17","cited_by_count":117,"area":"mllm"},{"id":"2211.01335","title":"Chinese CLIP: Contrastive Vision-Language Pretraining in Chinese","created":"2022-11-02","cited_by_count":109,"area":"mllm"},{"id":"2402.10828","title":"RAG-Driver: Generalisable Driving Explanations with Retrieval-Augmented In-Context Learning in Multi-Modal Large Language Model","created":"2024-02-16","cited_by_count":92,"area":"mllm"},{"id":"2303.11313","title":"CLIP goes 3D: Leveraging Prompt Tuning for Language Grounded 3D Recognition","created":"2023-03-20","cited_by_count":77,"area":"mllm"},{"id":"2501.09425","title":"Vision-Language Models Do Not Understand Negation","created":"2025-01-16","cited_by_count":72,"area":"mllm"},{"id":"2207.01297","title":"Revisiting Classifier: Transferring Vision-Language Models for Video Recognition","created":"2022-07-04","cited_by_count":71,"area":"mllm"},{"id":"2301.06309","title":"UATVR: Uncertainty-Adaptive Text-Video Retrieval","created":"2023-01-16","cited_by_count":55,"area":"mllm"},{"id":"2301.00182","title":"Bidirectional Cross-Modal Knowledge Exploration for Video Recognition with Pre-trained Vision-Language Models","created":"2022-12-31","cited_by_count":49,"area":"mllm"},{"id":"2302.06605","title":"UniAdapter: Unified Parameter-Efficient Transfer Learning for Cross-modal Modeling","created":"2023-02-13","cited_by_count":40,"area":"mllm"},{"id":"2403.14774","title":"Few-Shot Adversarial Prompt Learning on Vision-Language Models","created":"2024-03-21","cited_by_count":39,"area":"mllm"},{"id":"2510.27280","title":"FOCUS: Efficient Keyframe Selection for Long Video Understanding","created":"2025-10-31","cited_by_count":37,"area":"mllm"},{"id":"2305.14014","title":"CLIP4STR: A Simple Baseline for Scene Text Recognition with Pre-trained Vision-Language Model","created":"2023-05-23","cited_by_count":30,"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":"2210.04287","title":"Learning to Decompose Visual Features with Latent Textual Prompts","created":"2022-10-09","cited_by_count":28,"area":"mllm"},{"id":"2304.02560","title":"VicTR: Video-conditioned Text Representations for Activity Recognition","created":"2023-04-05","cited_by_count":28,"area":"mllm"},{"id":"2306.09244","title":"Text Promptable Surgical Instrument Segmentation with Vision-Language Models","created":"2023-06-15","cited_by_count":28,"area":"mllm"},{"id":"2309.00661","title":"Zero-Shot Video Moment Retrieval from Frozen Vision-Language Models","created":"2023-09-01","cited_by_count":22,"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":"2303.06591","title":"Accommodating Audio Modality in CLIP for Multimodal Processing","created":"2023-03-12","cited_by_count":18,"area":"mllm"},{"id":"2406.18113","title":"Chrono: A Simple Blueprint for Representing Time in MLLMs","created":"2024-06-26","cited_by_count":18,"area":"mllm"},{"id":"2306.10169","title":"Meta-Personalizing Vision-Language Models to Find Named Instances in Video","created":"2023-06-16","cited_by_count":16,"area":"mllm"},{"id":"2207.05333","title":"IDEA: Increasing Text Diversity via Online Multi-Label Recognition for Vision-Language Pre-training","created":"2022-07-12","cited_by_count":14,"area":"mllm"},{"id":"2303.10571","title":"Reinforcement Learning Friendly Vision-Language Model for Minecraft","created":"2023-03-19","cited_by_count":14,"area":"mllm"},{"id":"2412.00440","title":"Advancing Myopia To Holism: Fully Contrastive Language-Image Pre-training","created":"2024-11-30","cited_by_count":13,"area":"mllm"},{"id":"2503.15973","title":"STOP: Integrated Spatial-Temporal Dynamic Prompting for Video Understanding","created":"2025-03-20","cited_by_count":13,"area":"mllm"},{"id":"2212.09335","title":"Distilling Vision-Language Pre-training to Collaborate with Weakly-Supervised Temporal Action Localization","created":"2022-12-19","cited_by_count":12,"area":"mllm"},{"id":"2308.02982","title":"Beyond First Impressions: Integrating Joint Multi-modal Cues for Comprehensive 3D Representation","created":"2023-08-06","cited_by_count":12,"area":"mllm"},{"id":"2505.20715","title":"MUSEG: Reinforcing Video Temporal Understanding via Timestamp-Aware Multi-Segment Grounding","created":"2025-05-27","cited_by_count":12,"area":"mllm"},{"id":"2305.16999","title":"Three Towers: Flexible Contrastive Learning with Pretrained Image Models","created":"2023-05-26","cited_by_count":11,"area":"mllm"},{"id":"2306.09085","title":"COSA: Concatenated Sample Pretrained Vision-Language Foundation Model","created":"2023-06-15","cited_by_count":11,"area":"mllm"},{"id":"2312.07408","title":"Turbo: Informativity-Driven Acceleration Plug-In for Vision-Language Models","created":"2023-12-12","cited_by_count":11,"area":"mllm"},{"id":"2504.03970","title":"VideoComp: Advancing Fine-Grained Compositional and Temporal Alignment in Video-Text Models","created":"2025-04-04","cited_by_count":11,"area":"mllm"},{"id":"2503.05186","title":"Narrating the Video: Boosting Text-Video Retrieval via Comprehensive Utilization of Frame-Level Captions","created":"2025-03-07","cited_by_count":10,"area":"mllm"},{"id":"2212.04412","title":"Task Bias in Vision-Language Models","created":"2022-12-08","cited_by_count":8,"area":"mllm"},{"id":"2502.18816","title":"Grad-ECLIP: Gradient-based Visual and Textual Explanations for CLIP","created":"2025-02-26","cited_by_count":8,"area":"mllm"},{"id":"2506.18504","title":"Generalizing vision-language models to novel domains: A comprehensive survey","created":"2025-06-23","cited_by_count":7,"area":"mllm"},{"id":"2604.05418","title":"VideoStir: Understanding Long Videos via Spatio-Temporally Structured and Intent-Aware RAG","created":"2026-04-07","cited_by_count":6,"area":"mllm"},{"id":"2309.08928","title":"In-Style: Bridging Text and Uncurated Videos with Style Transfer for Text-Video Retrieval","created":"2023-09-16","cited_by_count":5,"area":"mllm"},{"id":"2310.15324","title":"Videoprompter: an ensemble of foundational models for zero-shot video understanding","created":"2023-10-23","cited_by_count":5,"area":"mllm"},{"id":"2312.00414","title":"Vision-Language Models Learn Super Images for Efficient Partially Relevant Video Retrieval","created":"2023-12-01","cited_by_count":5,"area":"mllm"},{"id":"2407.09073","title":"Open Vocabulary Multi-Label Video Classification","created":"2024-07-12","cited_by_count":5,"area":"mllm"},{"id":"2201.02772","title":"A Comprehensive Empirical Study of Vision-Language Pre-trained Model for Supervised Cross-Modal Retrieval","created":"2022-01-08","cited_by_count":4,"area":"mllm"},{"id":"2312.09507","title":"WAVER: Writing-style Agnostic Text-Video Retrieval via Distilling Vision-Language Models Through Open-Vocabulary Knowledge","created":"2023-12-15","cited_by_count":4,"area":"mllm"},{"id":"2410.17149","title":"Are Visual-Language Models Effective in Action Recognition? A Comparative Study","created":"2024-10-22","cited_by_count":4,"area":"mllm"},{"id":"2507.23284","title":"Bidirectional Likelihood Estimation with Multi-Modal Large Language Models for Text-Video Retrieval","created":"2025-07-31","cited_by_count":4,"area":"mllm"},{"id":"2602.08099","title":"VidVec: Unlocking Video MLLM Embeddings for Video-Text Retrieval","created":"2026-02-08","cited_by_count":4,"area":"mllm"},{"id":"2206.11091","title":"Generalizing Multimodal Pre-training into Multilingual via Language Acquisition","created":"2022-05-29","cited_by_count":3,"area":"mllm"},{"id":"2208.11553","title":"MuMUR : Multilingual Multimodal Universal Retrieval","created":"2022-08-24","cited_by_count":3,"area":"mllm"},{"id":"2307.07341","title":"PiTL: Cross-modal Retrieval with Weakly-supervised Vision-language Pre-training via Prompting","created":"2023-07-14","cited_by_count":3,"area":"mllm"},{"id":"2406.11331","title":"They're All Doctors: Synthesizing Diverse Counterfactuals to Mitigate Associative Bias","created":"2024-06-17","cited_by_count":3,"area":"mllm"},{"id":"2506.10202","title":"Q2E: Query-to-Event Decomposition for Zero-Shot Multilingual Text-to-Video Retrieval","created":"2025-06-11","cited_by_count":3,"area":"mllm"},{"id":"2511.12331","title":"SpaceVLM: Sub-Space Modeling of Negation in Vision-Language Models","created":"2025-11-15","cited_by_count":3,"area":"mllm"},{"id":"2511.12978","title":"Concept Regions Matter: Benchmarking CLIP with a New Cluster-Importance Approach","created":"2025-11-17","cited_by_count":3,"area":"mllm"},{"id":"2512.16925","title":"V-Agent: An Interactive Video Search System Using Vision-Language Models","created":"2025-11-04","cited_by_count":3,"area":"mllm"},{"id":"2305.18786","title":"Scalable Performance Analysis for Vision-Language Models","created":"2023-05-30","cited_by_count":2,"area":"mllm"},{"id":"2503.18407","title":"VTD-CLIP: Video-to-Text Discretization via Prompting CLIP","created":"2025-03-24","cited_by_count":2,"area":"mllm"},{"id":"2504.01890","title":"Is Temporal Prompting All We Need For Limited Labeled Action Recognition?","created":"2025-04-02","cited_by_count":2,"area":"mllm"},{"id":"2506.03589","title":"BiMa: Towards Biases Mitigation for Text-Video Retrieval via Scene Element Guidance","created":"2025-06-04","cited_by_count":2,"area":"mllm"},{"id":"2305.02297","title":"Making the Most of What You Have: Adapting Pre-trained Visual Language Models in the Low-data Regime","created":"2023-05-03","cited_by_count":1,"area":"mllm"},{"id":"2308.10185","title":"ViT-Lens: Initiating Omni-Modal Exploration through 3D Insights","created":"2023-08-20","cited_by_count":1,"area":"mllm"},{"id":"2407.12341","title":"Multimodal LLM-based Query Paraphrasing for Video Search","created":"2024-07-17","cited_by_count":1,"area":"mllm"},{"id":"2505.05681","title":"Fine-Tuning Video-Text Contrastive Model for Primate Behavior Retrieval from Unlabeled Raw Videos","created":"2025-05-08","cited_by_count":1,"area":"mllm"},{"id":"2507.14024","title":"Moodifier: MLLM-Enhanced Emotion-Driven Image Editing","created":"2025-07-18","cited_by_count":1,"area":"mllm"},{"id":"2509.22447","title":"Guiding Evolution of Artificial Life Using Vision-Language Models","created":"2025-09-26","cited_by_count":1,"area":"mllm"},{"id":"2604.26370","title":"Topology-Aware Representation Alignment for Semi-Supervised Vision-Language Learning","created":"2026-04-29","cited_by_count":1,"area":"mllm"},{"id":"2607.23271","title":"What CLIP Knows but Cannot Say: Recovering Negation from Frozen Intermediate Features","created":"2026-07-25","cited_by_count":1,"area":"mllm"},{"id":"2506.15201","title":"Privacy-Shielded Image Compression: Defending Against Exploitation from Vision-Language Pretrained Models","created":"2025-06-18","cited_by_count":0,"area":"mllm"},{"id":"2509.14060","title":"VSE-MOT: Multi-Object Tracking in Low-Quality Video Scenes Guided by Visual Semantic Enhancement","created":"2025-09-17","cited_by_count":0,"area":"mllm"},{"id":"2509.16452","title":"KRAST: Knowledge-Augmented Robotic Action Recognition with Structured Text for Vision-Language Models","created":"2025-09-19","cited_by_count":0,"area":"mllm"},{"id":"2512.00343","title":"Assimilation Matters: Model-level Backdoor Detection in Vision-Language Pretrained Models","created":"2025-11-29","cited_by_count":0,"area":"mllm"},{"id":"2601.04824","title":"SOVABench: A Vehicle Surveillance Action Retrieval Benchmark for Multimodal Large Language Models","created":"2026-01-08","cited_by_count":0,"area":"mllm"},{"id":"2602.06619","title":"CauCLIP: Bridging the Sim-to-Real Gap in Surgical Video Understanding via Causality-Inspired Vision-Language Modeling","created":"2026-02-06","cited_by_count":0,"area":"mllm"},{"id":"2603.25267","title":"EagleNet: Energy-Aware Fine-Grained Relationship Learning Network for Text-Video Retrieval","created":"2026-03-26","cited_by_count":0,"area":"mllm"},{"id":"2604.08337","title":"InstAP: Instance-Aware Vision-Language Pre-Train for Spatial-Temporal Understanding","created":"2026-04-09","cited_by_count":0,"area":"mllm"},{"id":"2606.19062","title":"DREAM: Extending Vision-Language Models with Dual-Objective Encoding for Cross-Modal Retrieval","created":"2026-06-17","cited_by_count":0,"area":"mllm"},{"id":"2608.17203","title":"Expressivity In Multimodal Contrastive Learning","created":"2026-08-17","cited_by_count":0,"area":"mllm"}],"next_cursor":null}