{"total":84,"rows":[{"id":"2204.14198","title":"Flamingo: a Visual Language Model for Few-Shot Learning","created":"2022-04-29","cited_by_count":4386,"area":"mllm"},{"id":"2410.02713","title":"LLaVA-Video: Video Instruction Tuning With Synthetic Data","created":"2024-10-03","cited_by_count":583,"area":"mllm"},{"id":"2302.14115","title":"Vid2Seq: Large-Scale Pretraining of a Visual Language Model for Dense Video Captioning","created":"2023-02-27","cited_by_count":263,"area":"mllm"},{"id":"2403.11481","title":"VideoAgent: A Memory-augmented Multimodal Agent for Video Understanding","created":"2024-03-18","cited_by_count":229,"area":"mllm"},{"id":"2404.05726","title":"MA-LMM: Memory-Augmented Large Multimodal Model for Long-Term Video Understanding","created":"2024-04-08","cited_by_count":229,"area":"mllm"},{"id":"2501.00574","title":"VideoChat-Flash: Hierarchical Compression for Long-Context Video Modeling","created":"2024-12-31","cited_by_count":220,"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":"2402.03681","title":"RL-VLM-F: Reinforcement Learning from Vision Language Foundation Model Feedback","created":"2024-02-06","cited_by_count":156,"area":"mllm"},{"id":"2503.13377","title":"Time-R1: Post-Training Large Vision Language Model for Temporal Video Grounding","created":"2025-03-17","cited_by_count":146,"area":"mllm"},{"id":"2403.19046","title":"LITA: Language Instructed Temporal-Localization Assistant","created":"2024-03-27","cited_by_count":125,"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":"2203.11933","title":"A Prompt Array Keeps the Bias Away: Debiasing Vision-Language Models with Adversarial Learning","created":"2022-03-22","cited_by_count":104,"area":"mllm"},{"id":"2108.09980","title":"TACo: Token-aware Cascade Contrastive Learning for Video-Text Alignment","created":"2021-08-23","cited_by_count":102,"area":"mllm"},{"id":"2510.07077","title":"Vision-Language-Action Models for Robotics: A Review Towards Real-World Applications","created":"2025-10-08","cited_by_count":84,"area":"mllm"},{"id":"2312.06720","title":"Audio-Visual LLM for Video Understanding","created":"2023-12-11","cited_by_count":77,"area":"mllm"},{"id":"2405.16640","title":"A Survey of Multimodal Large Language Model from A Data-centric Perspective","created":"2024-05-26","cited_by_count":75,"area":"mllm"},{"id":"2103.16110","title":"Kaleido-BERT: Vision-Language Pre-training on Fashion Domain","created":"2021-03-30","cited_by_count":67,"area":"mllm"},{"id":"2504.15271","title":"Eagle 2.5: Boosting Long-Context Post-Training for Frontier Vision-Language Models","created":"2025-04-21","cited_by_count":64,"area":"mllm"},{"id":"2301.06309","title":"UATVR: Uncertainty-Adaptive Text-Video Retrieval","created":"2023-01-16","cited_by_count":55,"area":"mllm"},{"id":"2103.08849","title":"Multilingual Multimodal Pre-training for Zero-Shot Cross-Lingual Transfer of Vision-Language Models","created":"2021-03-16","cited_by_count":41,"area":"mllm"},{"id":"2306.04362","title":"Youku-mPLUG: A 10 Million Large-scale Chinese Video-Language Dataset for Pre-training and Benchmarks","created":"2023-06-07","cited_by_count":36,"area":"mllm"},{"id":"2501.02765","title":"Visual Large Language Models for Generalized and Specialized Applications","created":"2025-01-06","cited_by_count":36,"area":"mllm"},{"id":"2512.01989","title":"PAI-Bench: A Comprehensive Benchmark For Physical AI","created":"2025-12-01","cited_by_count":34,"area":"mllm"},{"id":"2204.07441","title":"COTS: Collaborative Two-Stream Vision-Language Pre-Training Model for Cross-Modal Retrieval","created":"2022-04-15","cited_by_count":33,"area":"mllm"},{"id":"2411.15421","title":"OphCLIP: Hierarchical Retrieval-Augmented Learning for Ophthalmic Surgical Video-Language Pretraining","created":"2024-11-23","cited_by_count":29,"area":"mllm"},{"id":"2301.02241","title":"CiT: Curation in Training for Effective Vision-Language Data","created":"2023-01-05","cited_by_count":27,"area":"mllm"},{"id":"2506.19816","title":"CronusVLA: Towards Efficient and Robust Manipulation via Multi-Frame Vision-Language-Action Modeling","created":"2025-06-24","cited_by_count":25,"area":"mllm"},{"id":"2506.05332","title":"Unleashing Hour-Scale Video Training for Long Video-Language Understanding","created":"2025-06-05","cited_by_count":23,"area":"mllm"},{"id":"2404.06332","title":"X-VARS: Introducing Explainability in Football Refereeing with Multi-Modal Large Language Model","created":"2024-04-07","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":"2508.10922","title":"A Survey on Video Temporal Grounding with Multimodal Large Language Model","created":"2025-08-07","cited_by_count":20,"area":"mllm"},{"id":"2412.21080","title":"Vinci: A Real-time Embodied Smart Assistant based on Egocentric Vision-Language Model","created":"2024-12-30","cited_by_count":19,"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":"2401.00849","title":"COSMO: COntrastive Streamlined MultimOdal Model with Interleaved Pre-Training","created":"2024-01-01","cited_by_count":18,"area":"mllm"},{"id":"2407.08101","title":"What to Say and When to Say it: Live Fitness Coaching as a Testbed for Situated Interaction","created":"2024-07-11","cited_by_count":18,"area":"mllm"},{"id":"2306.10159","title":"Vision-Language Models can Identify Distracted Driver Behavior from Naturalistic Videos","created":"2023-06-16","cited_by_count":17,"area":"mllm"},{"id":"2412.17759","title":"Survey of Large Multimodal Model Datasets, Application Categories and Taxonomy","created":"2024-12-23","cited_by_count":17,"area":"mllm"},{"id":"2505.12632","title":"Scalable Video-to-Dataset Generation for Cross-Platform Mobile Agents","created":"2025-05-19","cited_by_count":14,"area":"mllm"},{"id":"2406.10221","title":"Long Story Short: Story-level Video Understanding from 20K Short Films","created":"2024-06-14","cited_by_count":12,"area":"mllm"},{"id":"2510.17023","title":"Enrich and Detect: Video Temporal Grounding with Multimodal LLMs","created":"2025-10-19","cited_by_count":12,"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":"2211.12402","title":"X$^2$-VLM: All-In-One Pre-trained Model For Vision-Language Tasks","created":"2022-11-22","cited_by_count":9,"area":"mllm"},{"id":"2404.03836","title":"PARIS3D: Reasoning-based 3D Part Segmentation Using Large Multimodal Model","created":"2024-04-04","cited_by_count":9,"area":"mllm"},{"id":"2501.00958","title":"2.5 Years in Class: A Multimodal Textbook for Vision-Language Pretraining","created":"2025-01-01","cited_by_count":9,"area":"mllm"},{"id":"2503.04250","title":"An Egocentric Vision-Language Model based Portable Real-time Smart Assistant","created":"2025-03-06","cited_by_count":8,"area":"mllm"},{"id":"2602.08439","title":"Demo-ICL: In-Context Learning for Procedural Video Knowledge Acquisition","created":"2026-02-09","cited_by_count":8,"area":"mllm"},{"id":"2606.09393","title":"CapRL++: Unified Reinforcement Learning with Verifiable Rewards for Dense Image and Video Captioning","created":"2026-06-08","cited_by_count":8,"area":"mllm"},{"id":"2211.16504","title":"Improving Commonsense in Vision-Language Models via Knowledge Graph Riddles","created":"2022-11-29","cited_by_count":7,"area":"mllm"},{"id":"2503.20472","title":"From Trial to Triumph: Advancing Long Video Understanding via Visual Context Sample Scaling and Self-reward Alignment","created":"2025-03-26","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":"2309.15915","title":"Zero-Shot and Few-Shot Video Question Answering with Multi-Modal Prompts","created":"2023-09-27","cited_by_count":5,"area":"mllm"},{"id":"2511.13261","title":"Building Egocentric Procedural AI Assistant: Methods, Benchmarks, and Challenges","created":"2025-11-17","cited_by_count":5,"area":"mllm"},{"id":"2402.12079","title":"LVCHAT: Facilitating Long Video Comprehension","created":"2024-02-19","cited_by_count":4,"area":"mllm"},{"id":"2501.05711","title":"From My View to Yours: Learning Egocentric Cues from Exocentric Video using Privileged Egocentric Supervision","created":"2025-01-10","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":"2509.11862","title":"Bridging Vision Language Models and Symbolic Grounding for Video Question Answering","created":"2025-09-15","cited_by_count":4,"area":"mllm"},{"id":"2511.16595","title":"TimeViper: A Hybrid Mamba-Transformer Vision-Language Model for Efficient Long Video Understanding","created":"2025-11-20","cited_by_count":4,"area":"mllm"},{"id":"2512.24271","title":"Taming Hallucinations: Boosting MLLMs' Video Understanding via Counterfactual Video Generation","created":"2025-12-30","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":"2208.11553","title":"MuMUR : Multilingual Multimodal Universal Retrieval","created":"2022-08-24","cited_by_count":3,"area":"mllm"},{"id":"2310.05060","title":"DeVAn: Dense Video Annotation for Video-Language Models","created":"2023-10-08","cited_by_count":3,"area":"mllm"},{"id":"2607.17423","title":"TimeLens2: Generalist Video Temporal Grounding with Multimodal LLMs","created":"2026-07-19","cited_by_count":3,"area":"mllm"},{"id":"2502.20811","title":"HAIC: Improving Human Action Understanding and Generation with Better Captions for Multi-modal Large Language Models","created":"2025-02-28","cited_by_count":2,"area":"mllm"},{"id":"2506.21586","title":"Can Vision Language Models Understand Mimed Actions?","created":"2025-06-17","cited_by_count":2,"area":"mllm"},{"id":"2509.14227","title":"Cin\\'{e}aste: A Fine-grained Contextual Movie Question Answering Benchmark","created":"2025-09-17","cited_by_count":2,"area":"mllm"},{"id":"2511.09483","title":"CrochetBench: Can Vision-Language Models Move from Describing to Doing in Crochet Domain?","created":"2025-11-12","cited_by_count":2,"area":"mllm"},{"id":"2511.21998","title":"Can Multi-Modal LLMs Provide Live Step-by-Step Task Guidance?","created":"2025-11-27","cited_by_count":2,"area":"mllm"},{"id":"2601.15287","title":"Towards Understanding Best Practices for Quantization of Vision-Language Models","created":"2026-01-21","cited_by_count":2,"area":"mllm"},{"id":"2608.05381","title":"C$^3$PO: Evaluating Cross-Modal Composition and Counterfactual Performance in Omnimodal Models","created":"2026-08-05","cited_by_count":2,"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":"2310.04914","title":"Analyzing Zero-Shot Abilities of Vision-Language Models on Video Understanding Tasks","created":"2023-10-07","cited_by_count":1,"area":"mllm"},{"id":"2411.15628","title":"ACE: Action Concept Enhancement of Video-Language Models in Procedural Videos","created":"2024-11-23","cited_by_count":1,"area":"mllm"},{"id":"2605.05831","title":"Unifying Scientific Communication: Fine-Grained Correspondence Across Scientific Media","created":"2026-05-07","cited_by_count":1,"area":"mllm"},{"id":"2606.31245","title":"HyperVLP: Enhancing Hierarchical Surgical Video-Language Pre-training in Hyperbolic Space","created":"2026-06-30","cited_by_count":1,"area":"mllm"},{"id":"2607.02991","title":"GuideMe: Multi-Domain Task Guidance and Intervention in Streaming Video","created":"2026-07-03","cited_by_count":1,"area":"mllm"},{"id":"2609.22588","title":"Seeing is not Enough: Vision-Language Models Perceive Evidence but Fail to Act","created":"2026-09-18","cited_by_count":1,"area":"mllm"},{"id":"2406.07091","title":"AutoTVG: A New Vision-language Pre-training Paradigm for Temporal Video Grounding","created":"2024-06-11","cited_by_count":0,"area":"mllm"},{"id":"2503.20348","title":"VideoGEM: Training-free Action Grounding in Videos","created":"2025-03-26","cited_by_count":0,"area":"mllm"},{"id":"2509.22019","title":"EgoInstruct: An Egocentric Video Dataset of Face-to-face Instructional Interactions with Multi-modal LLM Benchmarking","created":"2025-09-26","cited_by_count":0,"area":"mllm"},{"id":"2510.09586","title":"Vision Language Models: A Survey of 26K Papers","created":"2025-10-10","cited_by_count":0,"area":"mllm"},{"id":"2510.16989","title":"Training-free Online Video Step Grounding","created":"2025-10-19","cited_by_count":0,"area":"mllm"},{"id":"2512.11399","title":"Minimal Clips, Maximum Salience: Long Video Summarization via Key Moment Extraction","created":"2025-12-12","cited_by_count":0,"area":"mllm"},{"id":"2606.31187","title":"Learning to Deny: Action Denial in Multimodal Large Language Models","created":"2026-06-30","cited_by_count":0,"area":"mllm"},{"id":"2609.02565","title":"MARS: What Retrieval Signals Are Hidden in Multimodal Large Language Models for Text-Video Retrieval?","created":"2026-09-02","cited_by_count":0,"area":"mllm"}],"next_cursor":null}