{"total":75,"rows":[{"id":"2410.02713","title":"LLaVA-Video: Video Instruction Tuning With Synthetic Data","created":"2024-10-03","cited_by_count":583,"area":"mllm"},{"id":"2410.17434","title":"LongVU: Spatiotemporal Adaptive Compression for Long Video-Language Understanding","created":"2024-10-22","cited_by_count":356,"area":"mllm"},{"id":"2404.16994","title":"PLLaVA : Parameter-free LLaVA Extension from Images to Videos for Video Dense Captioning","created":"2024-04-25","cited_by_count":322,"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":"2501.12386","title":"InternVideo2.5: Empowering Video MLLMs with Long and Rich Context Modeling","created":"2025-01-21","cited_by_count":211,"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":"2601.10611","title":"Molmo2: Open Weights and Data for Vision-Language Models with Video Understanding and Grounding","created":"2026-01-15","cited_by_count":139,"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":"2406.09418","title":"VideoGPT+: Integrating Image and Video Encoders for Enhanced Video Understanding","created":"2024-06-13","cited_by_count":115,"area":"mllm"},{"id":"2402.03161","title":"Video-LaVIT: Unified Video-Language Pre-training with Decoupled Visual-Motional Tokenization","created":"2024-02-05","cited_by_count":100,"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":"2512.10942","title":"VL-JEPA: Joint Embedding Predictive Architecture for Vision-language","created":"2025-12-11","cited_by_count":68,"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":"2408.02718","title":"MMIU: Multimodal Multi-image Understanding for Evaluating Large Vision-Language Models","created":"2024-08-05","cited_by_count":67,"area":"mllm"},{"id":"2303.14465","title":"Equivariant Similarity for Vision-Language Foundation Models","created":"2023-03-25","cited_by_count":52,"area":"mllm"},{"id":"2111.14745","title":"A Simple Long-Tailed Recognition Baseline via Vision-Language Model","created":"2021-11-29","cited_by_count":49,"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":"2412.02611","title":"AV-Odyssey Bench: Can Your Multimodal LLMs Really Understand Audio-Visual Information?","created":"2024-12-03","cited_by_count":47,"area":"mllm"},{"id":"2311.14906","title":"AutoEval-Video: An Automatic Benchmark for Assessing Large Vision Language Models in Open-Ended Video Question Answering","created":"2023-11-25","cited_by_count":40,"area":"mllm"},{"id":"2503.10437","title":"4D LangSplat: 4D Language Gaussian Splatting via Multimodal Large Language Models","created":"2025-03-13","cited_by_count":35,"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":"2407.04603","title":"AWT: Transferring Vision-Language Models via Augmentation, Weighting, and Transportation","created":"2024-07-05","cited_by_count":28,"area":"mllm"},{"id":"2503.14935","title":"FAVOR-Bench: A Comprehensive Benchmark for Fine-Grained Video Motion Understanding","created":"2025-03-19","cited_by_count":24,"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":"2412.09754","title":"ViCaS: A Dataset for Combining Holistic and Pixel-level Video Understanding using Captions with Grounded Segmentation","created":"2024-12-12","cited_by_count":17,"area":"mllm"},{"id":"2408.06158","title":"OmniCLIP: Adapting CLIP for Video Recognition with Spatial-Temporal Omni-Scale Feature Learning","created":"2024-08-12","cited_by_count":14,"area":"mllm"},{"id":"2506.09079","title":"VidBridge-R1: Bridging QA and Captioning for RL-based Video Understanding Models with Intermediate Proxy Tasks","created":"2025-06-10","cited_by_count":14,"area":"mllm"},{"id":"2410.00982","title":"ScVLM: Enhancing Vision-Language Model for Safety-Critical Event Understanding","created":"2024-10-01","cited_by_count":13,"area":"mllm"},{"id":"2303.09756","title":"Video Action Recognition with Attentive Semantic Units","created":"2023-03-17","cited_by_count":12,"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":"2306.09085","title":"COSA: Concatenated Sample Pretrained Vision-Language Foundation Model","created":"2023-06-15","cited_by_count":11,"area":"mllm"},{"id":"2401.11649","title":"M2-CLIP: A Multimodal, Multi-task Adapting Framework for Video Action Recognition","created":"2024-01-22","cited_by_count":11,"area":"mllm"},{"id":"2503.22610","title":"Evaluating Multimodal Language Models as Visual Assistants for Visually Impaired Users","created":"2025-03-28","cited_by_count":11,"area":"mllm"},{"id":"2408.05775","title":"Efficient Test-Time Prompt Tuning for Vision-Language Models","created":"2024-08-11","cited_by_count":10,"area":"mllm"},{"id":"2510.13251","title":"Map the Flow: Revealing Hidden Pathways of Information in VideoLLMs","created":"2025-10-15","cited_by_count":10,"area":"mllm"},{"id":"2401.10039","title":"GPT4Ego: Unleashing the Potential of Pre-trained Models for Zero-Shot Egocentric Action Recognition","created":"2024-01-18","cited_by_count":8,"area":"mllm"},{"id":"2404.14890","title":"DENOISER: Rethinking the Robustness for Open-Vocabulary Action Recognition","created":"2024-04-23","cited_by_count":8,"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":"2505.18812","title":"SAMA: Towards Multi-Turn Referential Grounded Video Chat with Large Language Models","created":"2025-05-24","cited_by_count":8,"area":"mllm"},{"id":"2507.06973","title":"Free on the Fly: Enhancing Flexibility in Test-Time Adaptation with Online EM","created":"2025-07-09","cited_by_count":8,"area":"mllm"},{"id":"2502.15809","title":"Black Sheep in the Herd: Playing with Spuriously Correlated Attributes for Vision-Language Recognition","created":"2025-02-19","cited_by_count":7,"area":"mllm"},{"id":"2403.19811","title":"X-MIC: Cross-Modal Instance Conditioning for Egocentric Action Generalization","created":"2024-03-28","cited_by_count":6,"area":"mllm"},{"id":"2408.16412","title":"Text-Enhanced Zero-Shot Action Recognition: A training-free approach","created":"2024-08-29","cited_by_count":6,"area":"mllm"},{"id":"2510.15963","title":"ESCA: Contextualizing Embodied Agents via Scene-Graph Generation","created":"2025-10-11","cited_by_count":6,"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":"2404.08937","title":"ChimpVLM: Ethogram-Enhanced Chimpanzee Behaviour Recognition","created":"2024-04-13","cited_by_count":5,"area":"mllm"},{"id":"2412.12833","title":"FocusChat: Text-guided Long Video Understanding via Spatiotemporal Information Filtering","created":"2024-12-17","cited_by_count":5,"area":"mllm"},{"id":"2603.00490","title":"LifeEval: A Multimodal Benchmark for Assistive AI in Egocentric Daily Life Tasks","created":"2026-02-28","cited_by_count":5,"area":"mllm"},{"id":"2604.14149","title":"One Token per Highly Selective Frame: Towards Extreme Compression for Long Video Understanding","created":"2026-04-15","cited_by_count":5,"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":"2412.01558","title":"VideoLights: Feature Refinement and Cross-Task Alignment Transformer for Joint Video Highlight Detection and Moment Retrieval","created":"2024-12-02","cited_by_count":3,"area":"mllm"},{"id":"2503.09445","title":"Astrea: A MOE-based Visual Understanding Model with Progressive Alignment","created":"2025-03-12","cited_by_count":3,"area":"mllm"},{"id":"2503.18712","title":"LLaVAction: evaluating and training multi-modal large language models for action understanding","created":"2025-03-24","cited_by_count":3,"area":"mllm"},{"id":"2504.16936","title":"Multifaceted Evaluation of Audio-Visual Capability for MLLMs: Effectiveness, Efficiency, Generalizability and Robustness","created":"2025-04-03","cited_by_count":3,"area":"mllm"},{"id":"2505.18855","title":"Inference Compute-Optimal Video Vision Language Models","created":"2025-05-24","cited_by_count":3,"area":"mllm"},{"id":"2508.06092","title":"Q-CLIP: Unleashing the Power of Vision-Language Models for Video Quality Assessment through Unified Cross-Modal Adaptation","created":"2025-08-08","cited_by_count":3,"area":"mllm"},{"id":"2312.03936","title":"The Potential of Vision-Language Models for Content Moderation of Children's Videos","created":"2023-12-06","cited_by_count":2,"area":"mllm"},{"id":"2504.11669","title":"Co-STAR: Collaborative Curriculum Self-Training with Adaptive Regularization for Source-Free Video Domain Adaptation","created":"2025-04-15","cited_by_count":2,"area":"mllm"},{"id":"2505.12728","title":"SpecFLASH: A Latent-Guided Semi-autoregressive Speculative Decoding Framework for Efficient Multimodal Generation","created":"2025-05-19","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":"2601.05495","title":"MMViR: A Multi-Modal and Multi-Granularity Representation for Long-range Video Understanding","created":"2026-01-09","cited_by_count":2,"area":"mllm"},{"id":"2603.06467","title":"GreenRFM: Learning a resource-efficient radiology vision-language foundation model via supervision-centric pre-training","created":"2026-03-06","cited_by_count":2,"area":"mllm"},{"id":"2510.27255","title":"Enhancing Spatio-Temporal Zero-shot Action Recognition with Language-driven Description Attributes","created":"2025-10-31","cited_by_count":1,"area":"mllm"},{"id":"2512.09907","title":"VisualActBench: Can VLMs See and Act like a Human?","created":"2025-12-10","cited_by_count":1,"area":"mllm"},{"id":"2512.17574","title":"Enabling Disaggregated Multi-Stage MLLM Inference via GPU-Internal Scheduling and Resource Sharing","created":"2025-12-19","cited_by_count":1,"area":"mllm"},{"id":"2601.21078","title":"Towards Mitigating Modality Bias in Vision-Language Models for Temporal Action Localization","created":"2026-01-28","cited_by_count":1,"area":"mllm"},{"id":"2605.09422","title":"Perception Without Engagement: Dissecting the Causal Discovery Deficit in LMMs","created":"2026-05-10","cited_by_count":1,"area":"mllm"},{"id":"2607.05264","title":"SteelBench: Evaluating Vision-Language Models in Real-World Industrial Environments","created":"2026-07-06","cited_by_count":1,"area":"mllm"},{"id":"2608.17402","title":"MoE-ViE: Mixture of Experts Vision Encoder for Efficient Image and Video Understanding","created":"2026-08-18","cited_by_count":1,"area":"mllm"},{"id":"2608.21430","title":"Evaluating Multimodal Narrative Understanding of Popular Hollywood Films","created":"2026-08-17","cited_by_count":1,"area":"mllm"},{"id":"2408.10688","title":"TDS-CLIP: Temporal Difference Side Network for Efficient VideoAction Recognition","created":"2024-08-20","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":"2511.22125","title":"GA2-CLIP: Generic Attribute Anchor for Efficient Prompt Tuningin Video-Language Models","created":"2025-11-27","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":"2607.01086","title":"LongVQUBench: Benchmarking Long-Term Video Quality Understanding of Vision-Language Models","created":"2026-07-01","cited_by_count":0,"area":"mllm"}],"next_cursor":null}