{"total":41,"rows":[{"id":"2408.03326","title":"LLaVA-OneVision: Easy Visual Task Transfer","created":"2024-08-06","cited_by_count":2719,"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":"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":"2408.15542","title":"Kangaroo: A Powerful Video-Language Model Supporting Long-context Video Input","created":"2024-08-28","cited_by_count":134,"area":"mllm"},{"id":"2403.19046","title":"LITA: Language Instructed Temporal-Localization Assistant","created":"2024-03-27","cited_by_count":125,"area":"mllm"},{"id":"2311.17092","title":"SEED-Bench-2: Benchmarking Multimodal Large Language Models","created":"2023-11-28","cited_by_count":97,"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":"2503.18478","title":"Video-XL-Pro: Reconstructive Token Compression for Extremely Long Video Understanding","created":"2025-03-24","cited_by_count":49,"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":"2506.18883","title":"Universal Video Temporal Grounding with Generative Multi-modal Large Language Models","created":"2025-06-23","cited_by_count":27,"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":"2309.00661","title":"Zero-Shot Video Moment Retrieval from Frozen Vision-Language Models","created":"2023-09-01","cited_by_count":22,"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":"2503.16036","title":"Hybrid-Level Instruction Injection for Video Token Compression in Multi-modal Large Language Models","created":"2025-03-20","cited_by_count":19,"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":"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":"2506.01674","title":"MotionSight: Boosting Fine-Grained Motion Understanding in Multimodal LLMs","created":"2025-06-02","cited_by_count":11,"area":"mllm"},{"id":"2501.05067","title":"LLaVA-Octopus: Unlocking Instruction-Driven Adaptive Projector Fusion for Video Understanding","created":"2025-01-09","cited_by_count":10,"area":"mllm"},{"id":"2406.13719","title":"GUI Action Narrator: Where and When Did That Action Take Place?","created":"2024-06-19","cited_by_count":9,"area":"mllm"},{"id":"2511.07049","title":"From Pretrain to Pain: Adversarial Vulnerability of Video Foundation Models Without Task Knowledge","created":"2025-11-10","cited_by_count":9,"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":"2508.00399","title":"iSafetyBench: A video-language benchmark for safety in industrial environment","created":"2025-08-01","cited_by_count":5,"area":"mllm"},{"id":"2312.02483","title":"EtC: Temporal Boundary Expand then Clarify for Weakly Supervised Video Grounding with Multimodal Large Language Model","created":"2023-12-05","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":"2503.22577","title":"Breaking Language Barriers in Visual Language Models via Multilingual Textual Regularization","created":"2025-03-28","cited_by_count":4,"area":"mllm"},{"id":"2507.01643","title":"SAILViT: Towards Robust and Generalizable Visual Backbones for MLLMs via Gradual Feature Refinement","created":"2025-07-02","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":"2407.06157","title":"Temporal Grounding of Activities using Multimodal Large Language Models","created":"2024-05-30","cited_by_count":3,"area":"mllm"},{"id":"2511.18929","title":"Human-Centric Open-Future Task Discovery: Formulation, Benchmark, and Scalable Tree-Based Search","created":"2025-11-24","cited_by_count":3,"area":"mllm"},{"id":"2506.21586","title":"Can Vision Language Models Understand Mimed Actions?","created":"2025-06-17","cited_by_count":2,"area":"mllm"},{"id":"2511.10615","title":"Towards Blind and Low-Vision Accessibility of Lightweight VLMs and Custom LLM-Evals","created":"2025-11-13","cited_by_count":2,"area":"mllm"},{"id":"2605.17070","title":"EPIC-Bench: A Perception-Centric Benchmark for Fine-Grained Embodied Visual Grounding in Vision-Language Models","created":"2026-05-16","cited_by_count":1,"area":"mllm"},{"id":"2606.05758","title":"DRIFT: A Residual Flow Adapter for Decoding Continuous Outputs in Vision-Language Models","created":"2026-06-04","cited_by_count":1,"area":"mllm"},{"id":"2511.18685","title":"Beyond Description: Cognitively Benchmarking Fine-Grained Action for Embodied Agents","created":"2025-11-24","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":"2607.04559","title":"QSVideo: Query-Conditioned Semantic Temporal Retrieval for Video Understanding","created":"2026-07-06","cited_by_count":0,"area":"mllm"},{"id":"2608.06756","title":"Capek 0.5: An Execution-Centric Vision-Language Model for Embodied Intelligence","created":"2026-08-07","cited_by_count":0,"area":"mllm"},{"id":"2609.04550","title":"VISTA: Dense Multi-Label Classroom Coding with Vision-Language Models","created":"2026-09-03","cited_by_count":0,"area":"mllm"},{"id":"2609.27327","title":"Can Vision-Language Models Analyze Human-Centered Video? Mapping Model Capabilities and Human-AI Collaborative Workflows","created":"2026-09-23","cited_by_count":0,"area":"mllm"},{"id":"2609.28757","title":"Small yet Assistive: Spatially-Aware Post-Training for Low Vision","created":"2026-09-23","cited_by_count":0,"area":"mllm"}],"next_cursor":null}