{"list":"other","total":59,"rows":[{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"2502.13923","title":"Qwen2.5-VL Technical Report","created":"2025-02-19","cited_by_count":5587},{"id":"2410.21276","title":"GPT-4o System Card","created":"2024-10-25","cited_by_count":4588},{"id":"2303.05499","title":"Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection","created":"2023-03-09","cited_by_count":3332},{"id":"2408.00714","title":"SAM 2: Segment Anything in Images and Videos","created":"2024-08-01","cited_by_count":2863},{"id":"2412.05271","title":"Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling","created":"2024-12-06","cited_by_count":1599},{"id":"2110.07058","title":"Ego4D: Around the World in 3,000 Hours of Egocentric Video","created":"2021-10-13","cited_by_count":1556},{"id":"2306.02858","title":"Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding","created":"2023-06-05","cited_by_count":1471},{"id":"2601.03267","title":"OpenAI GPT-5 System Card","created":"2025-12-19","cited_by_count":989},{"id":"1804.02748","title":"Scaling Egocentric Vision: The EPIC-KITCHENS Dataset","created":"2018-04-08","cited_by_count":795},{"id":"2407.15754","title":"LongVideoBench: A Benchmark for Long-context Interleaved Video-Language Understanding","created":"2024-07-22","cited_by_count":665},{"id":"2412.13663","title":"Smarter, Better, Faster, Longer: A Modern Bidirectional Encoder for Fast, Memory Efficient, and Long Context Finetuning and Inference","created":"2024-12-18","cited_by_count":554},{"id":"2311.17043","title":"LLaMA-VID: An Image is Worth 2 Tokens in Large Language Models","created":"2023-11-28","cited_by_count":546},{"id":"2406.16852","title":"Long Context Transfer from Language to Vision","created":"2024-06-24","cited_by_count":515},{"id":"2312.02051","title":"TimeChat: A Time-sensitive Multimodal Large Language Model for Long Video Understanding","created":"2023-12-04","cited_by_count":406},{"id":"2410.17434","title":"LongVU: Spatiotemporal Adaptive Compression for Long Video-Language Understanding","created":"2024-10-22","cited_by_count":356},{"id":"2311.18445","title":"VTimeLLM: Empower LLM to Grasp Video Moments","created":"2023-11-30","cited_by_count":255},{"id":"2405.19209","title":"VideoTree: Adaptive Tree-based Video Representation for LLM Reasoning on Long Videos","created":"2024-05-29","cited_by_count":251},{"id":"2404.05726","title":"MA-LMM: Memory-Augmented Large Multimodal Model for Long-Term Video Understanding","created":"2024-04-08","cited_by_count":229},{"id":"2501.00574","title":"VideoChat-Flash: Hierarchical Compression for Long-Context Video Modeling","created":"2024-12-31","cited_by_count":220},{"id":"2201.02639","title":"MERLOT Reserve: Neural Script Knowledge through Vision and Language and Sound","created":"2022-01-07","cited_by_count":184},{"id":"2306.11290","title":"Habitat Synthetic Scenes Dataset (HSSD-200): An Analysis of 3D Scene Scale and Realism Tradeoffs for ObjectGoal Navigation","created":"2023-06-20","cited_by_count":167},{"id":"2502.21271","title":"Adaptive Keyframe Sampling for Long Video Understanding","created":"2025-02-28","cited_by_count":167},{"id":"2411.04998","title":"HourVideo: 1-Hour Video-Language Understanding","created":"2024-11-07","cited_by_count":113},{"id":"2508.09736","title":"Seeing, Listening, Remembering, and Reasoning: A Multimodal Agent with Long-Term Memory","created":"2025-08-13","cited_by_count":97},{"id":"2404.06609","title":"GOAT-Bench: A Benchmark for Multi-Modal Lifelong Navigation","created":"2024-04-09","cited_by_count":94},{"id":"2506.22139","title":"Q-Frame: Query-aware Frame Selection and Multi-Resolution Adaptation for Video-LLMs","created":"2025-06-27","cited_by_count":80},{"id":"2411.17735","title":"3D-Mem: 3D Scene Memory for Embodied Exploration and Reasoning","created":"2024-11-23","cited_by_count":75},{"id":"2406.09396","title":"Too Many Frames, Not All Useful: Efficient Strategies for Long-Form Video QA","created":"2024-06-13","cited_by_count":68},{"id":"2409.13682","title":"ReMEmbR: Building and Reasoning Over Long-Horizon Spatio-Temporal Memory for Robot Navigation","created":"2024-09-20","cited_by_count":67},{"id":"2508.15717","title":"StreamMem: Query-Agnostic KV Cache Memory for Streaming Video Understanding","created":"2025-08-21","cited_by_count":58},{"id":"2501.11858","title":"EmbodiedEval: Evaluate Multimodal LLMs as Embodied Agents","created":"2025-01-21","cited_by_count":57},{"id":"2312.03391","title":"Action Scene Graphs for Long-Form Understanding of Egocentric Videos","created":"2023-12-06","cited_by_count":51},{"id":"2312.05269","title":"LifelongMemory: Leveraging LLMs for Answering Queries in Long-form Egocentric Videos","created":"2023-12-07","cited_by_count":51},{"id":"2408.14469","title":"Grounded Multi-Hop VideoQA in Long-Form Egocentric Videos","created":"2024-08-26","cited_by_count":45},{"id":"2409.18313","title":"Embodied-RAG: General Non-parametric Embodied Memory for Retrieval and Generation","created":"2024-09-26","cited_by_count":44},{"id":"2412.03248","title":"AIM: Adaptive Inference of Multi-Modal LLMs via Token Merging and Pruning","created":"2024-12-04","cited_by_count":43},{"id":"2503.09146","title":"Generative Frame Sampler for Long Video Understanding","created":"2025-03-12","cited_by_count":37},{"id":"2510.27280","title":"FOCUS: Efficient Keyframe Selection for Long Video Understanding","created":"2025-10-31","cited_by_count":37},{"id":"2503.13139","title":"Logic-in-Frames: Dynamic Keyframe Search via Visual Semantic-Logical Verification for Long Video Understanding","created":"2025-03-17","cited_by_count":34},{"id":"2507.13353","title":"VideoITG: Multimodal Video Understanding with Instructed Temporal Grounding","created":"2025-07-17","cited_by_count":29},{"id":"2508.04369","title":"TSPO: Temporal Sampling Policy Optimization for Long-form Video Language Understanding","created":"2025-08-06","cited_by_count":25},{"id":"2501.00358","title":"Embodied VideoAgent: Persistent Memory from Egocentric Videos and Embodied Sensors Enables Dynamic Scene Understanding","created":"2024-12-31","cited_by_count":24},{"id":"2412.00161","title":"STEP: Enhancing Video-LLMs' Compositional Reasoning by Spatio-Temporal Graph-guided Self-Training","created":"2024-11-29","cited_by_count":22},{"id":"2411.18042","title":"HyperGLM: HyperGraph for Video Scene Graph Generation and Anticipation","created":"2024-11-27","cited_by_count":19},{"id":"2502.03183","title":"MaxInfo: A Training-Free Key-Frame Selection Method Using Maximum Volume for Enhanced Video Understanding","created":"2025-02-05","cited_by_count":18},{"id":"2509.16087","title":"See&Trek: Training-Free Spatial Prompting for Multimodal Large Language Model","created":"2025-09-19","cited_by_count":15},{"id":"2501.05037","title":"LongViTU: Instruction Tuning for Long-Form Video Understanding","created":"2025-01-09","cited_by_count":13},{"id":"2503.16032","title":"Agentic Keyframe Search for Video Question Answering","created":"2025-03-20","cited_by_count":13},{"id":"2506.15635","title":"FindingDory: A Benchmark to Evaluate Memory in Embodied Agents","created":"2025-06-18","cited_by_count":12},{"id":"2505.15447","title":"ViaRL: Adaptive Temporal Grounding via Visual Iterated Amplification Reinforcement Learning","created":"2025-05-21","cited_by_count":11},{"id":"2509.09263","title":"DATE: Dynamic Absolute Time Enhancement for Long Video Understanding","created":"2025-09-11","cited_by_count":9},{"id":"2409.00304","title":"StimuVAR: Spatiotemporal Stimuli-aware Video Affective Reasoning with Multimodal Large Language Models","created":"2024-08-31","cited_by_count":8},{"id":"2509.23724","title":"Video Panels for Long Video Understanding","created":"2025-09-28","cited_by_count":6},{"id":"2504.15380","title":"Plug-and-Play Versatile Compressed Video Enhancement","created":"2025-04-21","cited_by_count":5},{"id":"2404.18935","title":"What's in the Flow? Exploiting Temporal Motion Cues for Unsupervised Generic Event Boundary Detection","created":"2024-02-15","cited_by_count":4},{"id":"2505.03581","title":"DyGEnc: Encoding a Sequence of Textual Scene Graphs to Reason and Answer Questions in Dynamic Scenes","created":"2025-05-06","cited_by_count":4},{"id":"2511.17945","title":"Test-Time Temporal Sampling for Efficient MLLM Video Understanding","created":"2025-11-22","cited_by_count":3}],"next_cursor":null}