{"list":"other","total":52,"rows":[{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"2310.03744","title":"Improved Baselines with Visual Instruction Tuning","created":"2023-10-05","cited_by_count":4418},{"id":"2507.06261","title":"Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities","created":"2025-07-07","cited_by_count":3796},{"id":"2408.00714","title":"SAM 2: Segment Anything in Images and Videos","created":"2024-08-01","cited_by_count":2863},{"id":"2110.07058","title":"Ego4D: Around the World in 3,000 Hours of Egocentric Video","created":"2021-10-13","cited_by_count":1556},{"id":"2508.18265","title":"InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency","created":"2025-08-25","cited_by_count":1510},{"id":"2311.17005","title":"MVBench: A Comprehensive Multi-modal Video Understanding Benchmark","created":"2023-11-28","cited_by_count":1109},{"id":"1704.00675","title":"The 2017 DAVIS Challenge on Video Object Segmentation","created":"2017-04-03","cited_by_count":957},{"id":"2511.16719","title":"SAM 3: Segment Anything with Concepts","created":"2025-11-20","cited_by_count":906},{"id":"2105.08276","title":"NExT-QA:Next Phase of Question-Answering to Explaining Temporal Actions","created":"2021-05-18","cited_by_count":744},{"id":"2501.13106","title":"VideoLLaMA 3: Frontier Multimodal Foundation Models for Image and Video Understanding","created":"2025-01-22","cited_by_count":518},{"id":"1910.01442","title":"CLEVRER: CoLlision Events for Video REpresentation and Reasoning","created":"2019-10-03","cited_by_count":484},{"id":"2503.21776","title":"Video-R1: Reinforcing Video Reasoning in MLLMs","created":"2025-03-27","cited_by_count":484},{"id":"2305.13786","title":"Perception Test: A Diagnostic Benchmark for Multimodal Video Models","created":"2023-05-23","cited_by_count":314},{"id":"2311.18445","title":"VTimeLLM: Empower LLM to Grasp Video Moments","created":"2023-11-30","cited_by_count":255},{"id":"2504.06958","title":"VideoChat-R1: Enhancing Spatio-Temporal Perception via Reinforcement Fine-Tuning","created":"2025-04-09","cited_by_count":255},{"id":"2509.23661","title":"LLaVA-OneVision-1.5: Fully Open Framework for Democratized Multimodal Training","created":"2025-09-28","cited_by_count":244},{"id":"2308.08544","title":"MeViS: A Large-scale Benchmark for Video Segmentation with Motion Expressions","created":"2023-08-16","cited_by_count":228},{"id":"2405.09711","title":"STAR: A Benchmark for Situated Reasoning in Real-World Videos","created":"2024-05-15","cited_by_count":213},{"id":"1904.11574","title":"TVQA+: Spatio-Temporal Grounding for Video Question Answering","created":"2019-04-25","cited_by_count":154},{"id":"2503.13377","title":"Time-R1: Post-Training Large Vision Language Model for Temporal Video Grounding","created":"2025-03-17","cited_by_count":146},{"id":"2309.01327","title":"Can I Trust Your Answer? Visually Grounded Video Question Answering","created":"2023-09-04","cited_by_count":135},{"id":"2407.11325","title":"VISA: Reasoning Video Object Segmentation via Large Language Models","created":"2024-07-16","cited_by_count":127},{"id":"2402.11435","title":"Momentor: Advancing Video Large Language Model with Fine-Grained Temporal Reasoning","created":"2024-02-18","cited_by_count":122},{"id":"2406.09418","title":"VideoGPT+: Integrating Image and Video Encoders for Enhanced Video Understanding","created":"2024-06-13","cited_by_count":115},{"id":"2409.19603","title":"One Token to Seg Them All: Language Instructed Reasoning Segmentation in Videos","created":"2024-09-29","cited_by_count":100},{"id":"2405.13382","title":"VTG-LLM: Integrating Timestamp Knowledge into Video LLMs for Enhanced Video Temporal Grounding","created":"2024-05-22","cited_by_count":85},{"id":"2412.12075","title":"CG-Bench: Clue-grounded Question Answering Benchmark for Long Video Understanding","created":"2024-12-16","cited_by_count":85},{"id":"2506.11991","title":"VGR: Visual Grounded Reasoning","created":"2025-06-13","cited_by_count":73},{"id":"2501.00599","title":"VideoRefer Suite: Advancing Spatial-Temporal Object Understanding with Video LLM","created":"2024-12-31","cited_by_count":72},{"id":"2503.11495","title":"V-STaR: Benchmarking Video-LLMs on Video Spatio-Temporal Reasoning","created":"2025-03-14","cited_by_count":68},{"id":"2411.10332","title":"Number it: Temporal Grounding Videos like Flipping Manga","created":"2024-11-15","cited_by_count":65},{"id":"2411.14794","title":"VideoEspresso: A Large-Scale Chain-of-Thought Dataset for Fine-Grained Video Reasoning via Core Frame Selection","created":"2024-11-22","cited_by_count":65},{"id":"2411.04923","title":"VideoGLaMM: A Large Multimodal Model for Pixel-Level Visual Grounding in Videos","created":"2024-11-07","cited_by_count":51},{"id":"2510.20579","title":"Open-o3-Video: Grounded Video Reasoning with Explicit Spatio-Temporal Evidence","created":"2025-10-23","cited_by_count":49},{"id":"2304.01715","title":"Towards Open-Vocabulary Video Instance Segmentation","created":"2023-04-04","cited_by_count":45},{"id":"2506.22624","title":"Seg-R1: Segmentation Can Be Surprisingly Simple with Reinforcement Learning","created":"2025-06-27","cited_by_count":44},{"id":"2504.07962","title":"GLUS: Global-Local Reasoning Unified into A Single Large Language Model for Video Segmentation","created":"2025-04-10","cited_by_count":34},{"id":"2507.06485","title":"Video-RTS: Rethinking Reinforcement Learning and Test-Time Scaling for Efficient and Enhanced Video Reasoning","created":"2025-07-09","cited_by_count":33},{"id":"2509.18094","title":"UniPixel: Unified Object Referring and Segmentation for Pixel-Level Visual Reasoning","created":"2025-09-22","cited_by_count":28},{"id":"2307.12058","title":"Discovering Spatio-Temporal Rationales for Video Question Answering","created":"2023-07-22","cited_by_count":21},{"id":"2411.09921","title":"Motion-Grounded Video Reasoning: Understanding and Perceiving Motion at Pixel Level","created":"2024-11-15","cited_by_count":19},{"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},{"id":"2508.11538","title":"Reinforcing Video Reasoning Segmentation to Think Before It Segments","created":"2025-08-15","cited_by_count":15},{"id":"2506.05336","title":"VideoMolmo: Spatio-Temporal Grounding Meets Pointing","created":"2025-06-05","cited_by_count":14},{"id":"2508.00518","title":"Fine-grained Spatiotemporal Grounding on Egocentric Videos","created":"2025-08-01","cited_by_count":11},{"id":"2505.18812","title":"SAMA: Towards Multi-Turn Referential Grounded Video Chat with Large Language Models","created":"2025-05-24","cited_by_count":8},{"id":"2506.02356","title":"InterRVOS: Interaction-aware Referring Video Object Segmentation","created":"2025-06-03","cited_by_count":6},{"id":"2509.03501","title":"Strefer: Empowering Video LLMs with Space-Time Referring and Reasoning via Synthetic Instruction Data","created":"2025-09-03","cited_by_count":6},{"id":"2503.12855","title":"VITED: Video Temporal Evidence Distillation","created":"2025-03-17","cited_by_count":5},{"id":"2401.03901","title":"STAIR: Spatial-Temporal Reasoning with Auditable Intermediate Results for Video Question Answering","created":"2024-01-08","cited_by_count":3}],"next_cursor":null}