{"list":"other","total":54,"rows":[{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"2502.13923","title":"Qwen2.5-VL Technical Report","created":"2025-02-19","cited_by_count":5587},{"id":"2409.12191","title":"Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution","created":"2024-09-18","cited_by_count":4234},{"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":"2403.05530","title":"Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context","created":"2024-03-08","cited_by_count":3224},{"id":"2511.21631","title":"Qwen3-VL Technical Report","created":"2025-11-26","cited_by_count":2793},{"id":"2408.01800","title":"MiniCPM-V: A GPT-4V Level MLLM on Your Phone","created":"2024-08-03","cited_by_count":1079},{"id":"2507.18071","title":"Group Sequence Policy Optimization","created":"2025-07-24","cited_by_count":835},{"id":"1705.00754","title":"Dense-Captioning Events in Videos","created":"2017-05-02","cited_by_count":793},{"id":"2503.20215","title":"Qwen2.5-Omni Technical Report","created":"2025-03-26","cited_by_count":736},{"id":"1705.02101","title":"TALL: Temporal Activity Localization via Language Query","created":"2017-05-05","cited_by_count":584},{"id":"2407.10759","title":"Qwen2-Audio Technical Report","created":"2024-07-15","cited_by_count":560},{"id":"2509.17765","title":"Qwen3-Omni Technical Report","created":"2025-09-22","cited_by_count":497},{"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":"2302.14115","title":"Vid2Seq: Large-Scale Pretraining of a Visual Language Model for Dense Video Captioning","created":"2023-02-27","cited_by_count":263},{"id":"2406.14515","title":"MMBench-Video: A Long-Form Multi-Shot Benchmark for Holistic Video Understanding","created":"2024-06-20","cited_by_count":182},{"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":"2410.03051","title":"AuroraCap: Efficient, Performant Video Detailed Captioning and a New Benchmark","created":"2024-10-04","cited_by_count":140},{"id":"2108.07781","title":"End-to-End Dense Video Captioning with Parallel Decoding","created":"2021-08-17","cited_by_count":133},{"id":"2505.17862","title":"Daily-Omni: Towards Audio-Visual Reasoning with Temporal Alignment across Modalities","created":"2025-05-23","cited_by_count":110},{"id":"2410.19702","title":"TimeSuite: Improving MLLMs for Long Video Understanding via Grounded Tuning","created":"2024-10-25","cited_by_count":106},{"id":"2406.15704","title":"video-SALMONN: Speech-Enhanced Audio-Visual Large Language Models","created":"2024-06-22","cited_by_count":102},{"id":"2504.17343","title":"TimeChat-Online: 80% Visual Tokens are Naturally Redundant in Streaming Videos","created":"2025-04-24","cited_by_count":97},{"id":"2511.20347","title":"Soft Adaptive Policy Optimization","created":"2025-11-25","cited_by_count":96},{"id":"2511.22570","title":"DeepSeekMath-V2: Towards Self-Verifiable Mathematical Reasoning","created":"2025-11-27","cited_by_count":94},{"id":"2506.18866","title":"OmniAvatar: Efficient Audio-Driven Avatar Video Generation with Adaptive Body Animation","created":"2025-06-23","cited_by_count":83},{"id":"2501.07888","title":"Tarsier2: Advancing Large Vision-Language Models from Detailed Video Description to Comprehensive Video Understanding","created":"2025-01-14","cited_by_count":81},{"id":"2405.20985","title":"DeCo: Decoupling Token Compression from Semantic Abstraction in Multimodal Large Language Models","created":"2024-05-31","cited_by_count":75},{"id":"2506.09344","title":"Ming-Omni: A Unified Multimodal Model for Perception and Generation","created":"2025-06-11","cited_by_count":66},{"id":"2510.15870","title":"OmniVinci: Enhancing Architecture and Data for Omni-Modal Understanding LLM","created":"2025-10-17","cited_by_count":59},{"id":"2506.21277","title":"HumanOmniV2: From Understanding to Omni-Modal Reasoning with Context","created":"2025-06-26","cited_by_count":55},{"id":"2312.10300","title":"Shot2Story: A New Benchmark for Comprehensive Understanding of Multi-shot Videos","created":"2023-12-16","cited_by_count":54},{"id":"2411.19772","title":"LongVALE: Vision-Audio-Language-Event Benchmark Towards Time-Aware Omni-Modal Perception of Long Videos","created":"2024-11-29","cited_by_count":51},{"id":"2507.20939","title":"ARC-Hunyuan-Video-7B: Structured Video Comprehension of Real-World Shorts","created":"2025-07-28","cited_by_count":41},{"id":"2202.04298","title":"Image Difference Captioning with Pre-training and Contrastive Learning","created":"2022-02-09","cited_by_count":39},{"id":"2410.06166","title":"Temporal Reasoning Transfer from Text to Video","created":"2024-10-08","cited_by_count":38},{"id":"2509.22647","title":"CapRL: Stimulating Dense Image Caption Capabilities via Reinforcement Learning","created":"2025-09-26","cited_by_count":38},{"id":"2503.09146","title":"Generative Frame Sampler for Long Video Understanding","created":"2025-03-12","cited_by_count":37},{"id":"2512.07802","title":"OneStory: Coherent Multi-Shot Video Generation with Adaptive Memory","created":"2025-12-08","cited_by_count":35},{"id":"2506.01725","title":"VideoCap-R1: Enhancing MLLMs for Video Captioning via Structured Thinking","created":"2025-06-02","cited_by_count":30},{"id":"2510.10395","title":"AVoCaDO: An Audiovisual Video Captioner Driven by Temporal Orchestration","created":"2025-10-12","cited_by_count":27},{"id":"2502.11775","title":"video-SALMONN-o1: Reasoning-enhanced Audio-visual Large Language Model","created":"2025-02-17","cited_by_count":24},{"id":"2311.15930","title":"WorldSense: A Synthetic Benchmark for Grounded Reasoning in Large Language Models","created":"2023-11-27","cited_by_count":20},{"id":"2507.11336","title":"UGC-VideoCaptioner: An Omni UGC Video Detail Caption Model and New Benchmarks","created":"2025-07-15","cited_by_count":19},{"id":"2510.20470","title":"Conan: Progressive Learning to Reason Like a Detective over Multi-Scale Visual Evidence","created":"2025-10-23","cited_by_count":18},{"id":"2508.01699","title":"TimeExpert: An Expert-Guided Video LLM for Video Temporal Grounding","created":"2025-08-03","cited_by_count":14},{"id":"2407.20962","title":"MMTrail: A Multimodal Trailer Video Dataset with Language and Music Descriptions","created":"2024-07-30","cited_by_count":13},{"id":"2601.19267","title":"DiaDem: Advancing Dialogue Descriptions in Audiovisual Video Captioning for Multimodal Large Language Models","created":"2026-01-27","cited_by_count":13},{"id":"2508.18634","title":"OwlCap: Harmonizing Motion-Detail for Video Captioning via HMD-270K and Caption Set Equivalence Reward","created":"2025-08-26","cited_by_count":12},{"id":"2404.10763","title":"LaDiC: Are Diffusion Models Really Inferior to Autoregressive Counterparts for Image-to-Text Generation?","created":"2024-04-16","cited_by_count":9},{"id":"2404.13370","title":"Movie101v2: Improved Movie Narration Benchmark","created":"2024-04-20","cited_by_count":9},{"id":"2511.14349","title":"ARC-Chapter: Structuring Hour-Long Videos into Navigable Chapters and Hierarchical Summaries","created":"2025-11-18","cited_by_count":6},{"id":"2505.22613","title":"RICO: Improving Accuracy and Completeness in Image Recaptioning via Visual Reconstruction","created":"2025-05-28","cited_by_count":4},{"id":"1806.09278","title":"Best Vision Technologies Submission to ActivityNet Challenge 2018-Task: Dense-Captioning Events in Videos","created":"2018-06-25","cited_by_count":1}],"next_cursor":null}