{"list":"other","total":52,"rows":[{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"1904.09675","title":"BERTScore: Evaluating Text Generation with BERT","created":"2019-04-21","cited_by_count":5512},{"id":"2410.21276","title":"GPT-4o System Card","created":"2024-10-25","cited_by_count":4588},{"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":"2212.04356","title":"Robust Speech Recognition via Large-Scale Weak Supervision","created":"2022-12-06","cited_by_count":4057},{"id":"2303.15343","title":"Sigmoid Loss for Language Image Pre-Training","created":"2023-03-27","cited_by_count":3109},{"id":"2307.15818","title":"RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control","created":"2023-07-28","cited_by_count":3080},{"id":"2305.06500","title":"InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning","created":"2023-05-11","cited_by_count":2876},{"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":"2311.10122","title":"Video-LLaVA: Learning United Visual Representation by Alignment Before Projection","created":"2023-11-16","cited_by_count":1402},{"id":"1910.02054","title":"ZeRO: Memory Optimizations Toward Training Trillion Parameter Models","created":"2019-10-04","cited_by_count":1301},{"id":"2311.17005","title":"MVBench: A Comprehensive Multi-modal Video Understanding Benchmark","created":"2023-11-28","cited_by_count":1109},{"id":"1706.04261","title":"The \"something something\" video database for learning and evaluating visual common sense","created":"2017-06-13","cited_by_count":1103},{"id":"2306.05424","title":"Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language Models","created":"2023-06-08","cited_by_count":1062},{"id":"2406.07476","title":"VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMs","created":"2024-06-11","cited_by_count":771},{"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":"1809.01696","title":"TVQA: Localized, Compositional Video Question Answering","created":"2018-09-05","cited_by_count":467},{"id":"2406.08035","title":"LVBench: An Extreme Long Video Understanding Benchmark","created":"2024-06-12","cited_by_count":410},{"id":"2210.03094","title":"VIMA: General Robot Manipulation with Multimodal Prompts","created":"2022-10-06","cited_by_count":407},{"id":"2212.09058","title":"BEATs: Audio Pre-Training with Acoustic Tokenizers","created":"2022-12-18","cited_by_count":388},{"id":"2311.08046","title":"Chat-UniVi: Unified Visual Representation Empowers Large Language Models with Image and Video Understanding","created":"2023-11-14","cited_by_count":371},{"id":"2310.01852","title":"LanguageBind: Extending Video-Language Pretraining to N-modality by Language-based Semantic Alignment","created":"2023-10-03","cited_by_count":370},{"id":"2403.00476","title":"TempCompass: Do Video LLMs Really Understand Videos?","created":"2024-03-01","cited_by_count":363},{"id":"2005.00200","title":"HERO: Hierarchical Encoder for Video+Language Omni-representation Pre-training","created":"2020-05-01","cited_by_count":362},{"id":"1711.11543","title":"Embodied Question Answering","created":"2017-11-30","cited_by_count":336},{"id":"2302.04659","title":"ManiSkill2: A Unified Benchmark for Generalizable Manipulation Skills","created":"2023-02-09","cited_by_count":327},{"id":"2210.07474","title":"SQA3D: Situated Question Answering in 3D Scenes","created":"2022-10-14","cited_by_count":314},{"id":"2305.13786","title":"Perception Test: A Diagnostic Benchmark for Multimodal Video Models","created":"2023-05-23","cited_by_count":314},{"id":"2501.13826","title":"Video-MMMU: Evaluating Knowledge Acquisition from Multi-Discipline Professional Videos","created":"2025-01-23","cited_by_count":236},{"id":"2406.11816","title":"VideoLLM-online: Online Video Large Language Model for Streaming Video","created":"2024-06-17","cited_by_count":225},{"id":"2502.09560","title":"EmbodiedBench: Comprehensive Benchmarking Multi-modal Large Language Models for Vision-Driven Embodied Agents","created":"2025-02-13","cited_by_count":221},{"id":"2405.09711","title":"STAR: A Benchmark for Situated Reasoning in Real-World Videos","created":"2024-05-15","cited_by_count":213},{"id":"2406.08085","title":"Flash-VStream: Memory-Based Real-Time Understanding for Long Video Streams","created":"2024-06-12","cited_by_count":169},{"id":"2309.01327","title":"Can I Trust Your Answer? Visually Grounded Video Question Answering","created":"2023-09-04","cited_by_count":135},{"id":"2311.16103","title":"Video-Bench: A Comprehensive Benchmark and Toolkit for Evaluating Video-based Large Language Models","created":"2023-11-27","cited_by_count":107},{"id":"2305.05706","title":"DexArt: Benchmarking Generalizable Dexterous Manipulation with Articulated Objects","created":"2023-05-09","cited_by_count":66},{"id":"1910.10706","title":"KnowIT VQA: Answering Knowledge-Based Questions about Videos","created":"2019-10-23","cited_by_count":53},{"id":"2005.11185","title":"Low-Latency Sequence-to-Sequence Speech Recognition and Translation by Partial Hypothesis Selection","created":"2020-05-22","cited_by_count":49},{"id":"2303.15105","title":"Vision Transformer with Quadrangle Attention","created":"2023-03-27","cited_by_count":46},{"id":"2306.04362","title":"Youku-mPLUG: A 10 Million Large-scale Chinese Video-Language Dataset for Pre-training and Benchmarks","created":"2023-06-07","cited_by_count":36},{"id":"2201.12888","title":"A Dataset for Medical Instructional Video Classification and Question Answering","created":"2022-01-30","cited_by_count":26},{"id":"2312.04817","title":"LvBench: A Benchmark for Long-form Video Understanding with Versatile Multi-modal Question Answering","created":"2023-12-08","cited_by_count":25},{"id":"2307.14743","title":"Turning Whisper into Real-Time Transcription System","created":"2023-07-27","cited_by_count":24},{"id":"2311.00738","title":"Can Foundation Models Watch, Talk and Guide You Step by Step to Make a Cake?","created":"2023-11-01","cited_by_count":18},{"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},{"id":"1806.00525","title":"Audio Visual Scene-Aware Dialog (AVSD) Challenge at DSTC7","created":"2018-06-01","cited_by_count":9},{"id":"2311.07588","title":"NLQxform: A Language Model-based Question to SPARQL Transformer","created":"2023-11-08","cited_by_count":8},{"id":"2411.09052","title":"ClevrSkills: Compositional Language and Visual Reasoning in Robotics","created":"2024-11-13","cited_by_count":8},{"id":"2403.13365","title":"ManiPose: A Comprehensive Benchmark for Pose-aware Object Manipulation in Robotics","created":"2024-03-20","cited_by_count":7},{"id":"2310.18983","title":"DCQA: Document-Level Chart Question Answering towards Complex Reasoning and Common-Sense Understanding","created":"2023-10-29","cited_by_count":3},{"id":"2410.02921","title":"AirLetters: An Open Video Dataset of Characters Drawn in the Air","created":"2024-10-03","cited_by_count":1}],"next_cursor":null}