{"list":"other","total":53,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"2110.14168","title":"Training Verifiers to Solve Math Word Problems","created":"2021-10-27","cited_by_count":10109},{"id":"2402.03300","title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","created":"2024-02-05","cited_by_count":9379},{"id":"2005.11401","title":"Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks","created":"2020-05-22","cited_by_count":9297},{"id":"2210.03629","title":"ReAct: Synergizing Reasoning and Acting in Language Models","created":"2022-10-06","cited_by_count":8695},{"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":"2511.21631","title":"Qwen3-VL Technical Report","created":"2025-11-26","cited_by_count":2793},{"id":"2408.03326","title":"LLaVA-OneVision: Easy Visual Task Transfer","created":"2024-08-06","cited_by_count":2719},{"id":"2312.14238","title":"InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks","created":"2023-12-21","cited_by_count":2565},{"id":"2308.12950","title":"Code Llama: Open Foundation Models for Code","created":"2023-08-24","cited_by_count":2139},{"id":"1812.03982","title":"SlowFast Networks for Video Recognition","created":"2018-12-10","cited_by_count":1867},{"id":"1606.06565","title":"Concrete Problems in AI Safety","created":"2016-06-21","cited_by_count":1642},{"id":"2102.05095","title":"Is Space-Time Attention All You Need for Video Understanding?","created":"2021-02-09","cited_by_count":1620},{"id":"2503.09516","title":"Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning","created":"2025-03-12","cited_by_count":1444},{"id":"2401.14196","title":"DeepSeek-Coder: When the Large Language Model Meets Programming -- The Rise of Code Intelligence","created":"2024-01-25","cited_by_count":1181},{"id":"2507.18071","title":"Group Sequence Policy Optimization","created":"2025-07-24","cited_by_count":835},{"id":"2307.06942","title":"InternVid: A Large-scale Video-Text Dataset for Multimodal Understanding and Generation","created":"2023-07-13","cited_by_count":497},{"id":"1604.06573","title":"Convolutional Two-Stream Network Fusion for Video Action Recognition","created":"2016-04-22","cited_by_count":384},{"id":"1704.04497","title":"TGIF-QA: Toward Spatio-Temporal Reasoning in Visual Question Answering","created":"2017-04-14","cited_by_count":378},{"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":"2503.05592","title":"R1-Searcher: Incentivizing the Search Capability in LLMs via Reinforcement Learning","created":"2025-03-07","cited_by_count":336},{"id":"2403.10517","title":"VideoAgent: Long-form Video Understanding with Large Language Model as Agent","created":"2024-03-15","cited_by_count":332},{"id":"1511.03416","title":"Visual7W: Grounded Question Answering in Images","created":"2015-11-11","cited_by_count":318},{"id":"1512.02902","title":"MovieQA: Understanding Stories in Movies through Question-Answering","created":"2015-12-09","cited_by_count":304},{"id":"2406.04264","title":"MLVU: Benchmarking Multi-task Long Video Understanding","created":"2024-06-06","cited_by_count":292},{"id":"1904.02811","title":"Video Classification with Channel-Separated Convolutional Networks","created":"2019-04-04","cited_by_count":290},{"id":"2504.06958","title":"VideoChat-R1: Enhancing Spatio-Temporal Perception via Reinforcement Fine-Tuning","created":"2025-04-09","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":"2101.10030","title":"Weakly-supervised Video Anomaly Detection with Robust Temporal Feature Magnitude Learning","created":"2021-01-25","cited_by_count":230},{"id":"2007.10937","title":"MovieNet: A Holistic Dataset for Movie Understanding","created":"2020-07-21","cited_by_count":206},{"id":"2406.11409","title":"CodeGemma: Open Code Models Based on Gemma","created":"2024-06-17","cited_by_count":150},{"id":"2411.04998","title":"HourVideo: 1-Hour Video-Language Understanding","created":"2024-11-07","cited_by_count":113},{"id":"2511.22570","title":"DeepSeekMath-V2: Towards Self-Verifiable Mathematical Reasoning","created":"2025-11-27","cited_by_count":94},{"id":"2504.02259","title":"T*: Re-thinking Temporal Search for Long-Form Video Understanding","created":"2025-04-03","cited_by_count":82},{"id":"1909.05304","title":"Reinforcement Learning for Temporal Logic Control Synthesis with Probabilistic Satisfaction Guarantees","created":"2019-09-11","cited_by_count":77},{"id":"2404.17176","title":"MovieChat+: Question-aware Sparse Memory for Long Video Question Answering","created":"2024-04-26","cited_by_count":73},{"id":"2205.01089","title":"ComPhy: Compositional Physical Reasoning of Objects and Events from Videos","created":"2022-05-02","cited_by_count":63},{"id":"1707.06355","title":"Video Question Answering via Attribute-Augmented Attention Network Learning","created":"2017-07-20","cited_by_count":39},{"id":"2506.10821","title":"VideoExplorer: Think With Videos For Agentic Long-Video Understanding","created":"2025-06-12","cited_by_count":29},{"id":"2503.09590","title":"BIMBA: Selective-Scan Compression for Long-Range Video Question Answering","created":"2025-03-12","cited_by_count":24},{"id":"2511.05489","title":"TimeSearch-R: Adaptive Temporal Search for Long-Form Video Understanding via Self-Verification Reinforcement Learning","created":"2025-11-07","cited_by_count":20},{"id":"2410.20252","title":"Adaptive Video Understanding Agent: Enhancing efficiency with dynamic frame sampling and feedback-driven reasoning","created":"2024-10-26","cited_by_count":17},{"id":"2403.11021","title":"Towards Neuro-Symbolic Video Understanding","created":"2024-03-16","cited_by_count":16},{"id":"2309.10171","title":"Specification-Driven Video Search via Foundation Models and Formal Verification","created":"2023-09-18","cited_by_count":10},{"id":"2504.17180","title":"We'll Fix it in Post: Improving Text-to-Video Generation with Neuro-Symbolic Feedback","created":"2025-04-24","cited_by_count":10},{"id":"2411.16718","title":"Neuro-Symbolic Evaluation of Text-to-Video Models using Formal Verification","created":"2024-11-22","cited_by_count":9},{"id":"2406.07400","title":"Guiding LLM Temporal Logic Generation with Explicit Separation of Data and Control","created":"2024-06-11","cited_by_count":8},{"id":"2505.13851","title":"A Challenge to Build Neuro-Symbolic Video Agents","created":"2025-05-20","cited_by_count":5},{"id":"2605.01248","title":"$S^3$-R1: Learning to Retrieve and Answer Step-by-Step with Synthetic Data","created":"2026-05-02","cited_by_count":3},{"id":"2511.18701","title":"ObjectAlign: Neuro-Symbolic Object Consistency Verification and Correction","created":"2025-11-24","cited_by_count":2},{"id":"2602.23553","title":"RT-NeuS: Towards Real-Time Neuro-Symbolic Video Understanding via Adaptive Temporal Verification","created":"2026-02-26","cited_by_count":2}],"next_cursor":null}