{"list":"other","total":56,"rows":[{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"2402.03300","title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","created":"2024-02-05","cited_by_count":9379},{"id":"2305.18290","title":"Direct Preference Optimization: Your Language Model is Secretly a Reward Model","created":"2023-05-29","cited_by_count":8065},{"id":"2501.12948","title":"DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning","created":"2025-01-22","cited_by_count":6330},{"id":"2502.13923","title":"Qwen2.5-VL Technical Report","created":"2025-02-19","cited_by_count":5587},{"id":"2204.05862","title":"Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback","created":"2022-04-12","cited_by_count":3720},{"id":"2504.10479","title":"InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models","created":"2025-04-14","cited_by_count":1834},{"id":"2501.12599","title":"Kimi k1.5: Scaling Reinforcement Learning with LLMs","created":"2025-01-22","cited_by_count":1210},{"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":"2310.12036","title":"A General Theoretical Paradigm to Understand Learning from Human Preferences","created":"2023-10-18","cited_by_count":912},{"id":"2305.06355","title":"VideoChat: Chat-Centric Video Understanding","created":"2023-05-10","cited_by_count":857},{"id":"1705.00754","title":"Dense-Captioning Events in Videos","created":"2017-05-02","cited_by_count":793},{"id":"1708.01641","title":"Localizing Moments in Video with Natural Language","created":"2017-08-04","cited_by_count":663},{"id":"1705.02101","title":"TALL: Temporal Activity Localization via Language Query","created":"2017-05-05","cited_by_count":584},{"id":"2403.07691","title":"ORPO: Monolithic Preference Optimization without Reference Model","created":"2024-03-12","cited_by_count":562},{"id":"2307.16449","title":"MovieChat: From Dense Token to Sparse Memory for Long Video Understanding","created":"2023-07-31","cited_by_count":542},{"id":"2504.07615","title":"VLM-R1: A Stable and Generalizable R1-style Large Vision-Language Model","created":"2025-04-10","cited_by_count":526},{"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":"2212.03191","title":"InternVideo: General Video Foundation Models via Generative and Discriminative Learning","created":"2022-12-06","cited_by_count":447},{"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":"2403.15377","title":"InternVideo2: Scaling Foundation Models for Multimodal Video Understanding","created":"2024-03-22","cited_by_count":317},{"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":"2503.06520","title":"Seg-Zero: Reasoning-Chain Guided Segmentation via Cognitive Reinforcement","created":"2025-03-09","cited_by_count":239},{"id":"2312.17432","title":"Video Understanding with Large Language Models: A Survey","created":"2023-12-29","cited_by_count":206},{"id":"2305.06988","title":"Self-Chained Image-Language Model for Video Localization and Question Answering","created":"2023-05-11","cited_by_count":203},{"id":"2307.16715","title":"UniVTG: Towards Unified Video-Language Temporal Grounding","created":"2023-07-31","cited_by_count":190},{"id":"2004.03545","title":"Dense Regression Network for Video Grounding","created":"2020-04-07","cited_by_count":176},{"id":"2305.18500","title":"VAST: A Vision-Audio-Subtitle-Text Omni-Modality Foundation Model and Dataset","created":"2023-05-29","cited_by_count":169},{"id":"2303.13874","title":"Query-Dependent Video Representation for Moment Retrieval and Highlight Detection","created":"2023-03-24","cited_by_count":166},{"id":"1904.11574","title":"TVQA+: Spatio-Temporal Grounding for Video Question Answering","created":"2019-04-25","cited_by_count":154},{"id":"2402.11435","title":"Momentor: Advancing Video Large Language Model with Fine-Grained Temporal Reasoning","created":"2024-02-18","cited_by_count":122},{"id":"2504.07954","title":"Perception-R1: Pioneering Perception Policy with Reinforcement Learning","created":"2025-04-10","cited_by_count":120},{"id":"2401.06071","title":"GroundingGPT:Language Enhanced Multi-modal Grounding Model","created":"2024-01-11","cited_by_count":101},{"id":"2503.05379","title":"R1-Omni: Explainable Omni-Multimodal Emotion Recognition with Reinforcement Learning","created":"2025-03-07","cited_by_count":100},{"id":"2410.03290","title":"Grounded-VideoLLM: Sharpening Fine-grained Temporal Grounding in Video Large Language Models","created":"2024-10-04","cited_by_count":91},{"id":"2410.05643","title":"TRACE: Temporal Grounding Video LLM via Causal Event Modeling","created":"2024-10-08","cited_by_count":89},{"id":"2403.10228","title":"HawkEye: Training Video-Text LLMs for Grounding Text in Videos","created":"2024-03-15","cited_by_count":86},{"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":"2308.06947","title":"Knowing Where to Focus: Event-aware Transformer for Video Grounding","created":"2023-08-14","cited_by_count":79},{"id":"2406.06040","title":"Vript: A Video Is Worth Thousands of Words","created":"2024-06-10","cited_by_count":71},{"id":"2503.07065","title":"Boosting the Generalization and Reasoning of Vision Language Models with Curriculum Reinforcement Learning","created":"2025-03-10","cited_by_count":71},{"id":"2501.01904","title":"Virgo: A Preliminary Exploration on Reproducing o1-like MLLM","created":"2025-01-03","cited_by_count":68},{"id":"2308.11062","title":"UnLoc: A Unified Framework for Video Localization Tasks","created":"2023-08-21","cited_by_count":66},{"id":"2505.02835","title":"R1-Reward: Training Multimodal Reward Model Through Stable Reinforcement Learning","created":"2025-05-05","cited_by_count":65},{"id":"2210.09579","title":"Unpacking Reward Shaping: Understanding the Benefits of Reward Engineering on Sample Complexity","created":"2022-10-18","cited_by_count":62},{"id":"1903.00859","title":"Less is More: Learning Highlight Detection from Video Duration","created":"2019-03-03","cited_by_count":60},{"id":"2404.02257","title":"SnAG: Scalable and Accurate Video Grounding","created":"2024-04-02","cited_by_count":36},{"id":"2207.13457","title":"Reducing the Vision and Language Bias for Temporal Sentence Grounding","created":"2022-07-27","cited_by_count":35},{"id":"2012.02646","title":"Multi-Scale 2D Temporal Adjacent Networks for Moment Localization with Natural Language","created":"2020-12-04","cited_by_count":29},{"id":"2103.16848","title":"Embracing Uncertainty: Decoupling and De-bias for Robust Temporal Grounding","created":"2021-03-31","cited_by_count":29},{"id":"2412.13441","title":"FlashVTG: Feature Layering and Adaptive Score Handling Network for Video Temporal Grounding","created":"2024-12-18","cited_by_count":23},{"id":"2408.03029","title":"Highly Efficient Self-Adaptive Reward Shaping for Reinforcement Learning","created":"2024-08-06","cited_by_count":22},{"id":"2502.11594","title":"iMOVE: Instance-Motion-Aware Video Understanding","created":"2025-02-17","cited_by_count":10},{"id":"2503.15807","title":"Video-VoT-R1: An efficient video inference model integrating image packing and AoE architecture","created":"2025-03-20","cited_by_count":2}],"next_cursor":null}