{"list":"other","total":77,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2402.03300","title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","created":"2024-02-05","cited_by_count":9379},{"id":"2309.06180","title":"Efficient Memory Management for Large Language Model Serving with PagedAttention","created":"2023-09-12","cited_by_count":5944},{"id":"2502.13923","title":"Qwen2.5-VL Technical Report","created":"2025-02-19","cited_by_count":5587},{"id":"2412.15115","title":"Qwen2.5 Technical Report","created":"2024-12-19","cited_by_count":4942},{"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":"2408.03326","title":"LLaVA-OneVision: Easy Visual Task Transfer","created":"2024-08-06","cited_by_count":2719},{"id":"1910.03771","title":"HuggingFace's Transformers: State-of-the-art Natural Language Processing","created":"2019-10-09","cited_by_count":2218},{"id":"1506.02438","title":"High-Dimensional Continuous Control Using Generalized Advantage Estimation","created":"2015-06-08","cited_by_count":2026},{"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":"2110.07058","title":"Ego4D: Around the World in 3,000 Hours of Egocentric Video","created":"2021-10-13","cited_by_count":1556},{"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":"2405.21075","title":"Video-MME: The First-Ever Comprehensive Evaluation Benchmark of Multi-modal LLMs in Video Analysis","created":"2024-05-31","cited_by_count":1413},{"id":"2311.17005","title":"MVBench: A Comprehensive Multi-modal Video Understanding Benchmark","created":"2023-11-28","cited_by_count":1109},{"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":"2406.07476","title":"VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMs","created":"2024-06-11","cited_by_count":771},{"id":"2312.07533","title":"VILA: On Pre-training for Visual Language Models","created":"2023-12-12","cited_by_count":692},{"id":"2407.15754","title":"LongVideoBench: A Benchmark for Long-context Interleaved Video-Language Understanding","created":"2024-07-22","cited_by_count":665},{"id":"2503.06749","title":"Vision-R1: Incentivizing Reasoning Capability in Multimodal Large Language Models","created":"2025-03-09","cited_by_count":665},{"id":"2308.09583","title":"WizardMath: Empowering Mathematical Reasoning for Large Language Models via Reinforced Evol-Instruct","created":"2023-08-18","cited_by_count":625},{"id":"2412.14171","title":"Thinking in Space: How Multimodal Large Language Models See, Remember, and Recall Spaces","created":"2024-12-18","cited_by_count":611},{"id":"1705.02101","title":"TALL: Temporal Activity Localization via Language Query","created":"2017-05-05","cited_by_count":584},{"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":"2006.13256","title":"Rescaling Egocentric Vision","created":"2020-06-23","cited_by_count":540},{"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":"2501.13106","title":"VideoLLaMA 3: Frontier Multimodal Foundation Models for Image and Video Understanding","created":"2025-01-22","cited_by_count":518},{"id":"2406.16852","title":"Long Context Transfer from Language to Vision","created":"2024-06-24","cited_by_count":515},{"id":"2503.01785","title":"Visual-RFT: Visual Reinforcement Fine-Tuning","created":"2025-03-03","cited_by_count":513},{"id":"2503.21776","title":"Video-R1: Reinforcing Video Reasoning in MLLMs","created":"2025-03-27","cited_by_count":484},{"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":"2503.10615","title":"R1-Onevision: Advancing Generalized Multimodal Reasoning through Cross-Modal Formalization","created":"2025-03-13","cited_by_count":370},{"id":"2403.00476","title":"TempCompass: Do Video LLMs Really Understand Videos?","created":"2024-03-01","cited_by_count":363},{"id":"2410.17434","title":"LongVU: Spatiotemporal Adaptive Compression for Long Video-Language Understanding","created":"2024-10-22","cited_by_count":356},{"id":"2504.08837","title":"VL-Rethinker: Incentivizing Self-Reflection of Vision-Language Models with Reinforcement Learning","created":"2025-04-10","cited_by_count":323},{"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":"2501.13826","title":"Video-MMMU: Evaluating Knowledge Acquisition from Multi-Discipline Professional Videos","created":"2025-01-23","cited_by_count":236},{"id":"2206.08155","title":"Zero-Shot Video Question Answering via Frozen Bidirectional Language Models","created":"2022-06-16","cited_by_count":229},{"id":"2305.06988","title":"Self-Chained Image-Language Model for Video Localization and Question Answering","created":"2023-05-11","cited_by_count":203},{"id":"2302.00402","title":"mPLUG-2: A Modularized Multi-modal Foundation Model Across Text, Image and Video","created":"2023-02-01","cited_by_count":154},{"id":"2404.01258","title":"Direct Preference Optimization of Video Large Multimodal Models from Language Model Reward","created":"2024-04-01","cited_by_count":147},{"id":"2501.12380","title":"MMVU: Measuring Expert-Level Multi-Discipline Video Understanding","created":"2025-01-21","cited_by_count":137},{"id":"2309.01327","title":"Can I Trust Your Answer? Visually Grounded Video Question Answering","created":"2023-09-04","cited_by_count":135},{"id":"2408.15542","title":"Kangaroo: A Powerful Video-Language Model Supporting Long-context Video Input","created":"2024-08-28","cited_by_count":134},{"id":"2410.19702","title":"TimeSuite: Improving MLLMs for Long Video Understanding via Grounded Tuning","created":"2024-10-25","cited_by_count":106},{"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":"2504.13055","title":"NoisyRollout: Reinforcing Visual Reasoning with Data Augmentation","created":"2025-04-17","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":"1707.07402","title":"Reinforcement Learning for Bandit Neural Machine Translation with Simulated Human Feedback","created":"2017-07-24","cited_by_count":72},{"id":"1903.07940","title":"Truly Proximal Policy Optimization","created":"2019-03-19","cited_by_count":69},{"id":"2312.06722","title":"EgoPlan-Bench: Benchmarking Multimodal Large Language Models for Human-Level Planning","created":"2023-12-11","cited_by_count":69},{"id":"2404.16767","title":"REBEL: Reinforcement Learning via Regressing Relative Rewards","created":"2024-04-25","cited_by_count":69},{"id":"2503.18013","title":"Vision-R1: Evolving Human-Free Alignment in Large Vision-Language Models via Vision-Guided Reinforcement Learning","created":"2025-03-23","cited_by_count":69},{"id":"2206.02349","title":"Invariant Grounding for Video Question Answering","created":"2022-06-06","cited_by_count":68},{"id":"2504.09641","title":"TinyLLaVA-Video-R1: Towards Smaller LMMs for Video Reasoning","created":"2025-04-13","cited_by_count":62},{"id":"2310.15747","title":"Large Language Models are Temporal and Causal Reasoners for Video Question Answering","created":"2023-10-24","cited_by_count":51},{"id":"2403.17031","title":"The N+ Implementation Details of RLHF with PPO: A Case Study on TL;DR Summarization","created":"2024-03-24","cited_by_count":50},{"id":"2412.04447","title":"EgoPlan-Bench2: A Benchmark for Multimodal Large Language Model Planning in Real-World Scenarios","created":"2024-12-05","cited_by_count":41},{"id":"2009.10897","title":"Revisiting Design Choices in Proximal Policy Optimization","created":"2020-09-23","cited_by_count":38},{"id":"2502.12081","title":"Unhackable Temporal Rewarding for Scalable Video MLLMs","created":"2025-02-17","cited_by_count":33},{"id":"1704.06497","title":"Bandit Structured Prediction for Neural Sequence-to-Sequence Learning","created":"2017-04-21","cited_by_count":31},{"id":"2404.10501","title":"Self-Supervised Visual Preference Alignment","created":"2024-04-16","cited_by_count":31},{"id":"2503.24376","title":"Exploring the Effect of Reinforcement Learning on Video Understanding: Insights from SEED-Bench-R1","created":"2025-03-31","cited_by_count":25},{"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":"2411.00871","title":"LLaMo: Large Language Model-based Molecular Graph Assistant","created":"2024-10-31","cited_by_count":22},{"id":"2410.01615","title":"Saliency-Guided DETR for Moment Retrieval and Highlight Detection","created":"2024-10-02","cited_by_count":21},{"id":"2503.12542","title":"ST-Think: How Multimodal Large Language Models Reason About 4D Worlds from Ego-Centric Videos","created":"2025-03-16","cited_by_count":21},{"id":"2311.09762","title":"Graph Elicitation for Guiding Multi-Step Reasoning in Large Language Models","created":"2023-11-16","cited_by_count":10},{"id":"2501.06761","title":"VidChain: Chain-of-Tasks with Metric-based Direct Preference Optimization for Dense Video Captioning","created":"2025-01-12","cited_by_count":9},{"id":"2410.09350","title":"Generative Subgraph Retrieval for Knowledge Graph-Grounded Dialog Generation","created":"2024-10-12","cited_by_count":6}],"next_cursor":null}