{"list":"other","total":83,"rows":[{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"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":"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":"2503.14476","title":"DAPO: An Open-Source LLM Reinforcement Learning System at Scale","created":"2025-03-18","cited_by_count":2810},{"id":"2511.21631","title":"Qwen3-VL Technical Report","created":"2025-11-26","cited_by_count":2793},{"id":"2311.16502","title":"MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI","created":"2023-11-27","cited_by_count":2080},{"id":"1904.08920","title":"Towards VQA Models That Can Read","created":"2019-04-18","cited_by_count":1718},{"id":"2310.02255","title":"MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contexts","created":"2023-10-03","cited_by_count":1614},{"id":"2203.10244","title":"ChartQA: A Benchmark for Question Answering about Charts with Visual and Logical Reasoning","created":"2022-03-19","cited_by_count":1479},{"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":"1910.02054","title":"ZeRO: Memory Optimizations Toward Training Trillion Parameter Models","created":"2019-10-04","cited_by_count":1301},{"id":"2311.12793","title":"ShareGPT4V: Improving Large Multi-Modal Models with Better Captions","created":"2023-11-21","cited_by_count":1005},{"id":"1603.07396","title":"A Diagram Is Worth A Dozen Images","created":"2016-03-24","cited_by_count":804},{"id":"1708.01641","title":"Localizing Moments in Video with Natural Language","created":"2017-08-04","cited_by_count":663},{"id":"1905.13319","title":"MathQA: Towards Interpretable Math Word Problem Solving with Operation-Based Formalisms","created":"2019-05-30","cited_by_count":662},{"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":"2310.14566","title":"HallusionBench: An Advanced Diagnostic Suite for Entangled Language Hallucination and Visual Illusion in Large Vision-Language Models","created":"2023-10-23","cited_by_count":583},{"id":"2410.02713","title":"LLaVA-Video: Video Instruction Tuning With Synthetic Data","created":"2024-10-03","cited_by_count":583},{"id":"2307.16449","title":"MovieChat: From Dense Token to Sparse Memory for Long Video Understanding","created":"2023-07-31","cited_by_count":542},{"id":"1604.01753","title":"Hollywood in Homes: Crowdsourcing Data Collection for Activity Understanding","created":"2016-04-06","cited_by_count":537},{"id":"2503.21776","title":"Video-R1: Reinforcing Video Reasoning in MLLMs","created":"2025-03-27","cited_by_count":484},{"id":"1810.11981","title":"GOT-10k: A Large High-Diversity Benchmark for Generic Object Tracking in the Wild","created":"2018-10-29","cited_by_count":475},{"id":"2503.16419","title":"Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models","created":"2025-03-20","cited_by_count":464},{"id":"2503.09567","title":"Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Models","created":"2025-03-12","cited_by_count":384},{"id":"2408.05517","title":"SWIFT:A Scalable lightWeight Infrastructure for Fine-Tuning","created":"2024-08-10","cited_by_count":355},{"id":"1803.10794","title":"TrackingNet: A Large-Scale Dataset and Benchmark for Object Tracking in the Wild","created":"2018-03-28","cited_by_count":343},{"id":"2305.13786","title":"Perception Test: A Diagnostic Benchmark for Multimodal Video Models","created":"2023-05-23","cited_by_count":314},{"id":"2408.10188","title":"LongVILA: Scaling Long-Context Visual Language Models for Long Videos","created":"2024-08-19","cited_by_count":309},{"id":"2308.08544","title":"MeViS: A Large-scale Benchmark for Video Segmentation with Motion Expressions","created":"2023-08-16","cited_by_count":228},{"id":"2405.09711","title":"STAR: A Benchmark for Situated Reasoning in Real-World Videos","created":"2024-05-15","cited_by_count":213},{"id":"2601.05242","title":"GDPO: Group reward-Decoupled Normalization Policy Optimization for Multi-reward RL Optimization","created":"2026-01-08","cited_by_count":193},{"id":"2501.04001","title":"Sa2VA: Marrying SAM2 with MLLM for Dense Grounded Understanding of Images and Videos","created":"2025-01-07","cited_by_count":159},{"id":"2505.13417","title":"AdaptThink: Reasoning Models Can Learn When to Think","created":"2025-05-19","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":"2501.05444","title":"Can MLLMs Reason in Multimodality? EMMA: An Enhanced MultiModal ReAsoning Benchmark","created":"2025-01-09","cited_by_count":134},{"id":"2412.11664","title":"C3oT: Generating Shorter Chain-of-Thought without Compromising Effectiveness","created":"2024-12-16","cited_by_count":119},{"id":"2505.21374","title":"Video-Holmes: Can MLLM Think Like Holmes for Complex Video Reasoning?","created":"2025-05-27","cited_by_count":118},{"id":"2505.00127","title":"Between Underthinking and Overthinking: An Empirical Study of Reasoning Length and correctness in LLMs","created":"2025-04-30","cited_by_count":117},{"id":"2504.15279","title":"VisuLogic: A Benchmark for Evaluating Visual Reasoning in Multi-modal Large Language Models","created":"2025-04-21","cited_by_count":107},{"id":"2502.04144","title":"HD-EPIC: A Highly-Detailed Egocentric Video Dataset","created":"2025-02-06","cited_by_count":104},{"id":"2502.02542","title":"OverThink: Slowdown Attacks on Reasoning LLMs","created":"2025-02-04","cited_by_count":96},{"id":"2505.12434","title":"VideoRFT: Incentivizing Video Reasoning Capability in MLLMs via Reinforced Fine-Tuning","created":"2025-05-18","cited_by_count":93},{"id":"2508.04416","title":"Thinking With Videos: Multimodal Tool-Augmented Reinforcement Learning for Long Video Reasoning","created":"2025-08-06","cited_by_count":91},{"id":"2505.04921","title":"Perception, Reason, Think, and Plan: A Survey on Large Multimodal Reasoning Models","created":"2025-05-08","cited_by_count":90},{"id":"2505.11896","title":"AdaCoT: Pareto-Optimal Adaptive Chain-of-Thought Triggering via Reinforcement Learning","created":"2025-05-17","cited_by_count":87},{"id":"2207.10883","title":"My View is the Best View: Procedure Learning from Egocentric Videos","created":"2022-07-22","cited_by_count":81},{"id":"2410.23266","title":"TOMATO: Assessing Visual Temporal Reasoning Capabilities in Multimodal Foundation Models","created":"2024-10-30","cited_by_count":73},{"id":"2411.14794","title":"VideoEspresso: A Large-Scale Chain-of-Thought Dataset for Fine-Grained Video Reasoning via Core Frame Selection","created":"2024-11-22","cited_by_count":65},{"id":"2501.08282","title":"LLaVA-ST: A Multimodal Large Language Model for Fine-Grained Spatial-Temporal Understanding","created":"2025-01-14","cited_by_count":59},{"id":"2504.06514","title":"Missing Premise exacerbates Overthinking: Are Reasoning Models losing Critical Thinking Skill?","created":"2025-04-09","cited_by_count":58},{"id":"2408.00765","title":"MM-Vet v2: A Challenging Benchmark to Evaluate Large Multimodal Models for Integrated Capabilities","created":"2024-08-01","cited_by_count":57},{"id":"2512.03043","title":"OneThinker: All-in-one Reasoning Model for Image and Video","created":"2025-12-02","cited_by_count":56},{"id":"2510.20579","title":"Open-o3-Video: Grounded Video Reasoning with Explicit Spatio-Temporal Evidence","created":"2025-10-23","cited_by_count":49},{"id":"2403.16558","title":"Elysium: Exploring Object-level Perception in Videos via MLLM","created":"2024-03-25","cited_by_count":48},{"id":"2505.05464","title":"Bring Reason to Vision: Understanding Perception and Reasoning through Model Merging","created":"2025-05-08","cited_by_count":40},{"id":"2509.25848","title":"More Thought, Less Accuracy? On the Dual Nature of Reasoning in Vision-Language Models","created":"2025-09-30","cited_by_count":27},{"id":"2507.15028","title":"Towards Video Thinking Test: A Holistic Benchmark for Advanced Video Reasoning and Understanding","created":"2025-07-20","cited_by_count":24},{"id":"2512.16918","title":"AdaTooler-V: Adaptive Tool-Use for Images and Videos","created":"2025-12-18","cited_by_count":21},{"id":"2601.05175","title":"VideoAuto-R1: Video Auto Reasoning via Thinking Once, Answering Twice","created":"2026-01-08","cited_by_count":21},{"id":"2411.09921","title":"Motion-Grounded Video Reasoning: Understanding and Perceiving Motion at Pixel Level","created":"2024-11-15","cited_by_count":19},{"id":"2509.13031","title":"Perception Before Reasoning: Two-Stage Reinforcement Learning for Visual Reasoning in Vision-Language Models","created":"2025-09-16","cited_by_count":17},{"id":"2510.08559","title":"SciVideoBench: Benchmarking Scientific Video Reasoning in Large Multimodal Models","created":"2025-10-09","cited_by_count":13},{"id":"2512.21540","title":"Leash: Adaptive Length Penalty and Reward Shaping for Efficient Large Reasoning Model","created":"2025-12-25","cited_by_count":13},{"id":"2507.08297","title":"KAT-V1: Kwai-AutoThink Technical Report","created":"2025-07-11","cited_by_count":12},{"id":"2508.03100","title":"AVATAR: Reinforcement Learning to See, Hear, and Reason Over Video","created":"2025-08-05","cited_by_count":12},{"id":"2511.23478","title":"Video-R2: Reinforcing Consistent and Grounded Reasoning in Multimodal Language Models","created":"2025-11-28","cited_by_count":10},{"id":"2511.23477","title":"Video-CoM: Interactive Video Reasoning via Chain of Manipulations","created":"2025-11-28","cited_by_count":9},{"id":"2512.09616","title":"Rethinking Chain-of-Thought Reasoning for Videos","created":"2025-12-10","cited_by_count":9},{"id":"2603.25077","title":"Bridging Perception and Reasoning: Token Reweighting for RLVR in Multimodal LLMs","created":"2026-03-26","cited_by_count":9},{"id":"2504.14096","title":"VideoPASTA: 7K Preference Pairs That Matter for Video-LLM Alignment","created":"2025-04-18","cited_by_count":8},{"id":"2412.00624","title":"VideoSAVi: Self-Aligned Video Language Models without Human Supervision","created":"2024-12-01","cited_by_count":7},{"id":"2506.02356","title":"InterRVOS: Interaction-aware Referring Video Object Segmentation","created":"2025-06-03","cited_by_count":6},{"id":"2510.01719","title":"What MLLMs Learn about When they Learn about Multimodal Reasoning","created":"2025-10-02","cited_by_count":6},{"id":"2512.03783","title":"Omni-AutoThink: Adaptive Multimodal Reasoning via Reinforcement Learning","created":"2025-12-03","cited_by_count":5},{"id":"2602.17555","title":"GraphThinker: Reinforcing Temporally Grounded Video Reasoning with Event Graph Thinking","created":"2026-02-19","cited_by_count":5},{"id":"2510.08163","title":"ARM2: Adaptive Reasoning Model with Vision Understanding and Executable Code","created":"2025-10-09","cited_by_count":4},{"id":"2511.18242","title":"EgoVITA: Learning to Plan and Verify for Egocentric Video Reasoning","created":"2025-11-23","cited_by_count":4},{"id":"2603.14659","title":"VisionCoach: Reinforcing Grounded Video Reasoning via Visual-Perception Prompting","created":"2026-03-15","cited_by_count":4}],"next_cursor":null}