{"list":"other","total":56,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"2507.06261","title":"Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities","created":"2025-07-07","cited_by_count":3796},{"id":"2511.21631","title":"Qwen3-VL Technical Report","created":"2025-11-26","cited_by_count":2793},{"id":"1612.06890","title":"CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoning","created":"2016-12-20","cited_by_count":1457},{"id":"1608.00272","title":"Modeling Context in Referring Expressions","created":"2016-07-31","cited_by_count":1063},{"id":"2307.16125","title":"SEED-Bench: Benchmarking Multimodal LLMs with Generative Comprehension","created":"2023-07-30","cited_by_count":940},{"id":"2602.02276","title":"Kimi K2.5: Visual Agentic Intelligence","created":"2026-02-02","cited_by_count":501},{"id":"1910.01442","title":"CLEVRER: CoLlision Events for Video REpresentation and Reasoning","created":"2019-10-03","cited_by_count":484},{"id":"2507.01006","title":"GLM-4.5V and GLM-4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning","created":"2025-07-01","cited_by_count":466},{"id":"2505.07062","title":"Seed1.5-VL Technical Report","created":"2025-05-11","cited_by_count":373},{"id":"2403.00476","title":"TempCompass: Do Video LLMs Really Understand Videos?","created":"2024-03-01","cited_by_count":363},{"id":"2409.17146","title":"Molmo and PixMo: Open Weights and Open Data for State-of-the-Art Vision-Language Models","created":"2024-09-25","cited_by_count":329},{"id":"2305.13786","title":"Perception Test: A Diagnostic Benchmark for Multimodal Video Models","created":"2023-05-23","cited_by_count":314},{"id":"2305.15408","title":"Towards Revealing the Mystery behind Chain of Thought: A Theoretical Perspective","created":"2023-05-24","cited_by_count":294},{"id":"2406.04264","title":"MLVU: Benchmarking Multi-task Long Video Understanding","created":"2024-06-06","cited_by_count":292},{"id":"2210.10749","title":"Transformers Learn Shortcuts to Automata","created":"2022-10-19","cited_by_count":268},{"id":"2402.12875","title":"Chain of Thought Empowers Transformers to Solve Inherently Serial Problems","created":"2024-02-20","cited_by_count":260},{"id":"2501.13826","title":"Video-MMMU: Evaluating Knowledge Acquisition from Multi-Discipline Professional Videos","created":"2025-01-23","cited_by_count":236},{"id":"2207.04901","title":"Exploring Length Generalization in Large Language Models","created":"2022-07-11","cited_by_count":206},{"id":"2207.00729","title":"The Parallelism Tradeoff: Limitations of Log-Precision Transformers","created":"2022-07-02","cited_by_count":193},{"id":"2404.08819","title":"The Illusion of State in State-Space Models","created":"2024-04-12","cited_by_count":187},{"id":"2102.01558","title":"Occluded Video Instance Segmentation: A Benchmark","created":"2021-02-02","cited_by_count":154},{"id":"1910.04744","title":"CATER: A diagnostic dataset for Compositional Actions and TEmporal Reasoning","created":"2019-10-10","cited_by_count":137},{"id":"2501.12380","title":"MMVU: Measuring Expert-Level Multi-Discipline Video Understanding","created":"2025-01-21","cited_by_count":137},{"id":"2206.03428","title":"Revealing Single Frame Bias for Video-and-Language Learning","created":"2022-06-07","cited_by_count":133},{"id":"2410.10818","title":"TemporalBench: Benchmarking Fine-grained Temporal Understanding for Multimodal Video Models","created":"2024-10-14","cited_by_count":97},{"id":"2402.09963","title":"Why are Sensitive Functions Hard for Transformers?","created":"2024-02-15","cited_by_count":74},{"id":"2410.23266","title":"TOMATO: Assessing Visual Temporal Reasoning Capabilities in Multimodal Foundation Models","created":"2024-10-30","cited_by_count":73},{"id":"2102.13249","title":"Chess as a Testbed for Language Model State Tracking","created":"2021-02-26","cited_by_count":72},{"id":"2409.18111","title":"E.T. Bench: Towards Open-Ended Event-Level Video-Language Understanding","created":"2024-09-26","cited_by_count":70},{"id":"2506.22355","title":"Embodied AI Agents: Modeling the World","created":"2025-06-27","cited_by_count":61},{"id":"2503.12799","title":"Grounded Chain-of-Thought for Multimodal Large Language Models","created":"2025-03-17","cited_by_count":59},{"id":"2409.16597","title":"EventHallusion: Diagnosing Event Hallucinations in Video LLMs","created":"2024-09-25","cited_by_count":57},{"id":"2410.08633","title":"Transformers Provably Solve Parity Efficiently with Chain of Thought","created":"2024-10-11","cited_by_count":50},{"id":"2305.02363","title":"Entity Tracking in Language Models","created":"2023-05-03","cited_by_count":44},{"id":"2503.13646","title":"Omnia de EgoTempo: Benchmarking Temporal Understanding of Multi-Modal LLMs in Egocentric Videos","created":"2025-03-17","cited_by_count":44},{"id":"2405.16919","title":"VoCoT: Unleashing Visually Grounded Multi-Step Reasoning in Large Multi-Modal Models","created":"2024-05-27","cited_by_count":43},{"id":"2410.07752","title":"Lost in Time: A New Temporal Benchmark for VideoLLMs","created":"2024-10-10","cited_by_count":42},{"id":"2204.02892","title":"Sub-Task Decomposition Enables Learning in Sequence to Sequence Tasks","created":"2022-04-06","cited_by_count":41},{"id":"2504.15485","title":"CAPTURe: Evaluating Spatial Reasoning in Vision Language Models via Occluded Object Counting","created":"2025-04-21","cited_by_count":38},{"id":"2504.14693","title":"Video-MMLU: A Massive Multi-Discipline Lecture Understanding Benchmark","created":"2025-04-20","cited_by_count":37},{"id":"2512.04797","title":"SIMA 2: A Generalist Embodied Agent for Virtual Worlds","created":"2025-12-04","cited_by_count":31},{"id":"2506.09987","title":"A Shortcut-aware Video-QA Benchmark for Physical Understanding via Minimal Video Pairs","created":"2025-06-11","cited_by_count":30},{"id":"2601.02427","title":"NitroGen: An Open Foundation Model for Generalist Gaming Agents","created":"2026-01-04","cited_by_count":27},{"id":"2506.04034","title":"Rex-Thinker: Grounded Object Referring via Chain-of-Thought Reasoning","created":"2025-06-04","cited_by_count":26},{"id":"2505.23359","title":"VideoReasonBench: Can MLLMs Perform Vision-Centric Complex Video Reasoning?","created":"2025-05-29","cited_by_count":20},{"id":"2511.07378","title":"Transformers Provably Learn Chain-of-Thought Reasoning with Length Generalization","created":"2025-11-10","cited_by_count":14},{"id":"2602.00288","title":"TimeBlind: A Spatio-Temporal Compositionality Benchmark for Video LLMs","created":"2026-01-30","cited_by_count":11},{"id":"2505.20124","title":"TUNA: Comprehensive Fine-grained Temporal Understanding Evaluation on Dense Dynamic Videos","created":"2025-05-26","cited_by_count":9},{"id":"2507.02859","title":"Bootstrapping Grounded Chain-of-Thought in Multimodal LLMs for Data-Efficient Model Adaptation","created":"2025-07-03","cited_by_count":9},{"id":"2512.05513","title":"Know-Show: Benchmarking Video-Language Models on Spatio-Temporal Grounded Reasoning","created":"2025-12-05","cited_by_count":5},{"id":"2504.05925","title":"SVLTA: Benchmarking Vision-Language Temporal Alignment via Synthetic Video Situation","created":"2025-04-08","cited_by_count":4},{"id":"2512.00736","title":"REM: Evaluating LLM Embodied Spatial Reasoning through Multi-Frame Trajectories","created":"2025-11-30","cited_by_count":4},{"id":"2502.10886","title":"MET-Bench: Multimodal Entity Tracking for Evaluating the Limitations of Vision-Language and Reasoning Models","created":"2025-02-15","cited_by_count":1}],"next_cursor":null}