{"list":"other","total":68,"rows":[{"id":"2408.03326","title":"LLaVA-OneVision: Easy Visual Task Transfer","created":"2024-08-06","cited_by_count":2719},{"id":"1612.00837","title":"Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering","created":"2016-12-02","cited_by_count":2516},{"id":"1711.03938","title":"CARLA: An Open Urban Driving Simulator","created":"2017-11-10","cited_by_count":2449},{"id":"2308.12966","title":"Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond","created":"2023-08-24","cited_by_count":2224},{"id":"2307.06281","title":"MMBench: Is Your Multi-modal Model an All-around Player?","created":"2023-07-12","cited_by_count":2141},{"id":"1912.01603","title":"Dream to Control: Learning Behaviors by Latent Imagination","created":"2019-12-03","cited_by_count":1653},{"id":"2306.13394","title":"MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models","created":"2023-06-23","cited_by_count":1652},{"id":"2412.05271","title":"Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling","created":"2024-12-06","cited_by_count":1599},{"id":"1803.10122","title":"World Models","created":"2018-03-27","cited_by_count":1513},{"id":"1612.06890","title":"CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoning","created":"2016-12-20","cited_by_count":1457},{"id":"2311.17005","title":"MVBench: A Comprehensive Multi-modal Video Understanding Benchmark","created":"2023-11-28","cited_by_count":1109},{"id":"2307.16125","title":"SEED-Bench: Benchmarking Multimodal LLMs with Generative Comprehension","created":"2023-07-30","cited_by_count":940},{"id":"2410.18072","title":"WorldSimBench: Towards Video Generation Models as World Simulators","created":"2024-10-23","cited_by_count":881},{"id":"1809.01999","title":"Recurrent World Models Facilitate Policy Evolution","created":"2018-09-04","cited_by_count":785},{"id":"2402.15391","title":"Genie: Generative Interactive Environments","created":"2024-02-23","cited_by_count":747},{"id":"2105.08276","title":"NExT-QA:Next Phase of Question-Answering to Explaining Temporal Actions","created":"2021-05-18","cited_by_count":744},{"id":"2308.12952","title":"BridgeData V2: A Dataset for Robot Learning at Scale","created":"2023-08-24","cited_by_count":657},{"id":"2309.17080","title":"GAIA-1: A Generative World Model for Autonomous Driving","created":"2023-09-29","cited_by_count":637},{"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":"2407.07895","title":"LLaVA-NeXT-Interleave: Tackling Multi-image, Video, and 3D in Large Multimodal Models","created":"2024-07-10","cited_by_count":584},{"id":"2404.12390","title":"BLINK: Multimodal Large Language Models Can See but Not Perceive","created":"2024-04-18","cited_by_count":550},{"id":"2307.16449","title":"MovieChat: From Dense Token to Sparse Memory for Long Video Understanding","created":"2023-07-31","cited_by_count":542},{"id":"2106.14405","title":"Habitat 2.0: Training Home Assistants to Rearrange their Habitat","created":"2021-06-28","cited_by_count":511},{"id":"2305.18654","title":"Faith and Fate: Limits of Transformers on Compositionality","created":"2023-05-29","cited_by_count":503},{"id":"1910.01442","title":"CLEVRER: CoLlision Events for Video REpresentation and Reasoning","created":"2019-10-03","cited_by_count":484},{"id":"2312.14135","title":"V*: Guided Visual Search as a Core Mechanism in Multimodal LLMs","created":"2023-12-21","cited_by_count":482},{"id":"1811.00491","title":"A Corpus for Reasoning About Natural Language Grounded in Photographs","created":"2018-11-01","cited_by_count":459},{"id":"2310.06114","title":"Learning Interactive Real-World Simulators","created":"2023-10-09","cited_by_count":458},{"id":"2406.02523","title":"RoboCasa: Large-Scale Simulation of Everyday Tasks for Generalist Robots","created":"2024-06-04","cited_by_count":407},{"id":"1511.02799","title":"Neural Module Networks","created":"2015-11-09","cited_by_count":376},{"id":"2111.15366","title":"AI and the Everything in the Whole Wide World Benchmark","created":"2021-11-26","cited_by_count":349},{"id":"2302.04659","title":"ManiSkill2: A Unified Benchmark for Generalizable Manipulation Skills","created":"2023-02-09","cited_by_count":327},{"id":"2311.17918","title":"Driving into the Future: Multiview Visual Forecasting and Planning with World Model for Autonomous Driving","created":"2023-11-29","cited_by_count":319},{"id":"2305.13786","title":"Perception Test: A Diagnostic Benchmark for Multimodal Video Models","created":"2023-05-23","cited_by_count":314},{"id":"2406.01584","title":"SpatialRGPT: Grounded Spatial Reasoning in Vision Language Models","created":"2024-06-03","cited_by_count":311},{"id":"2205.00363","title":"Visual Spatial Reasoning","created":"2022-04-30","cited_by_count":293},{"id":"2007.04954","title":"ThreeDWorld: A Platform for Interactive Multi-Modal Physical Simulation","created":"2020-07-09","cited_by_count":250},{"id":"2410.00425","title":"ManiSkill3: GPU Parallelized Robotics Simulation and Rendering for Generalizable Embodied AI","created":"2024-10-01","cited_by_count":229},{"id":"2405.09711","title":"STAR: A Benchmark for Situated Reasoning in Real-World Videos","created":"2024-05-15","cited_by_count":213},{"id":"2411.02385","title":"How Far is Video Generation from World Model: A Physical Law Perspective","created":"2024-11-04","cited_by_count":212},{"id":"2412.04468","title":"NVILA: Efficient Frontier Visual Language Models","created":"2024-12-05","cited_by_count":209},{"id":"2404.12377","title":"RoboDreamer: Learning Compositional World Models for Robot Imagination","created":"2024-04-18","cited_by_count":195},{"id":"2404.08636","title":"Probing the 3D Awareness of Visual Foundation Models","created":"2024-04-12","cited_by_count":177},{"id":"2306.11290","title":"Habitat Synthetic Scenes Dataset (HSSD-200): An Analysis of 3D Scene Scale and Realism Tradeoffs for ObjectGoal Navigation","created":"2023-06-20","cited_by_count":167},{"id":"2310.08576","title":"Learning to Act from Actionless Videos through Dense Correspondences","created":"2023-10-12","cited_by_count":164},{"id":"1908.05656","title":"PHYRE: A New Benchmark for Physical Reasoning","created":"2019-08-15","cited_by_count":137},{"id":"1910.04744","title":"CATER: A diagnostic dataset for Compositional Actions and TEmporal Reasoning","created":"2019-10-10","cited_by_count":137},{"id":"2112.07566","title":"VALSE: A Task-Independent Benchmark for Vision and Language Models Centered on Linguistic Phenomena","created":"2021-12-14","cited_by_count":135},{"id":"2207.00221","title":"VL-CheckList: Evaluating Pre-trained Vision-Language Models with Objects, Attributes and Relations","created":"2022-07-01","cited_by_count":114},{"id":"2304.03843","title":"Why think step by step? Reasoning emerges from the locality of experience","created":"2023-04-07","cited_by_count":103},{"id":"1909.12000","title":"CoPhy: Counterfactual Learning of Physical Dynamics","created":"2019-09-26","cited_by_count":81},{"id":"2104.05832","title":"SpartQA: : A Textual Question Answering Benchmark for Spatial Reasoning","created":"2021-04-12","cited_by_count":77},{"id":"2410.23266","title":"TOMATO: Assessing Visual Temporal Reasoning Capabilities in Multimodal Foundation Models","created":"2024-10-30","cited_by_count":73},{"id":"2410.17385","title":"Do Vision-Language Models Represent Space and How? Evaluating Spatial Frame of Reference Under Ambiguities","created":"2024-10-22","cited_by_count":59},{"id":"1908.02660","title":"SpatialSense: An Adversarially Crowdsourced Benchmark for Spatial Relation Recognition","created":"2019-08-07","cited_by_count":55},{"id":"2306.15668","title":"Physion++: Evaluating Physical Scene Understanding that Requires Online Inference of Different Physical Properties","created":"2023-06-27","cited_by_count":54},{"id":"1704.04517","title":"ShapeWorld - A new test methodology for multimodal language understanding","created":"2017-04-14","cited_by_count":37},{"id":"2407.16711","title":"Benchmarks as Microscopes: A Call for Model Metrology","created":"2024-07-22","cited_by_count":35},{"id":"2406.17126","title":"MM-SpuBench: Towards Better Understanding of Spurious Biases in Multimodal LLMs","created":"2024-06-24","cited_by_count":33},{"id":"2012.01634","title":"Rel3D: A Minimally Contrastive Benchmark for Grounding Spatial Relations in 3D","created":"2020-12-03","cited_by_count":30},{"id":"2412.05152","title":"Navigating Shortcuts, Spurious Correlations, and Confounders: From Origins via Detection to Mitigation","created":"2024-12-06","cited_by_count":25},{"id":"2407.01418","title":"RoboPack: Learning Tactile-Informed Dynamics Models for Dense Packing","created":"2024-07-01","cited_by_count":19},{"id":"2503.11999","title":"Diffusion Dynamics Models with Generative State Estimation for Cloth Manipulation","created":"2025-03-15","cited_by_count":19},{"id":"2410.04659","title":"ActiView: Evaluating Active Perception Ability for Multimodal Large Language Models","created":"2024-10-07","cited_by_count":11},{"id":"2102.06448","title":"The MSR-Video to Text Dataset with Clean Annotations","created":"2021-02-12","cited_by_count":8},{"id":"2412.10908","title":"Do large language vision models understand 3D shapes?","created":"2024-12-14","cited_by_count":2},{"id":"2311.13874","title":"Transitive inference as probabilistic preference learning","created":"2023-11-23","cited_by_count":1},{"id":"2407.18391","title":"UOUO: Uncontextualized Uncommon Objects for Measuring Knowledge Horizons of Vision Language Models","created":"2024-07-25","cited_by_count":1}],"next_cursor":null}