{"list":"other","total":52,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"2501.12948","title":"DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning","created":"2025-01-22","cited_by_count":6330},{"id":"2204.14198","title":"Flamingo: a Visual Language Model for Few-Shot Learning","created":"2022-04-29","cited_by_count":4386},{"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":"2201.03545","title":"A ConvNet for the 2020s","created":"2022-01-10","cited_by_count":3579},{"id":"1702.04405","title":"ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes","created":"2017-02-14","cited_by_count":3117},{"id":"2408.03326","title":"LLaVA-OneVision: Easy Visual Task Transfer","created":"2024-08-06","cited_by_count":2719},{"id":"1505.00468","title":"VQA: Visual Question Answering","created":"2015-05-03","cited_by_count":2506},{"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":"2103.03206","title":"Perceiver: General Perception with Iterative Attention","created":"2021-03-04","cited_by_count":1104},{"id":"2412.05579","title":"LLMs-as-Judges: A Comprehensive Survey on LLM-based Evaluation Methods","created":"2024-12-07","cited_by_count":465},{"id":"2206.06994","title":"ProcTHOR: Large-Scale Embodied AI Using Procedural Generation","created":"2022-06-14","cited_by_count":380},{"id":"2302.04166","title":"GPTScore: Evaluate as You Desire","created":"2023-02-08","cited_by_count":361},{"id":"1502.05698","title":"Towards AI-Complete Question Answering: A Set of Prerequisite Toy Tasks","created":"2015-02-19","cited_by_count":314},{"id":"2505.15966","title":"Pixel Reasoner: Incentivizing Pixel-Space Reasoning with Curiosity-Driven Reinforcement Learning","created":"2025-05-21","cited_by_count":278},{"id":"2305.14836","title":"NuScenes-QA: A Multi-modal Visual Question Answering Benchmark for Autonomous Driving Scenario","created":"2023-05-24","cited_by_count":262},{"id":"2505.23747","title":"Spatial-MLLM: Boosting MLLM Capabilities in Visual-based Spatial Intelligence","created":"2025-05-29","cited_by_count":217},{"id":"2405.09711","title":"STAR: A Benchmark for Situated Reasoning in Real-World Videos","created":"2024-05-15","cited_by_count":213},{"id":"2501.07542","title":"Imagine while Reasoning in Space: Multimodal Visualization-of-Thought","created":"2025-01-13","cited_by_count":206},{"id":"2309.00615","title":"Point-Bind & Point-LLM: Aligning Point Cloud with Multi-modality for 3D Understanding, Generation, and Instruction Following","created":"2023-09-01","cited_by_count":194},{"id":"2409.18125","title":"LLaVA-3D: A Simple yet Effective Pathway to Empowering LMMs with 3D-awareness","created":"2024-09-26","cited_by_count":183},{"id":"1803.08495","title":"Text2Shape: Generating Shapes from Natural Language by Learning Joint Embeddings","created":"2018-03-22","cited_by_count":169},{"id":"2306.06687","title":"LAMM: Language-Assisted Multi-Modal Instruction-Tuning Dataset, Framework, and Benchmark","created":"2023-06-11","cited_by_count":169},{"id":"2412.07755","title":"SAT: Dynamic Spatial Aptitude Training for Multimodal Language Models","created":"2024-12-10","cited_by_count":114},{"id":"2111.12702","title":"Density-aware Chamfer Distance as a Comprehensive Metric for Point Cloud Completion","created":"2021-11-24","cited_by_count":112},{"id":"2410.08189","title":"SG-Nav: Online 3D Scene Graph Prompting for LLM-based Zero-shot Object Navigation","created":"2024-10-10","cited_by_count":109},{"id":"2003.05161","title":"A Benchmark for Systematic Generalization in Grounded Language Understanding","created":"2020-03-11","cited_by_count":108},{"id":"2305.13711","title":"LLM-Eval: Unified Multi-Dimensional Automatic Evaluation for Open-Domain Conversations with Large Language Models","created":"2023-05-23","cited_by_count":101},{"id":"2506.21458","title":"MindCube: Spatial Mental Modeling from Limited Views","created":"2025-06-26","cited_by_count":95},{"id":"2305.06311","title":"Automatic Evaluation of Attribution by Large Language Models","created":"2023-05-10","cited_by_count":72},{"id":"2410.04840","title":"Strong Model Collapse","created":"2024-10-07","cited_by_count":65},{"id":"2509.13317","title":"3D Aware Region Prompted Vision Language Model","created":"2025-09-16","cited_by_count":33},{"id":"2507.21028","title":"Multi-Agent-as-Judge: Aligning LLM-Agent-Based Automated Evaluation with Multi-Dimensional Human Evaluation","created":"2025-07-28","cited_by_count":30},{"id":"2403.11835","title":"Agent3D-Zero: An Agent for Zero-shot 3D Understanding","created":"2024-03-18","cited_by_count":29},{"id":"2402.03327","title":"Uni3D-LLM: Unifying Point Cloud Perception, Generation and Editing with Large Language Models","created":"2024-01-09","cited_by_count":25},{"id":"2103.08022","title":"Success Weighted by Completion Time: A Dynamics-Aware Evaluation Criteria for Embodied Navigation","created":"2021-03-14","cited_by_count":22},{"id":"2506.04633","title":"Unfolding Spatial Cognition: Evaluating Multimodal Models on Visual Simulations","created":"2025-06-05","cited_by_count":21},{"id":"2410.05193","title":"RevisEval: Improving LLM-as-a-Judge via Response-Adapted References","created":"2024-10-07","cited_by_count":20},{"id":"2311.00530","title":"Advances in Embodied Navigation Using Large Language Models: A Survey","created":"2023-11-01","cited_by_count":14},{"id":"2505.12363","title":"Towards Visuospatial Cognition via Hierarchical Fusion of Visual Experts","created":"2025-05-18","cited_by_count":11},{"id":"2411.11150","title":"A Comprehensive Survey on Visual Question Answering Datasets and Algorithms","created":"2024-11-17","cited_by_count":8},{"id":"2311.05298","title":"Improving Vision-and-Language Reasoning via Spatial Relations Modeling","created":"2023-11-09","cited_by_count":5},{"id":"2106.00954","title":"When and Why does a Model Fail? A Human-in-the-loop Error Detection Framework for Sentiment Analysis","created":"2021-06-02","cited_by_count":4},{"id":"2404.03498","title":"Integrating Large Language Models with Multimodal Virtual Reality Interfaces to Support Collaborative Human-Robot Construction Work","created":"2024-04-04","cited_by_count":2},{"id":"2502.14748","title":"Large Language Models Struggle to Describe the Haystack without Human Help: Human-in-the-loop Evaluation of Topic Models","created":"2025-02-20","cited_by_count":2},{"id":"2505.22429","title":"Zero-Shot 3D Visual Grounding from Vision-Language Models","created":"2025-05-28","cited_by_count":2}],"next_cursor":null}