{"list":"other","total":51,"rows":[{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"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":"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":"1702.04405","title":"ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes","created":"2017-02-14","cited_by_count":3117},{"id":"2303.15343","title":"Sigmoid Loss for Language Image Pre-Training","created":"2023-03-27","cited_by_count":3109},{"id":"2307.15818","title":"RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control","created":"2023-07-28","cited_by_count":3080},{"id":"1505.00468","title":"VQA: Visual Question Answering","created":"2015-05-03","cited_by_count":2506},{"id":"1703.04977","title":"What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?","created":"2017-03-15","cited_by_count":2352},{"id":"2307.06281","title":"MMBench: Is Your Multi-modal Model an All-around Player?","created":"2023-07-12","cited_by_count":2141},{"id":"2303.03378","title":"PaLM-E: An Embodied Multimodal Language Model","created":"2023-03-06","cited_by_count":2071},{"id":"1411.5726","title":"CIDEr: Consensus-based Image Description Evaluation","created":"2014-11-20","cited_by_count":2046},{"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":"2503.11651","title":"VGGT: Visual Geometry Grounded Transformer","created":"2025-03-14","cited_by_count":1539},{"id":"2501.12387","title":"Continuous 3D Perception Model with Persistent State","created":"2025-01-21","cited_by_count":548},{"id":"2402.12289","title":"DriveVLM: The Convergence of Autonomous Driving and Large Vision-Language Models","created":"2024-02-19","cited_by_count":490},{"id":"2206.06994","title":"ProcTHOR: Large-Scale Embodied AI Using Procedural Generation","created":"2022-06-14","cited_by_count":380},{"id":"2311.12871","title":"An Embodied Generalist Agent in 3D World","created":"2023-11-18","cited_by_count":365},{"id":"2112.10482","title":"ScanQA: 3D Question Answering for Spatial Scene Understanding","created":"2021-12-20","cited_by_count":346},{"id":"2505.23747","title":"Spatial-MLLM: Boosting MLLM Capabilities in Visual-based Spatial Intelligence","created":"2025-05-29","cited_by_count":217},{"id":"2308.04352","title":"3D-VisTA: Pre-trained Transformer for 3D Vision and Text Alignment","created":"2023-08-08","cited_by_count":204},{"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":"2312.08168","title":"Chat-Scene: Bridging 3D Scene and Large Language Models with Object Identifiers","created":"2023-12-13","cited_by_count":175},{"id":"2505.20279","title":"VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction","created":"2025-05-26","cited_by_count":166},{"id":"2412.00493","title":"Video-3D LLM: Learning Position-Aware Video Representation for 3D Scene Understanding","created":"2024-11-30","cited_by_count":138},{"id":"2503.22976","title":"From Flatland to Space: Teaching Vision-Language Models to Perceive and Reason in 3D","created":"2025-03-29","cited_by_count":138},{"id":"2401.09340","title":"SceneVerse: Scaling 3D Vision-Language Learning for Grounded Scene Understanding","created":"2024-01-17","cited_by_count":133},{"id":"2312.00438","title":"Dolphins: Multimodal Language Model for Driving","created":"2023-12-01","cited_by_count":124},{"id":"2505.24625","title":"Learning from Videos for 3D World: Enhancing MLLMs with 3D Vision Geometry Priors","created":"2025-05-30","cited_by_count":120},{"id":"2412.07755","title":"SAT: Dynamic Spatial Aptitude Training for Multimodal Language Models","created":"2024-12-10","cited_by_count":114},{"id":"2501.01428","title":"GPT4Scene: Understand 3D Scenes from Videos with Vision-Language Models","created":"2025-01-02","cited_by_count":109},{"id":"2405.14062","title":"ChatScene: Knowledge-Enabled Safety-Critical Scenario Generation for Autonomous Vehicles","created":"2024-05-22","cited_by_count":93},{"id":"2405.11442","title":"Unifying 3D Vision-Language Understanding via Promptable Queries","created":"2024-05-19","cited_by_count":70},{"id":"2501.01163","title":"3D-LLaVA: Towards Generalist 3D LMMs with Omni Superpoint Transformer","created":"2025-01-02","cited_by_count":68},{"id":"2504.01901","title":"Ross3D: Reconstructive Visual Instruction Tuning with 3D-Awareness","created":"2025-04-02","cited_by_count":63},{"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":"2505.17015","title":"Multi-SpatialMLLM: Multi-Frame Spatial Understanding with Multi-Modal Large Language Models","created":"2025-05-22","cited_by_count":52},{"id":"2503.00513","title":"Inst3D-LMM: Instance-Aware 3D Scene Understanding with Multi-modal Instruction Tuning","created":"2025-03-01","cited_by_count":51},{"id":"2412.01292","title":"LSceneLLM: Enhancing Large 3D Scene Understanding Using Adaptive Visual Preferences","created":"2024-12-02","cited_by_count":38},{"id":"2311.15977","title":"Text2Loc: 3D Point Cloud Localization from Natural Language","created":"2023-11-27","cited_by_count":35},{"id":"2406.07544","title":"Situational Awareness Matters in 3D Vision Language Reasoning","created":"2024-06-11","cited_by_count":33},{"id":"2509.13317","title":"3D Aware Region Prompted Vision Language Model","created":"2025-09-16","cited_by_count":33},{"id":"2412.12693","title":"SPHERE: Unveiling Spatial Blind Spots in Vision-Language Models Through Hierarchical Evaluation","created":"2024-12-17","cited_by_count":31},{"id":"2410.00255","title":"Robin3D: Improving 3D Large Language Model via Robust Instruction Tuning","created":"2024-09-30","cited_by_count":26},{"id":"2503.06271","title":"SplatTalk: 3D VQA with Gaussian Splatting","created":"2025-03-08","cited_by_count":24},{"id":"2503.22420","title":"Unveiling the Mist over 3D Vision-Language Understanding: Object-centric Evaluation with Chain-of-Analysis","created":"2025-03-28","cited_by_count":23},{"id":"2301.05372","title":"Text to Point Cloud Localization with Relation-Enhanced Transformer","created":"2023-01-13","cited_by_count":20},{"id":"2409.12969","title":"Seeing Through Their Eyes: Evaluating Visual Perspective Taking in Vision Language Models","created":"2024-09-02","cited_by_count":15},{"id":"2505.22143","title":"3D Question Answering via only 2D Vision-Language Models","created":"2025-05-28","cited_by_count":10},{"id":"2503.02593","title":"CMMLoc: Advancing Text-to-PointCloud Localization with Cauchy-Mixture-Model Based Framework","created":"2025-03-04","cited_by_count":8},{"id":"2503.23024","title":"Empowering Large Language Models with 3D Situation Awareness","created":"2025-03-29","cited_by_count":6},{"id":"2404.17845","title":"Instance-free Text to Point Cloud Localization with Relative Position Awareness","created":"2024-04-27","cited_by_count":3}],"next_cursor":null}