{"list":"other","total":54,"rows":[{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"2501.12948","title":"DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning","created":"2025-01-22","cited_by_count":6330},{"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":"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":"2312.14238","title":"InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks","created":"2023-12-21","cited_by_count":2565},{"id":"2407.10671","title":"Qwen2 Technical Report","created":"2024-07-15","cited_by_count":2120},{"id":"2503.11651","title":"VGGT: Visual Geometry Grounded Transformer","created":"2025-03-14","cited_by_count":1539},{"id":"2502.14786","title":"SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features","created":"2025-02-20","cited_by_count":1188},{"id":"2211.15654","title":"OpenScene: 3D Scene Understanding with Open Vocabularies","created":"2022-11-28","cited_by_count":559},{"id":"2406.16852","title":"Long Context Transfer from Language to Vision","created":"2024-06-24","cited_by_count":515},{"id":"1912.08830","title":"ScanRefer: 3D Object Localization in RGB-D Scans using Natural Language","created":"2019-12-18","cited_by_count":452},{"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":"2308.16911","title":"PointLLM: Empowering Large Language Models to Understand Point Clouds","created":"2023-08-31","cited_by_count":333},{"id":"2210.03105","title":"Mask3D: Mask Transformer for 3D Semantic Instance Segmentation","created":"2022-10-06","cited_by_count":303},{"id":"2012.02206","title":"Scan2Cap: Context-aware Dense Captioning in RGB-D Scans","created":"2020-12-03","cited_by_count":218},{"id":"2308.04352","title":"3D-VisTA: Pre-trained Transformer for 3D Vision and Text Alignment","created":"2023-08-08","cited_by_count":204},{"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":"2502.12138","title":"FLARE: Feed-forward Geometry, Appearance and Camera Estimation from Uncalibrated Sparse Views","created":"2025-02-17","cited_by_count":180},{"id":"2404.08636","title":"Probing the 3D Awareness of Visual Foundation Models","created":"2024-04-12","cited_by_count":177},{"id":"2409.12961","title":"Oryx MLLM: On-Demand Spatial-Temporal Understanding at Arbitrary Resolution","created":"2024-09-19","cited_by_count":159},{"id":"2309.05251","title":"Multi3DRefer: Grounding Text Description to Multiple 3D Objects","created":"2023-09-11","cited_by_count":146},{"id":"2204.02174","title":"Multi-View Transformer for 3D Visual Grounding","created":"2022-04-05","cited_by_count":140},{"id":"2312.02010","title":"Towards Learning a Generalist Model for Embodied Navigation","created":"2023-12-04","cited_by_count":138},{"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":"2308.08769","title":"Chat-3D: Data-efficiently Tuning Large Language Model for Universal Dialogue of 3D Scenes","created":"2023-08-17","cited_by_count":129},{"id":"2211.09646","title":"Language Conditioned Spatial Relation Reasoning for 3D Object Grounding","created":"2022-11-17","cited_by_count":122},{"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":"2405.10370","title":"Grounded 3D-LLM with Referent Tokens","created":"2024-05-16","cited_by_count":115},{"id":"2501.01428","title":"GPT4Scene: Understand 3D Scenes from Videos with Vision-Language Models","created":"2025-01-02","cited_by_count":109},{"id":"2312.02980","title":"GPT4Point: A Unified Framework for Point-Language Understanding and Generation","created":"2023-12-05","cited_by_count":71},{"id":"2407.20229","title":"Improving 2D Feature Representations by 3D-Aware Fine-Tuning","created":"2024-07-29","cited_by_count":71},{"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":"2211.09386","title":"BEVDistill: Cross-Modal BEV Distillation for Multi-View 3D Object Detection","created":"2022-11-17","cited_by_count":66},{"id":"2104.11225","title":"Pri3D: Can 3D Priors Help 2D Representation Learning?","created":"2021-04-22","cited_by_count":61},{"id":"2112.01551","title":"D3Net: A Unified Speaker-Listener Architecture for 3D Dense Captioning and Visual Grounding","created":"2021-12-02","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":"2405.01413","title":"MiniGPT-3D: Efficiently Aligning 3D Point Clouds with Large Language Models using 2D Priors","created":"2024-05-02","cited_by_count":49},{"id":"2409.03757","title":"Lexicon3D: Probing Visual Foundation Models for Complex 3D Scene Understanding","created":"2024-09-05","cited_by_count":49},{"id":"2104.02243","title":"3D-to-2D Distillation for Indoor Scene Parsing","created":"2021-04-06","cited_by_count":48},{"id":"2309.15109","title":"DistillBEV: Boosting Multi-Camera 3D Object Detection with Cross-Modal Knowledge Distillation","created":"2023-09-26","cited_by_count":41},{"id":"2403.05061","title":"RadarDistill: Boosting Radar-based Object Detection Performance via Knowledge Distillation from LiDAR Features","created":"2024-03-08","cited_by_count":28},{"id":"2411.19458","title":"Multiview Equivariance Improves 3D Correspondence Understanding with Minimal Feature Finetuning","created":"2024-11-29","cited_by_count":14},{"id":"2503.16707","title":"Cross-Modal and Uncertainty-Aware Agglomeration for Open-Vocabulary 3D Scene Understanding","created":"2025-03-20","cited_by_count":13},{"id":"2408.15966","title":"More Text, Less Point: Towards 3D Data-Efficient Point-Language Understanding","created":"2024-08-28","cited_by_count":10},{"id":"2211.15059","title":"Learning Dense Object Descriptors from Multiple Views for Low-shot Category Generalization","created":"2022-11-28","cited_by_count":6},{"id":"2405.04103","title":"COM3D: Leveraging Cross-View Correspondence and Cross-Modal Mining for 3D Retrieval","created":"2024-05-07","cited_by_count":6}],"next_cursor":null}