{"list":"other","total":55,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"1807.03748","title":"Representation Learning with Contrastive Predictive Coding","created":"2018-07-10","cited_by_count":7777},{"id":"2301.12597","title":"BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models","created":"2023-01-30","cited_by_count":6137},{"id":"2502.13923","title":"Qwen2.5-VL Technical Report","created":"2025-02-19","cited_by_count":5587},{"id":"2410.21276","title":"GPT-4o System Card","created":"2024-10-25","cited_by_count":4588},{"id":"2403.05530","title":"Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context","created":"2024-03-08","cited_by_count":3224},{"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":"2408.03326","title":"LLaVA-OneVision: Easy Visual Task Transfer","created":"2024-08-06","cited_by_count":2719},{"id":"1411.5726","title":"CIDEr: Consensus-based Image Description Evaluation","created":"2014-11-20","cited_by_count":2046},{"id":"1812.05784","title":"PointPillars: Fast Encoders for Object Detection from Point Clouds","created":"2018-12-14","cited_by_count":1715},{"id":"1711.06396","title":"VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detection","created":"2017-11-17","cited_by_count":1323},{"id":"2311.17005","title":"MVBench: A Comprehensive Multi-modal Video Understanding Benchmark","created":"2023-11-28","cited_by_count":1109},{"id":"2111.14819","title":"Point-BERT: Pre-training 3D Point Cloud Transformers with Masked Point Modeling","created":"2021-11-29","cited_by_count":653},{"id":"1711.08488","title":"Frustum PointNets for 3D Object Detection from RGB-D Data","created":"2017-11-22","cited_by_count":640},{"id":"2102.06183","title":"Less is More: ClipBERT for Video-and-Language Learning via Sparse Sampling","created":"2021-02-11","cited_by_count":484},{"id":"2112.02413","title":"PointCLIP: Point Cloud Understanding by CLIP","created":"2021-12-04","cited_by_count":463},{"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":"1906.10770","title":"Deep Modular Co-Attention Networks for Visual Question Answering","created":"2019-06-25","cited_by_count":339},{"id":"2308.16911","title":"PointLLM: Empowering Large Language Models to Understand Point Clouds","created":"2023-08-31","cited_by_count":333},{"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":"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":"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":"2412.00493","title":"Video-3D LLM: Learning Position-Aware Video Representation for 3D Scene Understanding","created":"2024-11-30","cited_by_count":138},{"id":"2502.01143","title":"ASAP: Aligning Simulation and Real-World Physics for Learning Agile Humanoid Whole-Body Skills","created":"2025-02-03","cited_by_count":130},{"id":"2112.08879","title":"Bottom Up Top Down Detection Transformers for Language Grounding in Images and Point Clouds","created":"2021-12-16","cited_by_count":128},{"id":"2211.09646","title":"Language Conditioned Spatial Relation Reasoning for 3D Object Grounding","created":"2022-11-17","cited_by_count":122},{"id":"2405.10370","title":"Grounded 3D-LLM with Referent Tokens","created":"2024-05-16","cited_by_count":115},{"id":"2209.14941","title":"EDA: Explicit Text-Decoupling and Dense Alignment for 3D Visual Grounding","created":"2022-09-29","cited_by_count":99},{"id":"2405.04390","title":"DriveWorld: 4D Pre-trained Scene Understanding via World Models for Autonomous Driving","created":"2024-05-07","cited_by_count":93},{"id":"2301.02508","title":"End-to-End 3D Dense Captioning with Vote2Cap-DETR","created":"2023-01-06","cited_by_count":78},{"id":"2411.17735","title":"3D-Mem: 3D Scene Memory for Embodied Exploration and Reasoning","created":"2024-11-23","cited_by_count":75},{"id":"2111.02444","title":"Panoptic 3D Scene Reconstruction From a Single RGB Image","created":"2021-11-03","cited_by_count":70},{"id":"2203.00843","title":"X-Trans2Cap: Cross-Modal Knowledge Transfer using Transformer for 3D Dense Captioning","created":"2022-03-02","cited_by_count":70},{"id":"1809.03355","title":"Learning to Zoom: a Saliency-Based Sampling Layer for Neural Networks","created":"2018-09-10","cited_by_count":56},{"id":"2304.06061","title":"CLIP-Guided Vision-Language Pre-training for Question Answering in 3D Scenes","created":"2023-04-12","cited_by_count":55},{"id":"2507.04047","title":"Move to Understand a 3D Scene: Bridging Visual Grounding and Exploration for Efficient and Versatile Embodied Navigation","created":"2025-07-05","cited_by_count":51},{"id":"2203.05203","title":"MORE: Multi-Order RElation Mining for Dense Captioning in 3D Scenes","created":"2022-03-10","cited_by_count":46},{"id":"2406.07544","title":"Situational Awareness Matters in 3D Vision Language Reasoning","created":"2024-06-11","cited_by_count":33},{"id":"2108.12102","title":"FOVEA: Foveated Image Magnification for Autonomous Navigation","created":"2021-08-27","cited_by_count":32},{"id":"2307.13363","title":"3DRP-Net: 3D Relative Position-aware Network for 3D Visual Grounding","created":"2023-07-25","cited_by_count":25},{"id":"2507.22825","title":"DepR: Depth Guided Single-view Scene Reconstruction with Instance-level Diffusion","created":"2025-07-30","cited_by_count":23},{"id":"2411.17030","title":"g3D-LF: Generalizable 3D-Language Feature Fields for Embodied Tasks","created":"2024-11-26","cited_by_count":22},{"id":"2407.15087","title":"Navigation Instruction Generation with BEV Perception and Large Language Models","created":"2024-07-21","cited_by_count":21},{"id":"1708.02421","title":"FoveaNet: Perspective-aware Urban Scene Parsing","created":"2017-08-08","cited_by_count":12},{"id":"2502.00342","title":"Embodied Intelligence for 3D Understanding: A Survey on 3D Scene Question Answering","created":"2025-02-01","cited_by_count":11}],"next_cursor":null}