{"list":"other","total":102,"rows":[{"id":"2402.03300","title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","created":"2024-02-05","cited_by_count":9379},{"id":"2308.04079","title":"3D Gaussian Splatting for Real-Time Radiance Field Rendering","created":"2023-08-08","cited_by_count":6226},{"id":"2408.00714","title":"SAM 2: Segment Anything in Images and Videos","created":"2024-08-01","cited_by_count":2863},{"id":"2503.14476","title":"DAPO: An Open-Source LLM Reinforcement Learning System at Scale","created":"2025-03-18","cited_by_count":2810},{"id":"2511.21631","title":"Qwen3-VL Technical Report","created":"2025-11-26","cited_by_count":2793},{"id":"2503.20783","title":"Understanding R1-Zero-Like Training: A Critical Perspective","created":"2025-03-26","cited_by_count":1345},{"id":"2511.16719","title":"SAM 3: Segment Anything with Concepts","created":"2025-11-20","cited_by_count":906},{"id":"2311.04400","title":"LRM: Large Reconstruction Model for Single Image to 3D","created":"2023-11-08","cited_by_count":849},{"id":"1711.00199","title":"PoseCNN: A Convolutional Neural Network for 6D Object Pose Estimation in Cluttered Scenes","created":"2017-11-01","cited_by_count":775},{"id":"2401.12168","title":"SpatialVLM: Endowing Vision-Language Models with Spatial Reasoning Capabilities","created":"2024-01-22","cited_by_count":706},{"id":"1912.08830","title":"ScanRefer: 3D Object Localization in RGB-D Scans using Natural Language","created":"2019-12-18","cited_by_count":452},{"id":"2312.08344","title":"FoundationPose: Unified 6D Pose Estimation and Tracking of Novel Objects","created":"2023-12-13","cited_by_count":429},{"id":"2103.15875","title":"In-Place Scene Labelling and Understanding with Implicit Scene Representation","created":"2021-03-29","cited_by_count":415},{"id":"2312.00732","title":"Gaussian Grouping: Segment and Edit Anything in 3D Scenes","created":"2023-12-01","cited_by_count":393},{"id":"2012.05877","title":"INeRF: Inverting Neural Radiance Fields for Pose Estimation","created":"2020-12-10","cited_by_count":382},{"id":"2011.09127","title":"3D-FRONT: 3D Furnished Rooms with layOuts and semaNTics","created":"2020-11-18","cited_by_count":380},{"id":"2309.16650","title":"ConceptGraphs: Open-Vocabulary 3D Scene Graphs for Perception and Planning","created":"2023-09-28","cited_by_count":365},{"id":"2507.13347","title":"$\\pi^3$: Permutation-Equivariant Visual Geometry Learning","created":"2025-07-17","cited_by_count":319},{"id":"2306.13631","title":"OpenMask3D: Open-Vocabulary 3D Instance Segmentation","created":"2023-06-23","cited_by_count":289},{"id":"2008.08465","title":"CosyPose: Consistent multi-view multi-object 6D pose estimation","created":"2020-08-19","cited_by_count":287},{"id":"1804.00175","title":"DeepIM: Deep Iterative Matching for 6D Pose Estimation","created":"2018-03-31","cited_by_count":283},{"id":"2312.09067","title":"Holodeck: Language Guided Generation of 3D Embodied AI Environments","created":"2023-12-14","cited_by_count":268},{"id":"2511.16624","title":"SAM 3D: 3Dfy Anything in Images","created":"2025-11-20","cited_by_count":247},{"id":"2205.04334","title":"Panoptic Neural Fields: A Semantic Object-Aware Neural Scene Representation","created":"2022-05-09","cited_by_count":243},{"id":"2403.02151","title":"TripoSR: Fast 3D Object Reconstruction from a Single Image","created":"2024-03-04","cited_by_count":232},{"id":"2109.01847","title":"Learning Object-Compositional Neural Radiance Field for Editable Scene Rendering","created":"2021-09-04","cited_by_count":228},{"id":"2308.04352","title":"3D-VisTA: Pre-trained Transformer for 3D Vision and Text Alignment","created":"2023-08-08","cited_by_count":204},{"id":"2212.06870","title":"MegaPose: 6D Pose Estimation of Novel Objects via Render & Compare","created":"2022-12-13","cited_by_count":201},{"id":"2403.17846","title":"Hierarchical Open-Vocabulary 3D Scene Graphs for Language-Grounded Robot Navigation","created":"2024-03-26","cited_by_count":196},{"id":"1703.09327","title":"DART: Noise Injection for Robust Imitation Learning","created":"2017-03-27","cited_by_count":191},{"id":"2212.09802","title":"Panoptic Lifting for 3D Scene Understanding with Neural Fields","created":"2022-12-19","cited_by_count":174},{"id":"2002.12212","title":"Total3DUnderstanding: Joint Layout, Object Pose and Mesh Reconstruction for Indoor Scenes from a Single Image","created":"2020-02-27","cited_by_count":172},{"id":"2306.06362","title":"Aria Digital Twin: A New Benchmark Dataset for Egocentric 3D Machine Perception","created":"2023-06-10","cited_by_count":167},{"id":"2207.10660","title":"Omni3D: A Large Benchmark and Model for 3D Object Detection in the Wild","created":"2022-07-21","cited_by_count":160},{"id":"2106.01178","title":"ImVoxelNet: Image to Voxels Projection for Monocular and Multi-View General-Purpose 3D Object Detection","created":"2021-06-02","cited_by_count":157},{"id":"2306.03908","title":"SAM3D: Segment Anything in 3D Scenes","created":"2023-06-06","cited_by_count":157},{"id":"2309.05251","title":"Multi3DRefer: Grounding Text Description to Multiple 3D Objects","created":"2023-09-11","cited_by_count":146},{"id":"2403.03949","title":"Reconciling Reality through Simulation: A Real-to-Sim-to-Real Approach for Robust Manipulation","created":"2024-03-06","cited_by_count":144},{"id":"1811.11187","title":"Scan2CAD: Learning CAD Model Alignment in RGB-D Scans","created":"2018-11-27","cited_by_count":142},{"id":"2309.12311","title":"LLM-Grounder: Open-Vocabulary 3D Visual Grounding with Large Language Model as an Agent","created":"2023-09-21","cited_by_count":135},{"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":"2404.09465","title":"PhyScene: Physically Interactable 3D Scene Synthesis for Embodied AI","created":"2024-04-15","cited_by_count":125},{"id":"2412.03558","title":"MIDI: Multi-Instance Diffusion for Single Image to 3D Scene Generation","created":"2024-12-04","cited_by_count":117},{"id":"2502.12894","title":"CAST: Component-Aligned 3D Scene Reconstruction from an RGB Image","created":"2025-02-18","cited_by_count":106},{"id":"2107.07905","title":"Unsupervised Discovery of Object Radiance Fields","created":"2021-07-16","cited_by_count":101},{"id":"2209.14941","title":"EDA: Explicit Text-Decoupling and Dense Alignment for 3D Visual Grounding","created":"2022-09-29","cited_by_count":99},{"id":"1808.08378","title":"Fusion++: Volumetric Object-Level SLAM","created":"2018-08-25","cited_by_count":98},{"id":"2103.06422","title":"Holistic 3D Scene Understanding from a Single Image with Implicit Representation","created":"2021-03-11","cited_by_count":94},{"id":"2410.07408","title":"Automated Creation of Digital Cousins for Robust Policy Learning","created":"2024-10-09","cited_by_count":91},{"id":"2511.05491","title":"Visual Spatial Tuning","created":"2025-11-07","cited_by_count":89},{"id":"2207.09686","title":"Object-Compositional Neural Implicit Surfaces","created":"2022-07-20","cited_by_count":74},{"id":"2112.01988","title":"ROCA: Robust CAD Model Retrieval and Alignment from a Single Image","created":"2021-12-03","cited_by_count":67},{"id":"2302.01838","title":"vMAP: Vectorised Object Mapping for Neural Field SLAM","created":"2023-02-03","cited_by_count":67},{"id":"2412.04383","title":"SeeGround: See and Ground for Zero-Shot Open-Vocabulary 3D Visual Grounding","created":"2024-12-05","cited_by_count":67},{"id":"2007.13034","title":"Mask2CAD: 3D Shape Prediction by Learning to Segment and Retrieve","created":"2020-07-26","cited_by_count":65},{"id":"2404.03421","title":"Gen3DSR: Generalizable 3D Scene Reconstruction via Divide and Conquer from a Single View","created":"2024-04-04","cited_by_count":61},{"id":"2401.07745","title":"MaskClustering: View Consensus based Mask Graph Clustering for Open-Vocabulary 3D Instance Segmentation","created":"2024-01-15","cited_by_count":56},{"id":"2410.13860","title":"VLM-Grounder: A VLM Agent for Zero-Shot 3D Visual Grounding","created":"2024-10-17","cited_by_count":56},{"id":"2503.13439","title":"Amodal3R: Amodal 3D Reconstruction from Occluded 2D Images","created":"2025-03-17","cited_by_count":54},{"id":"2508.15769","title":"SceneGen: Single-Image 3D Scene Generation in One Feedforward Pass","created":"2025-08-21","cited_by_count":54},{"id":"1810.13049","title":"Cooperative Holistic Scene Understanding: Unifying 3D Object, Layout, and Camera Pose Estimation","created":"2018-10-31","cited_by_count":51},{"id":"2307.14620","title":"NeRF-Det: Learning Geometry-Aware Volumetric Representation for Multi-View 3D Object Detection","created":"2023-07-27","cited_by_count":51},{"id":"2503.18673","title":"Any6D: Model-free 6D Pose Estimation of Novel Objects","created":"2025-03-24","cited_by_count":49},{"id":"2311.18610","title":"DiffCAD: Weakly-Supervised Probabilistic CAD Model Retrieval and Alignment from an RGB Image","created":"2023-11-30","cited_by_count":48},{"id":"2412.18605","title":"Orient Anything: Learning Robust Object Orientation Estimation from Rendering 3D Models","created":"2024-12-24","cited_by_count":45},{"id":"2003.12622","title":"SceneCAD: Predicting Object Alignments and Layouts in RGB-D Scans","created":"2020-03-27","cited_by_count":44},{"id":"2408.11811","title":"EmbodiedSAM: Online Segment Any 3D Thing in Real Time","created":"2024-08-21","cited_by_count":40},{"id":"2308.07868","title":"ObjectSDF++: Improved Object-Compositional Neural Implicit Surfaces","created":"2023-08-15","cited_by_count":39},{"id":"2412.04458","title":"Cubify Anything: Scaling Indoor 3D Object Detection","created":"2024-12-05","cited_by_count":39},{"id":"2410.15971","title":"Zero-Shot Scene Reconstruction from Single Images with Deep Prior Assembly","created":"2024-10-21","cited_by_count":35},{"id":"2504.07958","title":"Detect Anything 3D in the Wild","created":"2025-04-10","cited_by_count":33},{"id":"2507.13346","title":"AutoPartGen: Autogressive 3D Part Generation and Discovery","created":"2025-07-17","cited_by_count":33},{"id":"2405.03685","title":"Language-Image Models with 3D Understanding","created":"2024-05-06","cited_by_count":31},{"id":"2505.02388","title":"MetaScenes: Towards Automated Replica Creation for Real-world 3D Scans","created":"2025-05-05","cited_by_count":31},{"id":"2601.17895","title":"Masked Depth Modeling for Spatial Perception","created":"2026-01-25","cited_by_count":28},{"id":"2403.16210","title":"Frankenstein: Generating Semantic-Compositional 3D Scenes in One Tri-Plane","created":"2024-03-24","cited_by_count":26},{"id":"2503.04919","title":"FirePlace: Geometric Refinements of LLM Common Sense Reasoning for 3D Object Placement","created":"2025-03-06","cited_by_count":25},{"id":"2103.15231","title":"ReAgent: Point Cloud Registration using Imitation and Reinforcement Learning","created":"2021-03-28","cited_by_count":23},{"id":"2411.16833","title":"Open Vocabulary Monocular 3D Object Detection","created":"2024-11-25","cited_by_count":23},{"id":"2509.01106","title":"Robix: A Unified Model for Robot Interaction, Reasoning and Planning","created":"2025-09-01","cited_by_count":23},{"id":"2009.12678","title":"I Like to Move It: 6D Pose Estimation as an Action Decision Process","created":"2020-09-26","cited_by_count":22},{"id":"2601.11514","title":"ShapeR: Robust Conditional 3D Shape Generation from Casual Captures","created":"2026-01-16","cited_by_count":22},{"id":"2410.23643","title":"SceneComplete: Open-World 3D Scene Completion in Cluttered Real World Environments for Robot Manipulation","created":"2024-10-31","cited_by_count":18},{"id":"2504.13072","title":"HiScene: Creating Hierarchical 3D Scenes with Isometric View Generation","created":"2025-04-17","cited_by_count":18},{"id":"2509.22281","title":"MesaTask: Towards Task-Driven Tabletop Scene Generation via 3D Spatial Reasoning","created":"2025-09-26","cited_by_count":16},{"id":"2102.12096","title":"PFRL: Pose-Free Reinforcement Learning for 6D Pose Estimation","created":"2021-02-24","cited_by_count":14},{"id":"2510.05560","title":"HoloScene: Simulation-Ready Interactive 3D Worlds from a Single Video","created":"2025-10-07","cited_by_count":14},{"id":"2604.08626","title":"WildDet3D: Scaling Promptable 3D Detection in the Wild","created":"2026-04-09","cited_by_count":14},{"id":"2603.02133","title":"SimRecon: SimReady Compositional Scene Reconstruction from Real Videos","created":"2026-03-02","cited_by_count":12},{"id":"2310.00463","title":"Diff-DOPE: Differentiable Deep Object Pose Estimation","created":"2023-09-30","cited_by_count":11},{"id":"1612.03779","title":"PoseAgent: Budget-Constrained 6D Object Pose Estimation via Reinforcement Learning","created":"2016-12-12","cited_by_count":9},{"id":"2505.05288","title":"PlaceIt3D: Language-Guided Object Placement in Real 3D Scenes","created":"2025-05-08","cited_by_count":9},{"id":"2604.05212","title":"Boxer: Robust Lifting of Open-World 2D Bounding Boxes to 3D","created":"2026-04-06","cited_by_count":7},{"id":"2604.27106","title":"Reconstruction by Generation: 3D Multi-Object Scene Reconstruction from Sparse Observations","created":"2026-04-29","cited_by_count":7},{"id":"2201.00239","title":"SporeAgent: Reinforced Scene-level Plausibility for Object Pose Refinement","created":"2022-01-01","cited_by_count":4},{"id":"2512.22351","title":"VULCAN: Tool-Augmented Multi Agents for Iterative 3D Object Arrangement","created":"2025-12-26","cited_by_count":4},{"id":"2604.09781","title":"Text-Guided 6D Object Pose Rearrangement via Closed-Loop VLM Agents","created":"2026-04-10","cited_by_count":4},{"id":"2605.13862","title":"Seed3D 2.0: Advancing High-Fidelity Simulation-Ready 3D Content Generation","created":"2026-04-22","cited_by_count":4},{"id":"2312.02985","title":"FocalPose++: Focal Length and Object Pose Estimation via Render and Compare","created":"2023-11-15","cited_by_count":3},{"id":"2506.15610","title":"BoxFusion: Reconstruction-Free Open-Vocabulary 3D Object Detection via Real-Time Multi-View Box Fusion","created":"2025-06-18","cited_by_count":3}],"next_cursor":"100"}