{"list":"other","total":56,"rows":[{"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":"1504.08083","title":"Fast R-CNN","created":"2015-04-30","cited_by_count":2933},{"id":"2212.08051","title":"Objaverse: A Universe of Annotated 3D Objects","created":"2022-12-15","cited_by_count":1540},{"id":"2503.11651","title":"VGGT: Visual Geometry Grounded Transformer","created":"2025-03-14","cited_by_count":1539},{"id":"2307.05663","title":"Objaverse-XL: A Universe of 10M+ 3D Objects","created":"2023-07-11","cited_by_count":774},{"id":"2412.01506","title":"Structured 3D Latents for Scalable and Versatile 3D Generation","created":"2024-12-02","cited_by_count":770},{"id":"2011.09127","title":"3D-FRONT: 3D Furnished Rooms with layOuts and semaNTics","created":"2020-11-18","cited_by_count":380},{"id":"2505.09568","title":"BLIP3-o: A Family of Fully Open Unified Multimodal Models-Architecture, Training and Dataset","created":"2025-05-14","cited_by_count":376},{"id":"2110.06199","title":"ABO: Dataset and Benchmarks for Real-World 3D Object Understanding","created":"2021-10-12","cited_by_count":366},{"id":"2501.12202","title":"Hunyuan3D 2.0: Scaling Diffusion Models for High Resolution Textured 3D Assets Generation","created":"2025-01-21","cited_by_count":356},{"id":"2305.15393","title":"LayoutGPT: Compositional Visual Planning and Generation with Large Language Models","created":"2023-05-24","cited_by_count":347},{"id":"2507.13347","title":"$\\pi^3$: Permutation-Equivariant Visual Geometry Learning","created":"2025-07-17","cited_by_count":319},{"id":"2009.09633","title":"3D-FUTURE: 3D Furniture shape with TextURE","created":"2020-09-21","cited_by_count":311},{"id":"2410.19115","title":"MoGe: Unlocking Accurate Monocular Geometry Estimation for Open-Domain Images with Optimal Training Supervision","created":"2024-10-24","cited_by_count":299},{"id":"2312.09067","title":"Holodeck: Language Guided Generation of 3D Embodied AI Environments","created":"2023-12-14","cited_by_count":268},{"id":"2506.15564","title":"Show-o2: Improved Native Unified Multimodal Models","created":"2025-06-18","cited_by_count":250},{"id":"2511.16624","title":"SAM 3D: 3Dfy Anything in Images","created":"2025-11-20","cited_by_count":247},{"id":"2505.23747","title":"Spatial-MLLM: Boosting MLLM Capabilities in Visual-based Spatial Intelligence","created":"2025-05-29","cited_by_count":217},{"id":"2305.10764","title":"OpenShape: Scaling Up 3D Shape Representation Towards Open-World Understanding","created":"2023-05-18","cited_by_count":184},{"id":"2512.14692","title":"Native and Compact Structured Latents for 3D Generation","created":"2025-12-16","cited_by_count":175},{"id":"2604.15804","title":"Qwen3.5-Omni Technical Report","created":"2026-04-17","cited_by_count":174},{"id":"2505.00703","title":"T2I-R1: Reinforcing Image Generation with Collaborative Semantic-level and Token-level CoT","created":"2025-05-01","cited_by_count":166},{"id":"2412.03558","title":"MIDI: Multi-Instance Diffusion for Single Image to 3D Scene Generation","created":"2024-12-04","cited_by_count":117},{"id":"2412.03632","title":"MV-Adapter: Multi-view Consistent Image Generation Made Easy","created":"2024-12-04","cited_by_count":112},{"id":"2502.12894","title":"CAST: Component-Aligned 3D Scene Reconstruction from an RGB Image","created":"2025-02-18","cited_by_count":106},{"id":"2505.02567","title":"Unified Multimodal Understanding and Generation Models: Advances, Challenges, and Opportunities","created":"2025-05-05","cited_by_count":85},{"id":"2506.05573","title":"PartCrafter: Structured 3D Mesh Generation via Compositional Latent Diffusion Transformers","created":"2025-06-05","cited_by_count":84},{"id":"2410.16499","title":"SINGAPO: Single Image Controlled Generation of Articulated Parts in Objects","created":"2024-10-21","cited_by_count":69},{"id":"2506.09344","title":"Ming-Omni: A Unified Multimodal Model for Perception and Generation","created":"2025-06-11","cited_by_count":66},{"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":"2507.06165","title":"OmniPart: Part-Aware 3D Generation with Semantic Decoupling and Structural Cohesion","created":"2025-07-08","cited_by_count":61},{"id":"2508.15769","title":"SceneGen: Single-Image 3D Scene Generation in One Feedforward Pass","created":"2025-08-21","cited_by_count":54},{"id":"2602.10116","title":"SAGE: Scalable Agentic 3D Scene Generation for Embodied AI","created":"2026-02-10","cited_by_count":50},{"id":"2506.09980","title":"Efficient Part-level 3D Object Generation via Dual Volume Packing","created":"2025-06-11","cited_by_count":48},{"id":"2507.12465","title":"PhysX-3D: Physical-Grounded 3D Asset Generation","created":"2025-07-16","cited_by_count":42},{"id":"2506.01853","title":"ShapeLLM-Omni: A Native Multimodal LLM for 3D Generation and Understanding","created":"2025-06-02","cited_by_count":38},{"id":"2511.13648","title":"PhysX-Anything: Simulation-Ready Physical 3D Assets from Single Image","created":"2025-11-17","cited_by_count":37},{"id":"2505.14682","title":"UniGen: Enhanced Training & Test-Time Strategies for Unified Multimodal Understanding and Generation","created":"2025-05-20","cited_by_count":32},{"id":"2511.00279","title":"LongCat-Flash-Omni Technical Report","created":"2025-10-31","cited_by_count":26},{"id":"2507.05763","title":"DreamArt: Generating Interactable Articulated Objects from a Single Image","created":"2025-07-08","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":"2511.00940","title":"URDF-Anything: Constructing Articulated Objects with 3D Multimodal Language Model","created":"2025-11-02","cited_by_count":21},{"id":"2511.22850","title":"Resolving Evidence Sparsity: Agentic Context Engineering for Long-Document Understanding","created":"2025-11-28","cited_by_count":18},{"id":"2212.11473","title":"Restoring Vision in Hazy Weather with Hierarchical Contrastive Learning","created":"2022-12-22","cited_by_count":17},{"id":"2511.07222","title":"Omni-View: Unlocking How Generation Facilitates Understanding in Unified 3D Model based on Multiview images","created":"2025-11-10","cited_by_count":17},{"id":"2512.10957","title":"SceneMaker: Open-set 3D Scene Generation with Decoupled De-occlusion and Pose Estimation Model","created":"2025-12-11","cited_by_count":17},{"id":"2510.25970","title":"SplitFlow: Flow Decomposition for Inversion-Free Text-to-Image Editing","created":"2025-10-29","cited_by_count":16},{"id":"2604.04406","title":"3D-Fixer: Coarse-to-Fine In-place Completion for 3D Scenes from a Single Image","created":"2026-04-06","cited_by_count":11},{"id":"2508.11952","title":"UniUGG: Unified 3D Understanding and Generation via Geometric-Semantic Encoding","created":"2025-08-16","cited_by_count":10},{"id":"2510.15846","title":"3DPR: Single Image 3D Portrait Relight using Generative Priors","created":"2025-10-17","cited_by_count":8},{"id":"2605.21472","title":"Stream3D: Sequential Multi-View 3D Generation via Evidential Memory","created":"2026-05-20","cited_by_count":7},{"id":"2512.13683","title":"I-Scene: 3D Instance Models are Implicit Generalizable Spatial Learners","created":"2025-12-15","cited_by_count":6},{"id":"2602.07064","title":"OmniFysics: Towards Physical Intelligence Evolution via Omni-Modal Signal Processing and Network Optimization","created":"2026-02-05","cited_by_count":5},{"id":"2510.12095","title":"IL3D: A Large-Scale Indoor Layout Dataset for LLM-Driven 3D Scene Generation","created":"2025-10-14","cited_by_count":3},{"id":"2604.02289","title":"Omni123: Exploring 3D Native Foundation Models with Limited 3D Data by Unifying Text to 2D and 3D Generation","created":"2026-04-02","cited_by_count":3},{"id":"2512.13072","title":"Forging a Dynamic Memory: Retrieval-Guided Continual Learning for Generalist Medical Foundation Models","created":"2025-12-15","cited_by_count":1}],"next_cursor":null}