{"list":"other","total":106,"rows":[{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2502.13923","title":"Qwen2.5-VL Technical Report","created":"2025-02-19","cited_by_count":5587},{"id":"1711.00937","title":"Neural Discrete Representation Learning","created":"2017-11-02","cited_by_count":4712},{"id":"2209.14988","title":"DreamFusion: Text-to-3D using 2D Diffusion","created":"2022-09-29","cited_by_count":3025},{"id":"2211.10440","title":"Magic3D: High-Resolution Text-to-3D Content Creation","created":"2022-11-18","cited_by_count":1290},{"id":"2305.16213","title":"ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillation","created":"2023-05-25","cited_by_count":1219},{"id":"2508.02324","title":"Qwen-Image Technical Report","created":"2025-08-04","cited_by_count":1044},{"id":"2308.16512","title":"MVDream: Multi-view Diffusion for 3D Generation","created":"2023-08-31","cited_by_count":938},{"id":"2405.09818","title":"Chameleon: Mixed-Modal Early-Fusion Foundation Models","created":"2024-05-16","cited_by_count":927},{"id":"2505.14683","title":"Emerging Properties in Unified Multimodal Pretraining","created":"2025-05-20","cited_by_count":897},{"id":"2309.16653","title":"DreamGaussian: Generative Gaussian Splatting for Efficient 3D Content Creation","created":"2023-09-28","cited_by_count":843},{"id":"2501.17811","title":"Janus-Pro: Unified Multimodal Understanding and Generation with Data and Model Scaling","created":"2025-01-29","cited_by_count":812},{"id":"2409.18869","title":"Emu3: Next-Token Prediction is All You Need","created":"2024-09-27","cited_by_count":781},{"id":"2412.01506","title":"Structured 3D Latents for Scalable and Versatile 3D Generation","created":"2024-12-02","cited_by_count":770},{"id":"2303.13873","title":"Fantasia3D: Disentangling Geometry and Appearance for High-quality Text-to-3D Content Creation","created":"2023-03-24","cited_by_count":687},{"id":"1812.02713","title":"PartNet: A Large-scale Benchmark for Fine-grained and Hierarchical Part-level 3D Object Understanding","created":"2018-12-06","cited_by_count":526},{"id":"2303.12789","title":"Instruct-NeRF2NeRF: Editing 3D Scenes with Instructions","created":"2023-03-22","cited_by_count":484},{"id":"2301.11445","title":"3DShape2VecSet: A 3D Shape Representation for Neural Fields and Generative Diffusion Models","created":"2023-01-26","cited_by_count":458},{"id":"2406.13897","title":"CLAY: A Controllable Large-scale Generative Model for Creating High-quality 3D Assets","created":"2024-05-30","cited_by_count":455},{"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":"2308.16911","title":"PointLLM: Empowering Large Language Models to Understand Point Clouds","created":"2023-08-31","cited_by_count":333},{"id":"2310.08529","title":"GaussianDreamer: Fast Generation from Text to 3D Gaussians by Bridging 2D and 3D Diffusion Models","created":"2023-10-12","cited_by_count":255},{"id":"2509.20427","title":"Seedream 4.0: Toward Next-generation Multimodal Image Generation","created":"2025-09-24","cited_by_count":249},{"id":"2504.06256","title":"Transfer between Modalities with MetaQueries","created":"2025-04-08","cited_by_count":236},{"id":"2306.17115","title":"Michelangelo: Conditional 3D Shape Generation based on Shape-Image-Text Aligned Latent Representation","created":"2023-06-29","cited_by_count":228},{"id":"2502.06608","title":"TripoSG: High-Fidelity 3D Shape Synthesis using Large-Scale Rectified Flow Models","created":"2025-02-10","cited_by_count":213},{"id":"2412.14164","title":"MetaMorph: Multimodal Understanding and Generation via Instruction Tuning","created":"2024-12-18","cited_by_count":206},{"id":"2412.03069","title":"TokenFlow: Unified Image Tokenizer for Multimodal Understanding and Generation","created":"2024-12-04","cited_by_count":202},{"id":"2311.16918","title":"RichDreamer: A Generalizable Normal-Depth Diffusion Model for Detail Richness in Text-to-3D","created":"2023-11-28","cited_by_count":168},{"id":"2506.15442","title":"Hunyuan3D 2.1: From Images to High-Fidelity 3D Assets with Production-Ready PBR Material","created":"2025-06-18","cited_by_count":165},{"id":"2504.11346","title":"Seedream 3.0 Technical Report","created":"2025-04-15","cited_by_count":154},{"id":"2509.23951","title":"HunyuanImage 3.0 Technical Report","created":"2025-09-28","cited_by_count":149},{"id":"2406.10163","title":"MeshAnything: Artist-Created Mesh Generation with Autoregressive Transformers","created":"2024-06-14","cited_by_count":144},{"id":"2402.17766","title":"ShapeLLM: Universal 3D Object Understanding for Embodied Interaction","created":"2024-02-27","cited_by_count":137},{"id":"2506.16504","title":"Hunyuan3D 2.5: Towards High-Fidelity 3D Assets Generation with Ultimate Details","created":"2025-06-19","cited_by_count":125},{"id":"2405.14979","title":"CraftsMan3D: High-fidelity Mesh Generation with 3D Native Generation and Interactive Geometry Refiner","created":"2024-05-23","cited_by_count":123},{"id":"2408.02555","title":"MeshAnything V2: Artist-Created Mesh Generation With Adjacent Mesh Tokenization","created":"2024-08-05","cited_by_count":104},{"id":"2504.11451","title":"PARTFIELD: Learning 3D Feature Fields for Part Segmentation and Beyond","created":"2025-04-15","cited_by_count":95},{"id":"2412.09548","title":"Meshtron: High-Fidelity, Artist-Like 3D Mesh Generation at Scale","created":"2024-12-12","cited_by_count":89},{"id":"2505.14521","title":"Sparc3D: Sparse Representation and Construction for High-Resolution 3D Shapes Modeling","created":"2025-05-20","cited_by_count":89},{"id":"2409.18114","title":"EdgeRunner: Auto-regressive Auto-encoder for Artistic Mesh Generation","created":"2024-09-26","cited_by_count":87},{"id":"2503.21732","title":"SparseFlex: High-Resolution and Arbitrary-Topology 3D Shape Modeling","created":"2025-03-27","cited_by_count":79},{"id":"2401.14828","title":"TIP-Editor: An Accurate 3D Editor Following Both Text-Prompts And Image-Prompts","created":"2024-01-26","cited_by_count":77},{"id":"2411.07025","title":"Scaling Mesh Generation via Compressive Tokenization","created":"2024-11-11","cited_by_count":73},{"id":"2312.02980","title":"GPT4Point: A Unified Framework for Point-Language Understanding and Generation","created":"2023-12-05","cited_by_count":71},{"id":"2503.15265","title":"DeepMesh: Auto-Regressive Artist-mesh Creation with Reinforcement Learning","created":"2025-03-19","cited_by_count":65},{"id":"2507.06165","title":"OmniPart: Part-Aware 3D Generation with Semantic Decoupling and Structural Cohesion","created":"2025-07-08","cited_by_count":61},{"id":"2401.09050","title":"Consistent3D: Towards Consistent High-Fidelity Text-to-3D Generation with Deterministic Sampling Prior","created":"2024-01-17","cited_by_count":60},{"id":"2403.14613","title":"DreamReward: Text-to-3D Generation with Human Preference","created":"2024-03-21","cited_by_count":56},{"id":"2510.15857","title":"BLIP3o-NEXT: Next Frontier of Native Image Generation","created":"2025-10-17","cited_by_count":54},{"id":"2405.16890","title":"PivotMesh: Generic 3D Mesh Generation via Pivot Vertices Guidance","created":"2024-05-27","cited_by_count":50},{"id":"2403.12032","title":"Generic 3D Diffusion Adapter Using Controlled Multi-View Editing","created":"2024-03-18","cited_by_count":47},{"id":"2508.19247","title":"VoxHammer: Training-Free Precise and Coherent 3D Editing in Native 3D Space","created":"2025-08-26","cited_by_count":45},{"id":"2412.00518","title":"Instant3dit: Multiview Inpainting for Fast Editing of 3D Objects","created":"2024-11-30","cited_by_count":44},{"id":"2507.17745","title":"Ultra3D: Efficient and High-Fidelity 3D Generation with Part Attention","created":"2025-07-23","cited_by_count":44},{"id":"2509.08643","title":"X-Part: high fidelity and structure coherent shape decomposition","created":"2025-09-10","cited_by_count":44},{"id":"2512.03052","title":"LATTICE: Democratize High-Fidelity 3D Generation at Scale","created":"2025-11-24","cited_by_count":44},{"id":"2604.20329","title":"Image Generators are Generalist Vision Learners","created":"2026-04-22","cited_by_count":43},{"id":"2506.01853","title":"ShapeLLM-Omni: A Native Multimodal LLM for 3D Generation and Understanding","created":"2025-06-02","cited_by_count":38},{"id":"2312.09246","title":"SHAP-EDITOR: Instruction-guided Latent 3D Editing in Seconds","created":"2023-12-14","cited_by_count":37},{"id":"2410.16770","title":"The Scene Language: Representing Scenes with Programs, Words, and Embeddings","created":"2024-10-22","cited_by_count":36},{"id":"2407.06191","title":"Tailor3D: Customized 3D Assets Editing and Generation with Dual-Side Images","created":"2024-07-08","cited_by_count":35},{"id":"2403.09625","title":"Make-Your-3D: Fast and Consistent Subject-Driven 3D Content Generation","created":"2024-03-14","cited_by_count":32},{"id":"2510.15019","title":"NANO3D: A Training-Free Approach for Efficient 3D Editing Without Masks","created":"2025-10-16","cited_by_count":31},{"id":"2408.08000","title":"MVInpainter: Learning Multi-View Consistent Inpainting to Bridge 2D and 3D Editing","created":"2024-08-15","cited_by_count":30},{"id":"2510.06590","title":"Ming-UniVision: Joint Image Understanding and Generation with a Unified Continuous Tokenizer","created":"2025-10-08","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":"2510.20155","title":"PartNeXt: A Next-Generation Dataset for Fine-Grained and Hierarchical 3D Part Understanding","created":"2025-10-23","cited_by_count":26},{"id":"2404.16510","title":"Interactive3D: Create What You Want by Interactive 3D Generation","created":"2024-04-25","cited_by_count":21},{"id":"2506.20652","title":"EditP23: 3D Editing via Propagation of Image Prompts to Multi-View","created":"2025-06-25","cited_by_count":20},{"id":"2411.18548","title":"PhyCAGE: Physically Plausible Compositional 3D Asset Generation from a Single Image","created":"2024-11-27","cited_by_count":19},{"id":"2412.08641","title":"3D Mesh Editing using Masked LRMs","created":"2024-12-11","cited_by_count":18},{"id":"2508.19188","title":"FastMesh: Efficient Artistic Mesh Generation via Component Decoupling","created":"2025-08-26","cited_by_count":17},{"id":"2503.15475","title":"Cube: A Roblox View of 3D Intelligence","created":"2025-03-19","cited_by_count":15},{"id":"2503.23241","title":"Geometry in Style: 3D Stylization via Surface Normal Deformation","created":"2025-03-29","cited_by_count":14},{"id":"2509.12815","title":"Hunyuan3D Studio: End-to-End AI Pipeline for Game-Ready 3D Asset Generation","created":"2025-09-16","cited_by_count":13},{"id":"2506.00512","title":"Pro3D-Editor : A Progressive-Views Perspective for Consistent and Precise 3D Editing","created":"2025-05-31","cited_by_count":11},{"id":"2510.02994","title":"Towards Scalable and Consistent 3D Editing","created":"2025-10-03","cited_by_count":10},{"id":"2603.06357","title":"LATO: 3D Mesh Flow Matching with Structured TOpology Preserving LAtents","created":"2026-03-06","cited_by_count":10},{"id":"2605.27351","title":"Feedforward 3D Editing Learns from Semantic-Part Transformation","created":"2026-05-26","cited_by_count":10},{"id":"2511.22357","title":"AnchorFlow: Training-Free 3D Editing via Latent Anchor-Aligned Flows","created":"2025-11-27","cited_by_count":9},{"id":"2602.21499","title":"Easy3E: Feed-Forward 3D Asset Editing via Rectified Voxel Flow","created":"2026-02-25","cited_by_count":9},{"id":"2605.05163","title":"PhysForge: Generating Physics-Grounded 3D Assets for Interactive Virtual World","created":"2026-05-06","cited_by_count":9},{"id":"2506.18017","title":"Auto-Regressive Surface Cutting","created":"2025-06-22","cited_by_count":8},{"id":"2511.13647","title":"Part-X-MLLM: Part-aware 3D Multimodal Large Language Model","created":"2025-11-17","cited_by_count":7},{"id":"2511.16317","title":"NaTex: Seamless Texture Generation as Latent Color Diffusion","created":"2025-11-20","cited_by_count":7},{"id":"2512.13678","title":"Feedforward 3D Editing via Text-Steerable Image-to-3D","created":"2025-12-15","cited_by_count":7},{"id":"2606.04621","title":"MeshFlow: Efficient Artistic Mesh Generation via MeshVAE and Flow-based Diffusion Transformer","created":"2026-06-03","cited_by_count":7},{"id":"2603.01515","title":"FACE: A Face-based Autoregressive Representation for High-Fidelity and Efficient Mesh Generation","created":"2026-03-02","cited_by_count":6},{"id":"2603.17841","title":"Omni-3DEdit: Generalized Versatile 3D Editing in One-Pass","created":"2026-03-18","cited_by_count":6},{"id":"2605.28548","title":"GEM: Generative Supervision Helps Embodied Intelligence","created":"2026-05-27","cited_by_count":6},{"id":"2512.07628","title":"MoCA: Mixture-of-Components Attention for Scalable Compositional 3D Generation","created":"2025-12-08","cited_by_count":5},{"id":"2605.28763","title":"CubePart: An Open-Vocabulary Part-Controllable 3D Generator","created":"2026-05-27","cited_by_count":5},{"id":"2511.17501","title":"Native 3D Editing with Full Attention","created":"2025-11-21","cited_by_count":4},{"id":"2602.04349","title":"VecSet-Edit: Unleashing Pre-trained LRM for Mesh Editing from Single Image","created":"2026-02-04","cited_by_count":4},{"id":"2602.05676","title":"ShapeUP: Scalable Image-Conditioned 3D Editing","created":"2026-02-05","cited_by_count":4},{"id":"2601.21798","title":"CG-MLLM: Captioning and Generating 3D content via Multi-modal Large Language Models","created":"2026-01-29","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":"2605.16745","title":"EVA01: Unified Native 3D Understanding and Generation via Mixture-of-Transformers","created":"2026-05-16","cited_by_count":3},{"id":"2501.16177","title":"BAG: Body-Aligned 3D Wearable Asset Generation","created":"2025-01-27","cited_by_count":2}],"next_cursor":"100"}