{"list":"other","total":60,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"2012.09841","title":"Taming Transformers for High-Resolution Image Synthesis","created":"2020-12-17","cited_by_count":3253},{"id":"2202.04200","title":"MaskGIT: Masked Generative Image Transformer","created":"2022-02-08","cited_by_count":1099},{"id":"2404.02905","title":"Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction","created":"2024-04-03","cited_by_count":1023},{"id":"2412.01506","title":"Structured 3D Latents for Scalable and Versatile 3D Generation","created":"2024-12-02","cited_by_count":770},{"id":"2406.11838","title":"Autoregressive Image Generation without Vector Quantization","created":"2024-06-17","cited_by_count":651},{"id":"2301.00704","title":"Muse: Text-To-Image Generation via Masked Generative Transformers","created":"2023-01-02","cited_by_count":648},{"id":"2304.05302","title":"RRHF: Rank Responses to Align Language Models with Human Feedback without tears","created":"2023-04-11","cited_by_count":463},{"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":"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":"2311.15475","title":"MeshGPT: Generating Triangle Meshes with Decoder-Only Transformers","created":"2023-11-27","cited_by_count":259},{"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":"2311.16839","title":"Beyond Hallucinations: Enhancing LVLMs through Hallucination-Aware Direct Preference Optimization","created":"2023-11-28","cited_by_count":225},{"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":"2212.07422","title":"ECON: Explicit Clothed humans Optimized via Normal integration","created":"2022-12-14","cited_by_count":199},{"id":"2402.11411","title":"Aligning Modalities in Vision Large Language Models via Preference Fine-tuning","created":"2024-02-18","cited_by_count":198},{"id":"2406.10163","title":"MeshAnything: Artist-Created Mesh Generation with Autoregressive Transformers","created":"2024-06-14","cited_by_count":144},{"id":"2312.10665","title":"Silkie: Preference Distillation for Large Visual Language Models","created":"2023-12-17","cited_by_count":130},{"id":"2308.10899","title":"TADA! Text to Animatable Digital Avatars","created":"2023-08-21","cited_by_count":110},{"id":"2308.08545","title":"TeCH: Text-guided Reconstruction of Lifelike Clothed Humans","created":"2023-08-16","cited_by_count":104},{"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":"2411.07025","title":"Scaling Mesh Generation via Compressive Tokenization","created":"2024-11-11","cited_by_count":73},{"id":"2401.06838","title":"MAPO: Advancing Multilingual Reasoning through Multilingual Alignment-as-Preference Optimization","created":"2024-01-12","cited_by_count":69},{"id":"2309.11351","title":"C$\\cdot$ASE: Learning Conditional Adversarial Skill Embeddings for Physics-based Characters","created":"2023-09-20","cited_by_count":55},{"id":"2412.14963","title":"IDOL: Instant Photorealistic 3D Human Creation from a Single Image","created":"2024-12-19","cited_by_count":55},{"id":"2403.02475","title":"Enhancing LLM Safety via Constrained Direct Preference Optimization","created":"2024-03-04","cited_by_count":49},{"id":"2502.09615","title":"RigAnything: Template-Free Autoregressive Rigging for Diverse 3D Assets","created":"2025-02-13","cited_by_count":47},{"id":"2411.14740","title":"TEXGen: a Generative Diffusion Model for Mesh Textures","created":"2024-11-22","cited_by_count":46},{"id":"2504.12451","title":"One Model to Rig Them All: Diverse Skeleton Rigging with UniRig","created":"2025-04-16","cited_by_count":45},{"id":"2502.12135","title":"MagicArticulate: Make Your 3D Models Articulation-Ready","created":"2025-02-17","cited_by_count":43},{"id":"2502.17327","title":"AnyTop: Character Animation Diffusion with Any Topology","created":"2025-02-24","cited_by_count":41},{"id":"1908.08506","title":"Predicting Animation Skeletons for 3D Articulated Models via Volumetric Nets","created":"2019-08-22","cited_by_count":39},{"id":"2503.11629","title":"TreeMeshGPT: Artistic Mesh Generation with Autoregressive Tree Sequencing","created":"2025-03-14","cited_by_count":39},{"id":"2406.06050","title":"Generalizable Human Gaussians from Single-View Image","created":"2024-06-10","cited_by_count":29},{"id":"2411.17423","title":"DRiVE: Diffusion-based Rigging Empowers Generation of Versatile and Expressive Characters","created":"2024-11-26","cited_by_count":24},{"id":"2308.09712","title":"HumanLiff: Layer-wise 3D Human Generation with Diffusion Model","created":"2023-08-18","cited_by_count":23},{"id":"2411.18197","title":"Make-It-Animatable: An Efficient Framework for Authoring Animation-Ready 3D Characters","created":"2024-11-27","cited_by_count":23},{"id":"2211.10278","title":"Unsupervised 3D Pose Transfer with Cross Consistency and Dual Reconstruction","created":"2022-11-18","cited_by_count":21},{"id":"2405.14017","title":"MagicPose4D: Crafting Articulated Models with Appearance and Motion Control","created":"2024-05-22","cited_by_count":18},{"id":"2504.17789","title":"Token-Shuffle: Towards High-Resolution Image Generation with Autoregressive Models","created":"2025-04-24","cited_by_count":18},{"id":"2203.04746","title":"SkinningNet: Two-Stream Graph Convolutional Neural Network for Skinning Prediction of Synthetic Characters","created":"2022-03-09","cited_by_count":16},{"id":"2410.20986","title":"Skinned Motion Retargeting with Dense Geometric Interaction Perception","created":"2024-10-28","cited_by_count":13},{"id":"2307.13459","title":"Weakly-supervised 3D Pose Transfer with Keypoints","created":"2023-07-25","cited_by_count":12},{"id":"2405.12607","title":"S3O: A Dual-Phase Approach for Reconstructing Dynamic Shape and Skeleton of Articulated Objects from Single Monocular Video","created":"2024-05-21","cited_by_count":12},{"id":"2412.02317","title":"HumanRig: Learning Automatic Rigging for Humanoid Character in a Large Scale Dataset","created":"2024-12-03","cited_by_count":12},{"id":"2412.07766","title":"Make-A-Texture: Fast Shape-Aware Texture Generation in 3 Seconds","created":"2024-12-10","cited_by_count":12},{"id":"2503.20519","title":"MAR-3D: Progressive Masked Auto-regressor for High-Resolution 3D Generation","created":"2025-03-26","cited_by_count":11},{"id":"2401.12946","title":"Coverage Axis++: Efficient Inner Point Selection for 3D Shape Skeletonization","created":"2024-01-23","cited_by_count":10},{"id":"2401.08809","title":"Learning Implicit Representation for Reconstructing Articulated Objects","created":"2024-01-16","cited_by_count":9},{"id":"2503.08664","title":"MEAT: Multiview Diffusion Model for Human Generation on Megapixels with Mesh Attention","created":"2025-03-11","cited_by_count":8},{"id":"2502.12080","title":"HumanGif: Single-View Human Diffusion with Generative Prior","created":"2025-02-17","cited_by_count":7},{"id":"2502.14140","title":"ModSkill: Physical Character Skill Modularization","created":"2025-02-19","cited_by_count":7},{"id":"2411.10947","title":"Direct and Explicit 3D Generation from a Single Image","created":"2024-11-17","cited_by_count":6},{"id":"2407.11266","title":"Towards High-Quality 3D Motion Transfer with Realistic Apparel Animation","created":"2024-07-15","cited_by_count":5},{"id":"2404.02242","title":"Towards Robust 3D Pose Transfer with Adversarial Learning","created":"2024-04-02","cited_by_count":4},{"id":"2411.11903","title":"DiHuR: Diffusion-Guided Generalizable Human Reconstruction","created":"2024-11-16","cited_by_count":3}],"next_cursor":null}