{"list":"other","total":52,"rows":[{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2308.04079","title":"3D Gaussian Splatting for Real-Time Radiance Field Rendering","created":"2023-08-08","cited_by_count":6226},{"id":"1711.00937","title":"Neural Discrete Representation Learning","created":"2017-11-02","cited_by_count":4712},{"id":"2204.14198","title":"Flamingo: a Visual Language Model for Few-Shot Learning","created":"2022-04-29","cited_by_count":4386},{"id":"2310.06825","title":"Mistral 7B","created":"2023-10-10","cited_by_count":3164},{"id":"2209.14988","title":"DreamFusion: Text-to-3D using 2D Diffusion","created":"2022-09-29","cited_by_count":3025},{"id":"1512.03012","title":"ShapeNet: An Information-Rich 3D Model Repository","created":"2015-12-09","cited_by_count":2897},{"id":"2306.02858","title":"Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding","created":"2023-06-05","cited_by_count":1471},{"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":"2305.06355","title":"VideoChat: Chat-Centric Video Understanding","created":"2023-05-10","cited_by_count":857},{"id":"2103.01458","title":"Diffusion Probabilistic Models for 3D Point Cloud Generation","created":"2021-03-02","cited_by_count":735},{"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":"2111.14819","title":"Point-BERT: Pre-training 3D Point Cloud Transformers with Masked Point Modeling","created":"2021-11-29","cited_by_count":653},{"id":"2212.00774","title":"Score Jacobian Chaining: Lifting Pretrained 2D Diffusion Models for 3D Generation","created":"2022-12-01","cited_by_count":597},{"id":"1604.00449","title":"3D-R2N2: A Unified Approach for Single and Multi-view 3D Object Reconstruction","created":"2016-04-02","cited_by_count":588},{"id":"2211.15654","title":"OpenScene: 3D Scene Understanding with Open Vocabularies","created":"2022-11-28","cited_by_count":559},{"id":"2210.06978","title":"LION: Latent Point Diffusion Models for 3D Shape Generation","created":"2022-10-12","cited_by_count":553},{"id":"2303.09553","title":"LERF: Language Embedded Radiance Fields","created":"2023-03-16","cited_by_count":543},{"id":"2306.14795","title":"MotionGPT: Human Motion as a Foreign Language","created":"2023-06-26","cited_by_count":527},{"id":"2104.03670","title":"3D Shape Generation and Completion through Point-Voxel Diffusion","created":"2021-04-08","cited_by_count":516},{"id":"2112.01455","title":"Zero-Shot Text-Guided Object Generation with Dream Fields","created":"2021-12-02","cited_by_count":513},{"id":"2305.11175","title":"VisionLLM: Large Language Model is also an Open-Ended Decoder for Vision-Centric Tasks","created":"2023-05-18","cited_by_count":501},{"id":"1808.00671","title":"PCN: Point Completion Network","created":"2018-08-02","cited_by_count":384},{"id":"2212.04493","title":"SDFusion: Multimodal 3D Shape Completion, Reconstruction, and Generation","created":"2022-12-08","cited_by_count":288},{"id":"2108.08839","title":"PoinTr: Diverse Point Cloud Completion with Geometry-Aware Transformers","created":"2021-08-19","cited_by_count":286},{"id":"2110.02624","title":"CLIP-Forge: Towards Zero-Shot Text-to-Shape Generation","created":"2021-10-06","cited_by_count":254},{"id":"1612.00101","title":"Shape Completion using 3D-Encoder-Predictor CNNs and Shape Synthesis","created":"2016-12-01","cited_by_count":219},{"id":"2306.07279","title":"Scalable 3D Captioning with Pretrained Models","created":"2023-06-12","cited_by_count":203},{"id":"2303.08133","title":"MeshDiffusion: Score-based Generative 3D Mesh Modeling","created":"2023-03-14","cited_by_count":199},{"id":"1603.08637","title":"Learning a Predictable and Generative Vector Representation for Objects","created":"2016-03-29","cited_by_count":173},{"id":"1803.08495","title":"Text2Shape: Generating Shapes from Natural Language by Learning Joint Embeddings","created":"2018-03-22","cited_by_count":169},{"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":"2308.08769","title":"Chat-3D: Data-efficiently Tuning Large Language Model for Universal Dialogue of 3D Scenes","created":"2023-08-17","cited_by_count":129},{"id":"2012.03408","title":"PMP-Net: Point Cloud Completion by Learning Multi-step Point Moving Paths","created":"2020-12-07","cited_by_count":97},{"id":"1709.07599","title":"High-Resolution Shape Completion Using Deep Neural Networks for Global Structure and Local Geometry Inference","created":"2017-09-22","cited_by_count":87},{"id":"2306.07349","title":"ATT3D: Amortized Text-to-3D Object Synthesis","created":"2023-06-06","cited_by_count":87},{"id":"2401.17053","title":"BlockFusion: Expandable 3D Scene Generation using Latent Tri-plane Extrapolation","created":"2024-01-30","cited_by_count":83},{"id":"2104.13366","title":"Unsupervised 3D Shape Completion through GAN Inversion","created":"2021-04-27","cited_by_count":70},{"id":"1809.05068","title":"Learning Shape Priors for Single-View 3D Completion and Reconstruction","created":"2018-09-13","cited_by_count":68},{"id":"2003.07717","title":"Multimodal Shape Completion via Conditional Generative Adversarial Networks","created":"2020-03-17","cited_by_count":61},{"id":"1805.07290","title":"Learning 3D Shape Completion under Weak Supervision","created":"2018-05-18","cited_by_count":40},{"id":"2311.17618","title":"ShapeGPT: 3D Shape Generation with A Unified Multi-modal Language Model","created":"2023-11-29","cited_by_count":39},{"id":"2306.10533","title":"Point-Cloud Completion with Pretrained Text-to-image Diffusion Models","created":"2023-06-18","cited_by_count":37},{"id":"1505.06289","title":"Text to 3D Scene Generation with Rich Lexical Grounding","created":"2015-05-23","cited_by_count":36},{"id":"2303.10406","title":"3DQD: Generalized Deep 3D Shape Prior via Part-Discretized Diffusion Process","created":"2023-03-18","cited_by_count":25},{"id":"2310.17075","title":"HyperFields: Towards Zero-Shot Generation of NeRFs from Text","created":"2023-10-26","cited_by_count":13},{"id":"2403.18241","title":"NeuSDFusion: A Spatial-Aware Generative Model for 3D Shape Completion, Reconstruction, and Generation","created":"2024-03-27","cited_by_count":13},{"id":"2312.02568","title":"Prompt2NeRF-PIL: Fast NeRF Generation via Pretrained Implicit Latent","created":"2023-12-05","cited_by_count":1}],"next_cursor":null}