{"list":"other","total":62,"rows":[{"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":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"1503.03585","title":"Deep Unsupervised Learning using Nonequilibrium Thermodynamics","created":"2015-03-12","cited_by_count":7058},{"id":"2205.11487","title":"Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding","created":"2022-05-23","cited_by_count":6355},{"id":"2301.12597","title":"BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models","created":"2023-01-30","cited_by_count":6137},{"id":"2212.09748","title":"Scalable Diffusion Models with Transformers","created":"2022-12-19","cited_by_count":6054},{"id":"1907.05600","title":"Generative Modeling by Estimating Gradients of the Data Distribution","created":"2019-07-12","cited_by_count":4101},{"id":"2209.14988","title":"DreamFusion: Text-to-3D using 2D Diffusion","created":"2022-09-29","cited_by_count":3025},{"id":"2305.06500","title":"InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning","created":"2023-05-11","cited_by_count":2876},{"id":"2304.10592","title":"MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models","created":"2023-04-20","cited_by_count":2711},{"id":"2212.08051","title":"Objaverse: A Universe of Annotated 3D Objects","created":"2022-12-15","cited_by_count":1540},{"id":"2303.11328","title":"Zero-1-to-3: Zero-shot One Image to 3D Object","created":"2023-03-20","cited_by_count":1489},{"id":"2211.10440","title":"Magic3D: High-Resolution Text-to-3D Content Creation","created":"2022-11-18","cited_by_count":1290},{"id":"2308.16512","title":"MVDream: Multi-view Diffusion for 3D Generation","created":"2023-08-31","cited_by_count":938},{"id":"2307.05663","title":"Objaverse-XL: A Universe of 10M+ 3D Objects","created":"2023-07-11","cited_by_count":774},{"id":"2401.06209","title":"Eyes Wide Shut? Exploring the Visual Shortcomings of Multimodal LLMs","created":"2024-01-11","cited_by_count":735},{"id":"2212.08751","title":"Point-E: A System for Generating 3D Point Clouds from Complex Prompts","created":"2022-12-16","cited_by_count":699},{"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":"2212.00774","title":"Score Jacobian Chaining: Lifting Pretrained 2D Diffusion Models for 3D Generation","created":"2022-12-01","cited_by_count":597},{"id":"2306.16928","title":"One-2-3-45: Any Single Image to 3D Mesh in 45 Seconds without Per-Shape Optimization","created":"2023-06-29","cited_by_count":560},{"id":"2112.01455","title":"Zero-Shot Text-Guided Object Generation with Dream Fields","created":"2021-12-02","cited_by_count":513},{"id":"2305.02463","title":"Shap-E: Generating Conditional 3D Implicit Functions","created":"2023-05-03","cited_by_count":385},{"id":"2311.06214","title":"Instant3D: Fast Text-to-3D with Sparse-View Generation and Large Reconstruction Model","created":"2023-11-10","cited_by_count":378},{"id":"2303.14184","title":"Make-It-3D: High-Fidelity 3D Creation from A Single Image with Diffusion Prior","created":"2023-03-24","cited_by_count":343},{"id":"2112.03221","title":"Text2Mesh: Text-Driven Neural Stylization for Meshes","created":"2021-12-06","cited_by_count":334},{"id":"2308.16911","title":"PointLLM: Empowering Large Language Models to Understand Point Clouds","created":"2023-08-31","cited_by_count":333},{"id":"2302.10663","title":"RealFusion: 360{\\deg} Reconstruction of Any Object from a Single Image","created":"2023-02-21","cited_by_count":306},{"id":"2303.16203","title":"Your Diffusion Model is Secretly a Zero-Shot Classifier","created":"2023-03-28","cited_by_count":306},{"id":"2305.15347","title":"A Tale of Two Features: Stable Diffusion Complements DINO for Zero-Shot Semantic Correspondence","created":"2023-05-24","cited_by_count":301},{"id":"2303.02153","title":"Unleashing Text-to-Image Diffusion Models for Visual Perception","created":"2023-03-03","cited_by_count":269},{"id":"2110.02624","title":"CLIP-Forge: Towards Zero-Shot Text-to-Shape Generation","created":"2021-10-06","cited_by_count":254},{"id":"2303.11396","title":"Text2Tex: Text-driven Texture Synthesis via Diffusion Models","created":"2023-03-20","cited_by_count":235},{"id":"2311.01455","title":"RoboGen: Towards Unleashing Infinite Data for Automated Robot Learning via Generative Simulation","created":"2023-11-02","cited_by_count":218},{"id":"2311.09217","title":"DMV3D: Denoising Multi-View Diffusion using 3D Large Reconstruction Model","created":"2023-11-15","cited_by_count":214},{"id":"2311.18651","title":"LL3DA: Visual Interactive Instruction Tuning for Omni-3D Understanding, Reasoning, and Planning","created":"2023-11-30","cited_by_count":210},{"id":"2306.07279","title":"Scalable 3D Captioning with Pretrained Models","created":"2023-06-12","cited_by_count":203},{"id":"2312.03700","title":"OneLLM: One Framework to Align All Modalities with Language","created":"2023-12-06","cited_by_count":187},{"id":"2402.17766","title":"ShapeLLM: Universal 3D Object Understanding for Embodied Interaction","created":"2024-02-27","cited_by_count":137},{"id":"2310.02596","title":"SweetDreamer: Aligning Geometric Priors in 2D Diffusion for Consistent Text-to-3D","created":"2023-10-04","cited_by_count":134},{"id":"2302.14816","title":"Monocular Depth Estimation using Diffusion Models","created":"2023-02-28","cited_by_count":87},{"id":"2306.07349","title":"ATT3D: Amortized Text-to-3D Object Synthesis","created":"2023-06-06","cited_by_count":87},{"id":"2311.18799","title":"X-InstructBLIP: A Framework for aligning X-Modal instruction-aware representations to LLMs and Emergent Cross-modal Reasoning","created":"2023-11-30","cited_by_count":80},{"id":"2312.02980","title":"GPT4Point: A Unified Framework for Point-Language Understanding and Generation","created":"2023-12-05","cited_by_count":71},{"id":"2307.08702","title":"Diffusion Models Beat GANs on Image Classification","created":"2023-07-17","cited_by_count":58},{"id":"2310.02977","title":"T$^3$Bench: Benchmarking Current Progress in Text-to-3D Generation","created":"2023-10-04","cited_by_count":57},{"id":"2311.17137","title":"Generative Models: What Do They Know? Do They Know Things? Let's Find Out!","created":"2023-11-28","cited_by_count":50},{"id":"2312.09222","title":"Mosaic-SDF for 3D Generative Models","created":"2023-12-14","cited_by_count":48},{"id":"2311.05461","title":"Control3D: Towards Controllable Text-to-3D Generation","created":"2023-11-09","cited_by_count":46},{"id":"2312.11459","title":"VolumeDiffusion: Flexible Text-to-3D Generation with Efficient Volumetric Encoder","created":"2023-12-18","cited_by_count":39},{"id":"2312.04424","title":"Cascade-Zero123: One Image to Highly Consistent 3D with Self-Prompted Nearby Views","created":"2023-12-07","cited_by_count":33},{"id":"2303.13273","title":"TAPS3D: Text-Guided 3D Textured Shape Generation from Pseudo Supervision","created":"2023-03-23","cited_by_count":28},{"id":"2308.02299","title":"RegionBLIP: A Unified Multi-modal Pre-training Framework for Holistic and Regional Comprehension","created":"2023-08-03","cited_by_count":27},{"id":"2402.03327","title":"Uni3D-LLM: Unifying Point Cloud Perception, Generation and Editing with Large Language Models","created":"2024-01-09","cited_by_count":25},{"id":"2312.04963","title":"Text-to-3D Generation with Bidirectional Diffusion using both 2D and 3D priors","created":"2023-12-07","cited_by_count":24},{"id":"2401.07727","title":"HexaGen3D: StableDiffusion is just one step away from Fast and Diverse Text-to-3D Generation","created":"2024-01-15","cited_by_count":21},{"id":"2312.09069","title":"PI3D: Efficient Text-to-3D Generation with Pseudo-Image Diffusion","created":"2023-12-14","cited_by_count":20},{"id":"2309.01141","title":"VGDiffZero: Text-to-image Diffusion Models Can Be Zero-shot Visual Grounders","created":"2023-09-03","cited_by_count":18},{"id":"2402.12750","title":"Model Composition for Multimodal Large Language Models","created":"2024-02-20","cited_by_count":12},{"id":"2212.12952","title":"Neural Shape Compiler: A Unified Framework for Transforming between Text, Point Cloud, and Program","created":"2022-12-25","cited_by_count":6}],"next_cursor":null}