{"list":"other","total":56,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2010.02502","title":"Denoising Diffusion Implicit Models","created":"2020-10-06","cited_by_count":9781},{"id":"2105.05233","title":"Diffusion Models Beat GANs on Image Synthesis","created":"2021-05-11","cited_by_count":8255},{"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":"2308.04079","title":"3D Gaussian Splatting for Real-Time Radiance Field Rendering","created":"2023-08-08","cited_by_count":6226},{"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":"2204.02311","title":"PaLM: Scaling Language Modeling with Pathways","created":"2022-04-05","cited_by_count":5326},{"id":"2204.14198","title":"Flamingo: a Visual Language Model for Few-Shot Learning","created":"2022-04-29","cited_by_count":4386},{"id":"2102.12092","title":"Zero-Shot Text-to-Image Generation","created":"2021-02-24","cited_by_count":4288},{"id":"2201.05989","title":"Instant Neural Graphics Primitives with a Multiresolution Hash Encoding","created":"2022-01-16","cited_by_count":3723},{"id":"2203.15556","title":"Training Compute-Optimal Large Language Models","created":"2022-03-29","cited_by_count":3019},{"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":"2204.03458","title":"Video Diffusion Models","created":"2022-04-07","cited_by_count":2305},{"id":"2111.12077","title":"Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fields","created":"2021-11-23","cited_by_count":2032},{"id":"2211.05100","title":"BLOOM: A 176B-Parameter Open-Access Multilingual Language Model","created":"2022-11-09","cited_by_count":1984},{"id":"2103.13415","title":"Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fields","created":"2021-03-24","cited_by_count":1964},{"id":"2209.14792","title":"Make-A-Video: Text-to-Video Generation without Text-Video Data","created":"2022-09-29","cited_by_count":1742},{"id":"2107.03006","title":"Structured Denoising Diffusion Models in Discrete State-Spaces","created":"2021-07-07","cited_by_count":1719},{"id":"2306.00890","title":"LLaVA-Med: Training a Large Language-and-Vision Assistant for Biomedicine in One Day","created":"2023-06-01","cited_by_count":1305},{"id":"2306.14824","title":"Kosmos-2: Grounding Multimodal Large Language Models to the World","created":"2023-06-26","cited_by_count":1089},{"id":"2304.14178","title":"mPLUG-Owl: Modularization Empowers Large Language Models with Multimodality","created":"2023-04-27","cited_by_count":1040},{"id":"2205.14217","title":"Diffusion-LM Improves Controllable Text Generation","created":"2022-05-27","cited_by_count":1027},{"id":"2306.13549","title":"A Survey on Multimodal Large Language Models","created":"2023-06-23","cited_by_count":909},{"id":"2306.15195","title":"Shikra: Unleashing Multimodal LLM's Referential Dialogue Magic","created":"2023-06-27","cited_by_count":906},{"id":"2202.05263","title":"Block-NeRF: Scalable Large Scene Neural View Synthesis","created":"2022-02-10","cited_by_count":724},{"id":"2212.00490","title":"Zero-Shot Image Restoration Using Denoising Diffusion Null-Space Model","created":"2022-12-01","cited_by_count":583},{"id":"2305.03726","title":"Otter: A Multi-Modal Model with In-Context Instruction Tuning","created":"2023-05-05","cited_by_count":550},{"id":"2310.07704","title":"Ferret: Refer and Ground Anything Anywhere at Any Granularity","created":"2023-10-11","cited_by_count":509},{"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":"2105.06337","title":"Grad-TTS: A Diffusion Probabilistic Model for Text-to-Speech","created":"2021-05-13","cited_by_count":447},{"id":"2112.10703","title":"Mega-NeRF: Scalable Construction of Large-Scale NeRFs for Virtual Fly-Throughs","created":"2021-12-20","cited_by_count":398},{"id":"2012.05877","title":"INeRF: Inverting Neural Radiance Fields for Pose Estimation","created":"2020-12-10","cited_by_count":382},{"id":"2401.15947","title":"MoE-LLaVA: Mixture of Experts for Large Vision-Language Models","created":"2024-01-29","cited_by_count":300},{"id":"2112.00390","title":"SegDiff: Image Segmentation with Diffusion Probabilistic Models","created":"2021-12-01","cited_by_count":280},{"id":"2406.12080","title":"A Hierarchical 3D Gaussian Representation for Real-Time Rendering of Very Large Datasets","created":"2024-06-17","cited_by_count":216},{"id":"2404.01133","title":"CityGaussian: Real-time High-quality Large-Scale Scene Rendering with Gaussians","created":"2024-04-01","cited_by_count":192},{"id":"2309.16553","title":"MatrixCity: A Large-scale City Dataset for City-scale Neural Rendering and Beyond","created":"2023-09-28","cited_by_count":185},{"id":"2307.15058","title":"MARS: An Instance-aware, Modular and Realistic Simulator for Autonomous Driving","created":"2023-07-27","cited_by_count":170},{"id":"2306.15667","title":"PoseDiffusion: Solving Pose Estimation via Diffusion-aided Bundle Adjustment","created":"2023-06-27","cited_by_count":147},{"id":"1509.05909","title":"Modelling Uncertainty in Deep Learning for Camera Relocalization","created":"2015-09-19","cited_by_count":134},{"id":"2107.04286","title":"Capturing, Reconstructing, and Simulating: the UrbanScene3D Dataset","created":"2021-07-09","cited_by_count":118},{"id":"2112.03530","title":"A Conditional Point Diffusion-Refinement Paradigm for 3D Point Cloud Completion","created":"2021-12-07","cited_by_count":100},{"id":"2311.04498","title":"NExT-Chat: An LMM for Chat, Detection and Segmentation","created":"2023-11-08","cited_by_count":80},{"id":"2403.09637","title":"GaussianGrasper: 3D Language Gaussian Splatting for Open-vocabulary Robotic Grasping","created":"2024-03-14","cited_by_count":78},{"id":"2002.05907","title":"A Survey on 3D Skeleton-Based Action Recognition Using Learning Method","created":"2020-02-14","cited_by_count":47},{"id":"2408.14873","title":"Robo-GS: A Physics Consistent Spatial-Temporal Model for Robotic Arm with Hybrid Representation","created":"2024-08-27","cited_by_count":46},{"id":"2203.15125","title":"Text2Pos: Text-to-Point-Cloud Cross-Modal Localization","created":"2022-03-28","cited_by_count":40},{"id":"2311.15977","title":"Text2Loc: 3D Point Cloud Localization from Natural Language","created":"2023-11-27","cited_by_count":35},{"id":"2405.00676","title":"Spectrally Pruned Gaussian Fields with Neural Compensation","created":"2024-05-01","cited_by_count":33},{"id":"2408.10906","title":"ShapeSplat: A Large-scale Dataset of Gaussian Splats and Their Self-Supervised Pretraining","created":"2024-08-20","cited_by_count":21},{"id":"2301.05372","title":"Text to Point Cloud Localization with Relation-Enhanced Transformer","created":"2023-01-13","cited_by_count":20}],"next_cursor":null}