{"list":"other","total":59,"rows":[{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"1801.03924","title":"The Unreasonable Effectiveness of Deep Features as a Perceptual Metric","created":"2018-01-11","cited_by_count":11177},{"id":"2305.18290","title":"Direct Preference Optimization: Your Language Model is Secretly a Reward Model","created":"2023-05-29","cited_by_count":8065},{"id":"2308.04079","title":"3D Gaussian Splatting for Real-Time Radiance Field Rendering","created":"2023-08-08","cited_by_count":6226},{"id":"2403.03206","title":"Scaling Rectified Flow Transformers for High-Resolution Image Synthesis","created":"2024-03-05","cited_by_count":4181},{"id":"2310.06825","title":"Mistral 7B","created":"2023-10-10","cited_by_count":3164},{"id":"2503.20314","title":"Wan: Open and Advanced Large-Scale Video Generative Models","created":"2025-03-26","cited_by_count":2708},{"id":"2412.03603","title":"HunyuanVideo: A Systematic Framework For Large Video Generative Models","created":"2024-12-03","cited_by_count":1660},{"id":"2503.11651","title":"VGGT: Visual Geometry Grounded Transformer","created":"2025-03-14","cited_by_count":1539},{"id":"2508.10104","title":"DINOv3","created":"2025-08-13","cited_by_count":1414},{"id":"2402.15391","title":"Genie: Generative Interactive Environments","created":"2024-02-23","cited_by_count":747},{"id":"2311.17117","title":"Animate Anyone: Consistent and Controllable Image-to-Video Synthesis for Character Animation","created":"2023-11-28","cited_by_count":688},{"id":"2012.03065","title":"Dynamic Neural Radiance Fields for Monocular 4D Facial Avatar Reconstruction","created":"2020-12-05","cited_by_count":467},{"id":"2401.12945","title":"Lumiere: A Space-Time Diffusion Model for Video Generation","created":"2024-01-23","cited_by_count":455},{"id":"2105.02872","title":"Animatable Neural Radiance Fields for Modeling Dynamic Human Bodies","created":"2021-05-06","cited_by_count":361},{"id":"2504.13181","title":"Perception Encoder: The best visual embeddings are not at the output of the network","created":"2025-04-17","cited_by_count":326},{"id":"2203.12575","title":"NeuMan: Neural Human Radiance Field from a Single Video","created":"2022-03-23","cited_by_count":244},{"id":"2408.12569","title":"Sapiens: Foundation for Human Vision Models","created":"2024-08-22","cited_by_count":229},{"id":"1911.07013","title":"Understanding and Improving Layer Normalization","created":"2019-11-16","cited_by_count":217},{"id":"2404.10667","title":"VASA-1: Lifelike Audio-Driven Talking Faces Generated in Real Time","created":"2024-04-16","cited_by_count":187},{"id":"2206.08929","title":"TAVA: Template-free Animatable Volumetric Actors","created":"2022-06-17","cited_by_count":172},{"id":"2212.10550","title":"InstantAvatar: Learning Avatars from Monocular Video in 60 Seconds","created":"2022-12-20","cited_by_count":138},{"id":"2302.11566","title":"Vid2Avatar: 3D Avatar Reconstruction from Videos in the Wild via Self-supervised Scene Decomposition","created":"2023-02-22","cited_by_count":134},{"id":"2104.04638","title":"Pixel Codec Avatars","created":"2021-04-09","cited_by_count":127},{"id":"2312.03704","title":"Relightable Gaussian Codec Avatars","created":"2023-12-06","cited_by_count":127},{"id":"2311.08581","title":"Drivable 3D Gaussian Avatars","created":"2023-11-14","cited_by_count":120},{"id":"2109.10686","title":"Scale Efficiently: Insights from Pre-training and Fine-tuning Transformers","created":"2021-09-22","cited_by_count":106},{"id":"2407.21686","title":"Expressive Whole-Body 3D Gaussian Avatar","created":"2024-07-31","cited_by_count":89},{"id":"2305.04789","title":"AvatarReX: Real-time Expressive Full-body Avatars","created":"2023-05-08","cited_by_count":84},{"id":"2105.10441","title":"Driving-Signal Aware Full-Body Avatars","created":"2021-05-21","cited_by_count":81},{"id":"2509.14055","title":"Wan-Animate: Unified Character Animation and Replacement with Holistic Replication","created":"2025-09-17","cited_by_count":80},{"id":"2503.10625","title":"LHM: Large Animatable Human Reconstruction Model from a Single Image in Seconds","created":"2025-03-13","cited_by_count":61},{"id":"2412.14963","title":"IDOL: Instant Photorealistic 3D Human Creation from a Single Image","created":"2024-12-19","cited_by_count":55},{"id":"2207.06955","title":"Learning Implicit Templates for Point-Based Clothed Human Modeling","created":"2022-07-14","cited_by_count":50},{"id":"2410.24223","title":"URAvatar: Universal Relightable Gaussian Codec Avatars","created":"2024-10-31","cited_by_count":43},{"id":"1605.07116","title":"A Formal Evaluation of PSNR as Quality Measurement Parameter for Image Segmentation Algorithms","created":"2016-05-23","cited_by_count":42},{"id":"2205.01355","title":"Predicting Loose-Fitting Garment Deformations Using Bone-Driven Motion Networks","created":"2022-05-03","cited_by_count":39},{"id":"2410.08188","title":"DifFRelight: Diffusion-Based Facial Performance Relighting","created":"2024-10-10","cited_by_count":35},{"id":"2309.04247","title":"Towards Practical Capture of High-Fidelity Relightable Avatars","created":"2023-09-08","cited_by_count":34},{"id":"2407.08414","title":"MeshAvatar: Learning High-quality Triangular Human Avatars from Multi-view Videos","created":"2024-07-11","cited_by_count":34},{"id":"2503.01610","title":"Vid2Avatar-Pro: Authentic Avatar from Videos in the Wild via Universal Prior","created":"2025-03-03","cited_by_count":31},{"id":"2409.08353","title":"Robust Dual Gaussian Splatting for Immersive Human-centric Volumetric Videos","created":"2024-09-12","cited_by_count":30},{"id":"2401.12175","title":"Template-Free Single-View 3D Human Digitalization with Diffusion-Guided LRM","created":"2024-01-22","cited_by_count":23},{"id":"2501.14726","title":"Relightable Full-Body Gaussian Codec Avatars","created":"2025-01-24","cited_by_count":22},{"id":"2505.03351","title":"GUAVA: Generalizable Upper Body 3D Gaussian Avatar","created":"2025-05-06","cited_by_count":22},{"id":"2409.15269","title":"ReLoo: Reconstructing Humans Dressed in Loose Garments from Monocular Video in the Wild","created":"2024-09-23","cited_by_count":19},{"id":"2508.07519","title":"Exploring Multimodal Diffusion Transformers for Enhanced Prompt-based Image Editing","created":"2025-08-11","cited_by_count":17},{"id":"2412.21206","title":"PERSE: Personalized 3D Generative Avatars from A Single Portrait","created":"2024-12-30","cited_by_count":15},{"id":"2503.07390","title":"PersonaBooth: Personalized Text-to-Motion Generation","created":"2025-03-10","cited_by_count":14},{"id":"2406.04253","title":"A Survey on 3D Human Avatar Modeling -- From Reconstruction to Generation","created":"2024-06-06","cited_by_count":13},{"id":"2508.09973","title":"PERSONA: Personalized Whole-Body 3D Avatar with Pose-Driven Deformations from a Single Image","created":"2025-08-13","cited_by_count":13},{"id":"2508.15767","title":"ATLAS: Decoupling Skeletal and Shape Parameters for Expressive Parametric Human Modeling","created":"2025-08-21","cited_by_count":12},{"id":"2509.24817","title":"UP2You: Fast Reconstruction of Yourself from Unconstrained Photo Collections","created":"2025-09-29","cited_by_count":10},{"id":"2502.19739","title":"LUCAS: Layered Universal Codec Avatars","created":"2025-02-27","cited_by_count":7}],"next_cursor":null}