{"list":"other","total":77,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"2308.04079","title":"3D Gaussian Splatting for Real-Time Radiance Field Rendering","created":"2023-08-08","cited_by_count":6226},{"id":"1607.06450","title":"Layer Normalization","created":"2016-07-21","cited_by_count":5669},{"id":"2104.09864","title":"RoFormer: Enhanced Transformer with Rotary Position Embedding","created":"2021-04-20","cited_by_count":4703},{"id":"1909.08053","title":"Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism","created":"2019-09-17","cited_by_count":1868},{"id":"2504.16054","title":"$\\pi_{0.5}$: a Vision-Language-Action Model with Open-World Generalization","created":"2025-04-22","cited_by_count":1761},{"id":"1910.07467","title":"Root Mean Square Layer Normalization","created":"2019-10-16","cited_by_count":1480},{"id":"1910.02054","title":"ZeRO: Memory Optimizations Toward Training Trillion Parameter Models","created":"2019-10-04","cited_by_count":1301},{"id":"2111.09883","title":"Swin Transformer V2: Scaling Up Capacity and Resolution","created":"2021-11-18","cited_by_count":1228},{"id":"2106.02034","title":"DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification","created":"2021-06-03","cited_by_count":864},{"id":"2103.14899","title":"CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image Classification","created":"2021-03-27","cited_by_count":806},{"id":"2412.01506","title":"Structured 3D Latents for Scalable and Versatile 3D Generation","created":"2024-12-02","cited_by_count":770},{"id":"2101.10994","title":"Neural Geometric Level of Detail: Real-time Rendering with Implicit 3D Shapes","created":"2021-01-26","cited_by_count":426},{"id":"2110.06199","title":"ABO: Dataset and Benchmarks for Real-World 3D Object Understanding","created":"2021-10-12","cited_by_count":366},{"id":"1702.02463","title":"Video Frame Synthesis using Deep Voxel Flow","created":"2017-02-08","cited_by_count":209},{"id":"2404.13026","title":"PhysDreamer: Physics-Based Interaction with 3D Objects via Video Generation","created":"2024-04-19","cited_by_count":191},{"id":"2312.03806","title":"XCube: Large-Scale 3D Generative Modeling using Sparse Voxel Hierarchies","created":"2023-12-06","cited_by_count":189},{"id":"2409.18964","title":"PhysGen: Rigid-Body Physics-Grounded Image-to-Video Generation","created":"2024-09-27","cited_by_count":174},{"id":"1912.11913","title":"Category-Level Articulated Object Pose Estimation","created":"2019-12-26","cited_by_count":159},{"id":"2303.05512","title":"PAC-NeRF: Physics Augmented Continuum Neural Radiance Fields for Geometry-Agnostic System Identification","created":"2023-03-09","cited_by_count":154},{"id":"2212.08013","title":"FlexiViT: One Model for All Patch Sizes","created":"2022-12-15","cited_by_count":152},{"id":"2105.15075","title":"Not All Images are Worth 16x16 Words: Dynamic Transformers for Efficient Image Recognition","created":"2021-05-31","cited_by_count":144},{"id":"2404.09465","title":"PhyScene: Physically Interactable 3D Scene Synthesis for Embodied AI","created":"2024-04-15","cited_by_count":125},{"id":"2406.04338","title":"Physics3D: Learning Physical Properties of 3D Gaussians via Video Diffusion","created":"2024-06-06","cited_by_count":80},{"id":"2211.09761","title":"Efficient Transformers with Dynamic Token Pooling","created":"2022-11-17","cited_by_count":76},{"id":"2306.14447","title":"RoboCook: Long-Horizon Elasto-Plastic Object Manipulation with Diverse Tools","created":"2023-06-26","cited_by_count":76},{"id":"2501.18982","title":"OmniPhysGS: 3D Constitutive Gaussians for General Physics-Based Dynamics Generation","created":"2025-01-31","cited_by_count":69},{"id":"2503.20746","title":"PhysGen3D: Crafting a Miniature Interactive World from a Single Image","created":"2025-03-26","cited_by_count":66},{"id":"1906.03853","title":"DensePhysNet: Learning Dense Physical Object Representations via Multi-step Dynamic Interactions","created":"2019-06-10","cited_by_count":63},{"id":"2203.03821","title":"CF-ViT: A General Coarse-to-Fine Method for Vision Transformer","created":"2022-03-08","cited_by_count":63},{"id":"2410.20030","title":"SCube: Instant Large-Scale Scene Reconstruction using VoxSplats","created":"2024-10-26","cited_by_count":60},{"id":"2004.13664","title":"Visual Grounding of Learned Physical Models","created":"2020-04-28","cited_by_count":55},{"id":"2311.17024","title":"Diffusion 3D Features (Diff3F): Decorating Untextured Shapes with Distilled Semantic Features","created":"2023-11-28","cited_by_count":55},{"id":"2407.07889","title":"AdaptiGraph: Material-Adaptive Graph-Based Neural Dynamics for Robotic Manipulation","created":"2024-07-10","cited_by_count":54},{"id":"2311.13099","title":"PIE-NeRF: Physics-based Interactive Elastodynamics with NeRF","created":"2023-11-22","cited_by_count":51},{"id":"2405.02794","title":"Octopi: Object Property Reasoning with Large Tactile-Language Models","created":"2024-05-05","cited_by_count":48},{"id":"2210.09420","title":"Differentiable Physics Simulation of Dynamics-Augmented Neural Objects","created":"2022-10-17","cited_by_count":45},{"id":"2502.12135","title":"MagicArticulate: Make Your 3D Models Articulation-Ready","created":"2025-02-17","cited_by_count":43},{"id":"2507.12465","title":"PhysX-3D: Physical-Grounded 3D Asset Generation","created":"2025-07-16","cited_by_count":42},{"id":"2406.01476","title":"DreamPhysics: Learning Physics-Based 3D Dynamics with Video Diffusion Priors","created":"2024-06-03","cited_by_count":41},{"id":"2405.20510","title":"Physically Compatible 3D Object Modeling from a Single Image","created":"2024-05-30","cited_by_count":39},{"id":"1604.01360","title":"The Curious Robot: Learning Visual Representations via Physical Interactions","created":"2016-04-05","cited_by_count":38},{"id":"2304.00287","title":"Vision Transformers with Mixed-Resolution Tokenization","created":"2023-04-01","cited_by_count":36},{"id":"2411.14423","title":"PhysFlow: Unleashing the Potential of Multi-modal Foundation Models and Video Diffusion for 4D Dynamic Physical Scene Simulation","created":"2024-11-21","cited_by_count":36},{"id":"2411.12789","title":"Efficient Physics Simulation for 3D Scenes via MLLM-Guided Gaussian Splatting","created":"2024-11-19","cited_by_count":32},{"id":"2412.09530","title":"Dynamic-VLM: Simple Dynamic Visual Token Compression for VideoLLM","created":"2024-12-12","cited_by_count":32},{"id":"2504.09975","title":"OctGPT: Octree-based Multiscale Autoregressive Models for 3D Shape Generation","created":"2025-04-14","cited_by_count":30},{"id":"2504.15278","title":"DRAWER: Digital Reconstruction and Articulation With Environment Realism","created":"2025-04-21","cited_by_count":29},{"id":"2407.09497","title":"Simplicits: Mesh-Free, Geometry-Agnostic, Elastic Simulation","created":"2024-06-09","cited_by_count":27},{"id":"1511.04048","title":"Newtonian Image Understanding: Unfolding the Dynamics of Objects in Static Images","created":"2015-11-12","cited_by_count":26},{"id":"2404.09833","title":"Video2Game: Real-time, Interactive, Realistic and Browser-Compatible Environment from a Single Video","created":"2024-04-15","cited_by_count":26},{"id":"2508.17437","title":"Pixie: Fast and Generalizable Supervised Learning of 3D Physics from Pixels","created":"2025-08-20","cited_by_count":24},{"id":"2604.09860","title":"RoboLab: A High-Fidelity Simulation Benchmark for Analysis of Task Generalist Policies","created":"2026-04-10","cited_by_count":24},{"id":"2409.07179","title":"Phy124: Fast Physics-Driven 4D Content Generation from a Single Image","created":"2024-09-11","cited_by_count":23},{"id":"2411.16800","title":"Phys4DGen: Physics-Compliant 4D Generation with Multi-Material Composition Perception","created":"2024-11-25","cited_by_count":23},{"id":"2310.18511","title":"3DCoMPaT$^{++}$: An improved Large-scale 3D Vision Dataset for Compositional Recognition","created":"2023-10-27","cited_by_count":21},{"id":"2307.02321","title":"MSViT: Dynamic Mixed-Scale Tokenization for Vision Transformers","created":"2023-07-05","cited_by_count":20},{"id":"2506.06440","title":"Vid2Sim: Generalizable, Video-based Reconstruction of Appearance, Geometry and Physics for Mesh-free Simulation","created":"2025-06-06","cited_by_count":20},{"id":"2509.01708","title":"Articulated Object Estimation in the Wild","created":"2025-09-01","cited_by_count":19},{"id":"2303.13514","title":"SAOR: Single-View Articulated Object Reconstruction","created":"2023-03-23","cited_by_count":16},{"id":"2305.08810","title":"AutoRecon: Automated 3D Object Discovery and Reconstruction","created":"2023-05-15","cited_by_count":13},{"id":"2402.00033","title":"LF-ViT: Reducing Spatial Redundancy in Vision Transformer for Efficient Image Recognition","created":"2024-01-08","cited_by_count":13},{"id":"2504.02747","title":"GEOPARD: Geometric Pretraining for Articulation Prediction in 3D Shapes","created":"2025-04-03","cited_by_count":13},{"id":"2504.02817","title":"Efficient Autoregressive Shape Generation via Octree-Based Adaptive Tokenization","created":"2025-04-03","cited_by_count":13},{"id":"2506.07865","title":"FreeGave: 3D Physics Learning from Dynamic Videos by Gaussian Velocity","created":"2025-06-09","cited_by_count":13},{"id":"2304.11470","title":"3D-IntPhys: Towards More Generalized 3D-grounded Visual Intuitive Physics under Challenging Scenes","created":"2023-04-22","cited_by_count":12},{"id":"2203.01587","title":"Multi-Tailed Vision Transformer for Efficient Inference","created":"2022-03-03","cited_by_count":10},{"id":"2307.02092","title":"Make A Long Image Short: Adaptive Token Length for Vision Transformers","created":"2023-07-05","cited_by_count":10},{"id":"1810.08729","title":"Learning Material-Aware Local Descriptors for 3D Shapes","created":"2018-10-20","cited_by_count":8},{"id":"2308.09400","title":"GIPC: Fast and stable Gauss-Newton optimization of IPC barrier energy","created":"2023-08-18","cited_by_count":7},{"id":"2411.06224","title":"StiffGIPC: Advancing GPU IPC for stiff affine-deformable simulation","created":"2024-11-09","cited_by_count":6},{"id":"2504.12684","title":"SOPHY: Learning to Generate Simulation-Ready Objects with Physical Materials","created":"2025-04-17","cited_by_count":5},{"id":"2501.06785","title":"3DCoMPaT200: Language-Grounded Compositional Understanding of Parts and Materials of 3D Shapes","created":"2025-01-12","cited_by_count":4},{"id":"2404.09470","title":"LatticeML: A data-driven application for predicting the effective Young Modulus of high temperature graph based architected materials","created":"2024-04-15","cited_by_count":2},{"id":"2505.13201","title":"MatPredict: a dataset and benchmark for learning material properties of diverse indoor objects","created":"2025-05-19","cited_by_count":2},{"id":"2605.29318","title":"FreeForm: Reduced-Order Deformable Simulation from Particle-Based Skinning Eigenmodes","created":"2026-05-28","cited_by_count":2}],"next_cursor":null}