{"list":"other","total":82,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"1801.03924","title":"The Unreasonable Effectiveness of Deep Features as a Perceptual Metric","created":"2018-01-11","cited_by_count":11177},{"id":"2505.09388","title":"Qwen3 Technical Report","created":"2025-05-14","cited_by_count":8820},{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"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":"2502.13923","title":"Qwen2.5-VL Technical Report","created":"2025-02-19","cited_by_count":5587},{"id":"2302.05543","title":"Adding Conditional Control to Text-to-Image Diffusion Models","created":"2023-02-10","cited_by_count":5503},{"id":"2211.09800","title":"InstructPix2Pix: Learning to Follow Image Editing Instructions","created":"2022-11-17","cited_by_count":2611},{"id":"2408.06072","title":"CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer","created":"2024-08-12","cited_by_count":2261},{"id":"2412.03603","title":"HunyuanVideo: A Systematic Framework For Large Video Generative Models","created":"2024-12-03","cited_by_count":1660},{"id":"2307.04725","title":"AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning","created":"2023-07-10","cited_by_count":1433},{"id":"2508.02324","title":"Qwen-Image Technical Report","created":"2025-08-04","cited_by_count":1044},{"id":"2506.15742","title":"FLUX.1 Kontext: Flow Matching for In-Context Image Generation and Editing in Latent Space","created":"2025-06-17","cited_by_count":1006},{"id":"2205.15868","title":"CogVideo: Large-scale Pretraining for Text-to-Video Generation via Transformers","created":"2022-05-29","cited_by_count":985},{"id":"2311.04400","title":"LRM: Large Reconstruction Model for Single Image to 3D","created":"2023-11-08","cited_by_count":849},{"id":"2412.01506","title":"Structured 3D Latents for Scalable and Versatile 3D Generation","created":"2024-12-02","cited_by_count":770},{"id":"2402.05054","title":"LGM: Large Multi-View Gaussian Model for High-Resolution 3D Content Creation","created":"2024-02-07","cited_by_count":739},{"id":"2310.15008","title":"Wonder3D: Single Image to 3D using Cross-Domain Diffusion","created":"2023-10-23","cited_by_count":689},{"id":"2306.14795","title":"MotionGPT: Human Motion as a Foreign Language","created":"2023-06-26","cited_by_count":527},{"id":"2503.07598","title":"VACE: All-in-One Video Creation and Editing","created":"2025-03-10","cited_by_count":479},{"id":"2303.12688","title":"Pix2Video: Video Editing using Image Diffusion","created":"2023-03-22","cited_by_count":320},{"id":"2303.04761","title":"Video-P2P: Video Editing with Cross-attention Control","created":"2023-03-08","cited_by_count":314},{"id":"2105.09492","title":"DeepCAD: A Deep Generative Network for Computer-Aided Design Models","created":"2021-05-20","cited_by_count":271},{"id":"2212.05171","title":"ULIP: Learning a Unified Representation of Language, Images, and Point Clouds for 3D Understanding","created":"2022-12-10","cited_by_count":267},{"id":"2311.15475","title":"MeshGPT: Generating Triangle Meshes with Decoder-Only Transformers","created":"2023-11-27","cited_by_count":259},{"id":"2512.14692","title":"Native and Compact Structured Latents for 3D Generation","created":"2025-12-16","cited_by_count":175},{"id":"2404.19759","title":"MotionLCM: Real-time Controllable Motion Generation via Latent Consistency Model","created":"2024-04-30","cited_by_count":168},{"id":"2007.11301","title":"DeepSVG: A Hierarchical Generative Network for Vector Graphics Animation","created":"2020-07-22","cited_by_count":159},{"id":"2102.02798","title":"Im2Vec: Synthesizing Vector Graphics without Vector Supervision","created":"2021-02-04","cited_by_count":116},{"id":"2402.17113","title":"Transparent Image Layer Diffusion using Latent Transparency","created":"2024-02-27","cited_by_count":114},{"id":"2211.11319","title":"VectorFusion: Text-to-SVG by Abstracting Pixel-Based Diffusion Models","created":"2022-11-21","cited_by_count":112},{"id":"2312.11556","title":"StarVector: Generating Scalable Vector Graphics Code from Images and Text","created":"2023-12-17","cited_by_count":102},{"id":"2503.22236","title":"Hi3DGen: High-fidelity 3D Geometry Generation from Images via Normal Bridging","created":"2025-03-28","cited_by_count":99},{"id":"2411.09595","title":"LLaMA-Mesh: Unifying 3D Mesh Generation with Language Models","created":"2024-11-14","cited_by_count":91},{"id":"2412.09548","title":"Meshtron: High-Fidelity, Artist-Like 3D Mesh Generation at Scale","created":"2024-12-12","cited_by_count":89},{"id":"2409.18114","title":"EdgeRunner: Auto-regressive Auto-encoder for Artistic Mesh Generation","created":"2024-09-26","cited_by_count":87},{"id":"2503.15451","title":"MotionStreamer: Streaming Motion Generation via Diffusion-based Autoregressive Model in Causal Latent Space","created":"2025-03-19","cited_by_count":86},{"id":"2312.16476","title":"SVGDreamer: Text Guided SVG Generation with Diffusion Model","created":"2023-12-27","cited_by_count":76},{"id":"2304.14400","title":"IconShop: Text-Guided Vector Icon Synthesis with Autoregressive Transformers","created":"2023-04-27","cited_by_count":75},{"id":"2504.06263","title":"OmniSVG: A Unified Scalable Vector Graphics Generation Model","created":"2025-04-08","cited_by_count":74},{"id":"2501.00912","title":"AutoPresent: Designing Structured Visuals from Scratch","created":"2025-01-01","cited_by_count":68},{"id":"2507.07095","title":"Go to Zero: Towards Zero-shot Motion Generation with Million-scale Data","created":"2025-07-09","cited_by_count":68},{"id":"2412.11102","title":"Empowering LLMs to Understand and Generate Complex Vector Graphics","created":"2024-12-15","cited_by_count":66},{"id":"2506.07491","title":"SpatialLM: Training Large Language Models for Structured Indoor Modeling","created":"2025-06-09","cited_by_count":65},{"id":"2303.01818","title":"Word-As-Image for Semantic Typography","created":"2023-03-03","cited_by_count":63},{"id":"2410.05340","title":"Generating CAD Code with Vision-Language Models for 3D Designs","created":"2024-10-07","cited_by_count":62},{"id":"2505.23757","title":"Impromptu VLA: Open Weights and Open Data for Driving Vision-Language-Action Models","created":"2025-05-29","cited_by_count":60},{"id":"2311.13608","title":"Breathing Life Into Sketches Using Text-to-Video Priors","created":"2023-11-21","cited_by_count":48},{"id":"2502.12135","title":"MagicArticulate: Make Your 3D Models Articulation-Ready","created":"2025-02-17","cited_by_count":43},{"id":"2508.10898","title":"Puppeteer: Rig and Animate Your 3D Models","created":"2025-08-14","cited_by_count":43},{"id":"2412.11596","title":"MeshArt: Generating Articulated Meshes with Structure-Guided Transformers","created":"2024-12-16","cited_by_count":41},{"id":"2403.19589","title":"TOD3Cap: Towards 3D Dense Captioning in Outdoor Scenes","created":"2024-03-28","cited_by_count":40},{"id":"2503.11629","title":"TreeMeshGPT: Artistic Mesh Generation with Autoregressive Tree Sequencing","created":"2025-03-14","cited_by_count":39},{"id":"2411.16602","title":"Chat2SVG: Vector Graphics Generation with Large Language Models and Image Diffusion Models","created":"2024-11-25","cited_by_count":38},{"id":"2405.10317","title":"Text-to-Vector Generation with Neural Path Representation","created":"2024-05-16","cited_by_count":33},{"id":"2409.06702","title":"Hint-AD: Holistically Aligned Interpretability in End-to-End Autonomous Driving","created":"2024-09-10","cited_by_count":33},{"id":"2503.09631","title":"V2M4: 4D Mesh Animation Reconstruction from a Single Monocular Video","created":"2025-03-11","cited_by_count":33},{"id":"2504.14257","title":"HoLa: B-Rep Generation using a Holistic Latent Representation","created":"2025-04-19","cited_by_count":30},{"id":"2512.16561","title":"N3D-VLM: Native 3D Grounding Enables Accurate Spatial Reasoning in Vision-Language Models","created":"2025-12-18","cited_by_count":29},{"id":"2404.13710","title":"SVGEditBench: A Benchmark Dataset for Quantitative Assessment of LLM's SVG Editing Capabilities","created":"2024-04-21","cited_by_count":26},{"id":"2210.10775","title":"TOIST: Task Oriented Instance Segmentation Transformer with Noun-Pronoun Distillation","created":"2022-10-19","cited_by_count":25},{"id":"2411.17423","title":"DRiVE: Diffusion-based Rigging Empowers Generation of Versatile and Expressive Characters","created":"2024-11-26","cited_by_count":24},{"id":"2505.05469","title":"Generating Physically Stable and Buildable Brick Structures from Text","created":"2025-05-08","cited_by_count":24},{"id":"2411.18197","title":"Make-It-Animatable: An Efficient Framework for Authoring Animation-Ready 3D Characters","created":"2024-11-27","cited_by_count":23},{"id":"2404.12347","title":"AniClipart: Clipart Animation with Text-to-Video Priors","created":"2024-04-18","cited_by_count":17},{"id":"2409.18980","title":"IW-Bench: Evaluating Large Multimodal Models for Converting Image-to-Web","created":"2024-09-14","cited_by_count":16},{"id":"2506.03139","title":"SVGenius: Benchmarking LLMs in SVG Understanding, Editing and Generation","created":"2025-06-03","cited_by_count":16},{"id":"2412.10488","title":"SVGBuilder: Component-Based Colored SVG Generation with Text-Guided Autoregressive Transformers","created":"2024-12-13","cited_by_count":14},{"id":"2509.12815","title":"Hunyuan3D Studio: End-to-End AI Pipeline for Game-Ready 3D Asset Generation","created":"2025-09-16","cited_by_count":13},{"id":"2404.04363","title":"Idea23D: Collaborative LMM Agents Enable 3D Model Generation from Interleaved Multimodal Inputs","created":"2024-04-05","cited_by_count":12},{"id":"2404.11614","title":"Dynamic Typography: Bringing Text to Life via Video Diffusion Prior","created":"2024-04-17","cited_by_count":12},{"id":"2502.13372","title":"MoVer: Motion Verification for Motion Graphics Animations","created":"2025-02-19","cited_by_count":10},{"id":"2402.06071","title":"Keyframer: Empowering Animation Design using Large Language Models","created":"2024-02-08","cited_by_count":9},{"id":"2602.01661","title":"From Frames to Sequences: Temporally Consistent Human-Centric Dense Prediction","created":"2026-02-02","cited_by_count":9},{"id":"2309.14642","title":"Editing Motion Graphics Video via Motion Vectorization and Transformation","created":"2023-09-26","cited_by_count":8},{"id":"2505.23740","title":"LayerPeeler: Autoregressive Peeling for Layer-wise Image Vectorization","created":"2025-05-29","cited_by_count":8},{"id":"2411.18654","title":"AToM: Aligning Text-to-Motion Model at Event-Level with GPT-4Vision Reward","created":"2024-11-27","cited_by_count":7},{"id":"2604.03305","title":"HVG-3D: Bridging Real and Simulation Domains for 3D-Conditional Hand-Object Interaction Video Synthesis","created":"2026-03-31","cited_by_count":7},{"id":"2311.13562","title":"Soulstyler: Using Large Language Model to Guide Image Style Transfer for Target Object","created":"2023-11-22","cited_by_count":6},{"id":"2504.10905","title":"InterAnimate: Taming Region-aware Diffusion Model for Realistic Human Interaction Animation","created":"2025-04-15","cited_by_count":4},{"id":"2509.07484","title":"LINR Bridge: Vector Graphic Animation via Neural Implicits and Video Diffusion Priors","created":"2025-09-09","cited_by_count":2}],"next_cursor":null}