{"list":"other","total":52,"rows":[{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"1801.03924","title":"The Unreasonable Effectiveness of Deep Features as a Perceptual Metric","created":"2018-01-11","cited_by_count":11177},{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"2503.20314","title":"Wan: Open and Advanced Large-Scale Video Generative Models","created":"2025-03-26","cited_by_count":2708},{"id":"2209.14792","title":"Make-A-Video: Text-to-Video Generation without Text-Video Data","created":"2022-09-29","cited_by_count":1742},{"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":"1812.01717","title":"Towards Accurate Generative Models of Video: A New Metric & Challenges","created":"2018-12-03","cited_by_count":1234},{"id":"2502.14786","title":"SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features","created":"2025-02-20","cited_by_count":1188},{"id":"2212.11565","title":"Tune-A-Video: One-Shot Tuning of Image Diffusion Models for Text-to-Video Generation","created":"2022-12-22","cited_by_count":961},{"id":"2302.01329","title":"Dreamix: Video Diffusion Models are General Video Editors","created":"2023-02-02","cited_by_count":191},{"id":"2312.01725","title":"StableVITON: Learning Semantic Correspondence with Latent Diffusion Model for Virtual Try-On","created":"2023-12-04","cited_by_count":175},{"id":"2403.01779","title":"OOTDiffusion: Outfitting Fusion based Latent Diffusion for Controllable Virtual Try-on","created":"2024-03-04","cited_by_count":151},{"id":"2306.08276","title":"TryOnDiffusion: A Tale of Two UNets","created":"2023-06-14","cited_by_count":141},{"id":"2308.06101","title":"Taming the Power of Diffusion Models for High-Quality Virtual Try-On with Appearance Flow","created":"2023-08-11","cited_by_count":124},{"id":"2403.05139","title":"Improving Diffusion Models for Authentic Virtual Try-on in the Wild","created":"2024-03-08","cited_by_count":109},{"id":"2407.15886","title":"CatVTON: Concatenation Is All You Need for Virtual Try-On with Diffusion Models","created":"2024-07-21","cited_by_count":102},{"id":"1902.11026","title":"Towards Multi-pose Guided Virtual Try-on Network","created":"2019-02-28","cited_by_count":95},{"id":"2501.15891","title":"Any2AnyTryon: Leveraging Adaptive Position Embeddings for Versatile Virtual Clothing Tasks","created":"2025-01-27","cited_by_count":63},{"id":"2503.18860","title":"HunyuanPortrait: Implicit Condition Control for Enhanced Portrait Animation","created":"2025-03-24","cited_by_count":59},{"id":"2404.16771","title":"ConsistentID: Portrait Generation with Multimodal Fine-Grained Identity Preserving","created":"2024-04-25","cited_by_count":43},{"id":"2311.16094","title":"Street TryOn: Learning In-the-Wild Virtual Try-On from Unpaired Person Images","created":"2023-11-27","cited_by_count":34},{"id":"2403.10783","title":"StableGarment: Garment-Centric Generation via Stable Diffusion","created":"2024-03-16","cited_by_count":27},{"id":"2412.08486","title":"Learning Flow Fields in Attention for Controllable Person Image Generation","created":"2024-12-11","cited_by_count":27},{"id":"2501.11325","title":"CatV2TON: Taming Diffusion Transformers for Vision-Based Virtual Try-On with Temporal Concatenation","created":"2025-01-20","cited_by_count":25},{"id":"2405.00448","title":"MMTryon: Multi-Modal Multi-Reference Control for High-Quality Fashion Generation","created":"2024-05-01","cited_by_count":23},{"id":"2505.23742","title":"MAGREF: Masked Guidance for Any-Reference Video Generation with Subject Disentanglement","created":"2025-05-29","cited_by_count":23},{"id":"2407.10625","title":"WildVidFit: Video Virtual Try-On in the Wild via Image-Based Controlled Diffusion Models","created":"2024-07-15","cited_by_count":22},{"id":"2312.15861","title":"Towards Squeezing-Averse Virtual Try-On via Sequential Deformation","created":"2023-12-26","cited_by_count":18},{"id":"2504.02542","title":"Audio-visual Controlled Video Diffusion with Masked Selective State Spaces Modeling for Natural Talking Head Generation","created":"2025-04-03","cited_by_count":17},{"id":"2508.02807","title":"DreamVVT: Mastering Realistic Video Virtual Try-On in the Wild via a Stage-Wise Diffusion Transformer Framework","created":"2025-08-04","cited_by_count":17},{"id":"2411.00225","title":"Fashion-VDM: Video Diffusion Model for Virtual Try-On","created":"2024-10-31","cited_by_count":16},{"id":"2505.21325","title":"MagicTryOn: Harnessing Diffusion Transformer for Garment-Preserving Video Virtual Try-on","created":"2025-05-27","cited_by_count":15},{"id":"2405.18326","title":"VITON-DiT: Learning In-the-Wild Video Try-On from Human Dance Videos via Diffusion Transformers","created":"2024-05-28","cited_by_count":11},{"id":"2505.16980","title":"Pursuing Temporal-Consistent Video Virtual Try-On via Dynamic Pose Interaction","created":"2025-05-22","cited_by_count":11},{"id":"2605.14278","title":"KVPO: ODE-Native GRPO for Autoregressive Video Alignment via KV Semantic Exploration","created":"2026-05-14","cited_by_count":11},{"id":"2503.19904","title":"Tracktention: Leveraging Point Tracking to Attend Videos Faster and Better","created":"2025-03-25","cited_by_count":9},{"id":"2507.15037","title":"OmniVTON: Training-Free Universal Virtual Try-On","created":"2025-07-20","cited_by_count":9},{"id":"2509.06723","title":"Zo3T: Zero-Shot 3D-Aware Trajectory-Guided Image-to-Video Generation via Test-Time Training","created":"2025-09-08","cited_by_count":9},{"id":"2511.16249","title":"Controllable Layer Decomposition for Reversible Multi-Layer Image Generation","created":"2025-11-20","cited_by_count":9},{"id":"2501.08682","title":"RealVVT: Towards Photorealistic Video Virtual Try-on via Spatio-Temporal Consistency","created":"2025-01-15","cited_by_count":8},{"id":"2412.09822","title":"Dynamic Try-On: Taming Video Virtual Try-on with Dynamic Attention Mechanism","created":"2024-12-13","cited_by_count":7},{"id":"2511.18957","title":"Eevee: Towards Close-up High-resolution Video-based Virtual Try-on","created":"2025-11-24","cited_by_count":7},{"id":"2605.15803","title":"Embedding-perturbed Exploration Preference Optimization for Flow Models","created":"2026-05-15","cited_by_count":5},{"id":"2605.21431","title":"iTryOn: Mastering Interactive Video Virtual Try-On with Spatial-Semantic Guidance","created":"2026-05-20","cited_by_count":4},{"id":"2510.07654","title":"Once Is Enough: Lightweight DiT-Based Video Virtual Try-On via One-Time Garment Appearance Injection","created":"2025-10-09","cited_by_count":3},{"id":"2603.21299","title":"Identity-Consistent Video Generation under Large Facial-Angle Variations","created":"2026-03-22","cited_by_count":3},{"id":"2606.26092","title":"TryOnCrafter: Unleashing Camera Trajectories for Realistic Video Virtual Try-on via a Renderable 4D Try-on Proxy","created":"2026-06-24","cited_by_count":3},{"id":"2508.21070","title":"Dress&Dance: Dress up and Dance as You Like It - Technical Preview","created":"2025-08-28","cited_by_count":2},{"id":"2606.27880","title":"OrthoTryOn: Geometric Orthogonalization for Conflict-Free Unified Fashion Generation","created":"2026-06-26","cited_by_count":2},{"id":"2606.08514","title":"OmniTryOn: Video Try-On Anything at Once!","created":"2026-06-07","cited_by_count":1},{"id":"2606.27773","title":"ModaFlow: Modality-Aware Flow Matching for High-Fidelity Virtual Try-On","created":"2026-06-26","cited_by_count":1}],"next_cursor":null}