{"list":"other","total":63,"rows":[{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"2010.02502","title":"Denoising Diffusion Implicit Models","created":"2020-10-06","cited_by_count":9781},{"id":"2011.13456","title":"Score-Based Generative Modeling through Stochastic Differential Equations","created":"2020-11-26","cited_by_count":9122},{"id":"2408.00714","title":"SAM 2: Segment Anything in Images and Videos","created":"2024-08-01","cited_by_count":2863},{"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":"2402.17177","title":"Sora: A Review on Background, Technology, Limitations, and Opportunities of Large Vision Models","created":"2024-02-27","cited_by_count":477},{"id":"2302.04867","title":"UniPC: A Unified Predictor-Corrector Framework for Fast Sampling of Diffusion Models","created":"2023-02-09","cited_by_count":450},{"id":"2304.01186","title":"Follow Your Pose: Pose-Guided Text-to-Video Generation using Pose-Free Videos","created":"2023-04-03","cited_by_count":314},{"id":"2211.12446","title":"EDICT: Exact Diffusion Inversion via Coupled Transformations","created":"2022-11-22","cited_by_count":258},{"id":"2211.14461","title":"CDDFuse: Correlation-Driven Dual-Branch Feature Decomposition for Multi-Modality Image Fusion","created":"2022-11-26","cited_by_count":223},{"id":"2411.04746","title":"Taming Rectified Flow for Inversion and Editing","created":"2024-11-07","cited_by_count":204},{"id":"2305.16807","title":"Negative-prompt Inversion: Fast Image Inversion for Editing with Text-guided Diffusion Models","created":"2023-05-26","cited_by_count":174},{"id":"2406.01900","title":"Follow-Your-Emoji: Fine-Controllable and Expressive Freestyle Portrait Animation","created":"2024-06-04","cited_by_count":174},{"id":"2303.06840","title":"DDFM: Denoising Diffusion Model for Multi-Modality Image Fusion","created":"2023-03-13","cited_by_count":153},{"id":"2312.16272","title":"SSR-Encoder: Encoding Selective Subject Representation for Subject-Driven Generation","created":"2023-12-26","cited_by_count":143},{"id":"2306.00943","title":"Make-Your-Video: Customized Video Generation Using Textual and Structural Guidance","created":"2023-06-01","cited_by_count":129},{"id":"2311.17009","title":"Space-Time Diffusion Features for Zero-Shot Text-Driven Motion Transfer","created":"2023-11-28","cited_by_count":124},{"id":"2503.07027","title":"EasyControl: Adding Efficient and Flexible Control for Diffusion Transformer","created":"2025-03-10","cited_by_count":119},{"id":"1811.12673","title":"ComDefend: An Efficient Image Compression Model to Defend Adversarial Examples","created":"2018-11-30","cited_by_count":105},{"id":"2406.05338","title":"MotionClone: Training-Free Motion Cloning for Controllable Video Generation","created":"2024-06-08","cited_by_count":105},{"id":"2310.06313","title":"Advancing Pose-Guided Image Synthesis with Progressive Conditional Diffusion Models","created":"2023-10-10","cited_by_count":104},{"id":"2411.03286","title":"DiT4Edit: Diffusion Transformer for Image Editing","created":"2024-11-05","cited_by_count":101},{"id":"2203.06616","title":"LAS-AT: Adversarial Training with Learnable Attack Strategy","created":"2022-03-13","cited_by_count":95},{"id":"2404.14055","title":"RingID: Rethinking Tree-Ring Watermarking for Enhanced Multi-Key Identification","created":"2024-04-22","cited_by_count":91},{"id":"2312.00852","title":"Beyond First-Order Tweedie: Solving Inverse Problems using Latent Diffusion","created":"2023-12-01","cited_by_count":78},{"id":"2312.03047","title":"MagicStick: Controllable Video Editing via Control Handle Transformations","created":"2023-12-05","cited_by_count":62},{"id":"2310.07222","title":"Uni-paint: A Unified Framework for Multimodal Image Inpainting with Pretrained Diffusion Model","created":"2023-10-11","cited_by_count":60},{"id":"2503.18860","title":"HunyuanPortrait: Implicit Condition Control for Enhanced Portrait Animation","created":"2025-03-24","cited_by_count":59},{"id":"2506.17267","title":"CF-VLM:CounterFactual Vision-Language Fine-tuning","created":"2025-06-10","cited_by_count":59},{"id":"2505.23399","title":"GAM-Agent: Game-Theoretic and Uncertainty-Aware Collaboration for Complex Visual Reasoning","created":"2025-05-29","cited_by_count":58},{"id":"2410.05470","title":"Image Watermarks are Removable Using Controllable Regeneration from Clean Noise","created":"2024-10-07","cited_by_count":50},{"id":"2502.09533","title":"Long-Term TalkingFace Generation via Motion-Prior Conditional Diffusion Model","created":"2025-02-13","cited_by_count":49},{"id":"2404.14239","title":"MultiBooth: Towards Generating All Your Concepts in an Image from Text","created":"2024-04-22","cited_by_count":45},{"id":"2502.01572","title":"MakeAnything: Harnessing Diffusion Transformers for Multi-Domain Procedural Sequence Generation","created":"2025-02-03","cited_by_count":45},{"id":"2503.10270","title":"EEdit: Rethinking the Spatial and Temporal Redundancy for Efficient Image Editing","created":"2025-03-13","cited_by_count":45},{"id":"2502.01105","title":"LayerTracer: Cognitive-Aligned Layered SVG Synthesis via Diffusion Transformer","created":"2025-02-03","cited_by_count":43},{"id":"2509.16630","title":"Follow-Your-Emoji-Faster: Towards Efficient, Fine-Controllable, and Expressive Freestyle Portrait Animation","created":"2025-09-20","cited_by_count":43},{"id":"2110.05007","title":"Boosting Fast Adversarial Training with Learnable Adversarial Initialization","created":"2021-10-11","cited_by_count":40},{"id":"2510.17845","title":"MAT-Agent: Adaptive Multi-Agent Training Optimization","created":"2025-10-10","cited_by_count":35},{"id":"2412.01197","title":"InstantSwap: Fast Customized Concept Swapping across Sharp Shape Differences","created":"2024-12-02","cited_by_count":34},{"id":"2509.02785","title":"DrDiff: Dynamic Routing Diffusion with Hierarchical Attention for Breaking the Efficiency-Quality Trade-off","created":"2025-09-02","cited_by_count":34},{"id":"2412.16563","title":"SemTalk: Holistic Co-speech Motion Generation with Frame-level Semantic Emphasis","created":"2024-12-21","cited_by_count":32},{"id":"2509.04876","title":"OSC: Cognitive Orchestration through Dynamic Knowledge Alignment in Multi-Agent LLM Collaboration","created":"2025-09-05","cited_by_count":30},{"id":"2506.01949","title":"IMAGHarmony: Controllable Image Editing with Consistent Object Quantity and Layout","created":"2025-06-02","cited_by_count":28},{"id":"2210.07883","title":"One Model to Edit Them All: Free-Form Text-Driven Image Manipulation with Semantic Modulations","created":"2022-10-14","cited_by_count":24},{"id":"2404.15677","title":"CharacterFactory: Sampling Consistent Characters with GANs for Diffusion Models","created":"2024-04-24","cited_by_count":24},{"id":"2502.14397","title":"PhotoDoodle: Learning Artistic Image Editing from Few-Shot Pairwise Data","created":"2025-02-20","cited_by_count":24},{"id":"2312.07539","title":"HeadArtist: Text-conditioned 3D Head Generation with Self Score Distillation","created":"2023-12-12","cited_by_count":22},{"id":"2412.11638","title":"IDProtector: An Adversarial Noise Encoder to Protect Against ID-Preserving Image Generation","created":"2024-12-16","cited_by_count":22},{"id":"2211.07825","title":"Direct Inversion: Optimization-Free Text-Driven Real Image Editing with Diffusion Models","created":"2022-11-15","cited_by_count":19},{"id":"2412.05980","title":"Anti-Reference: Universal and Immediate Defense Against Reference-Based Generation","created":"2024-12-08","cited_by_count":18},{"id":"2509.23082","title":"Follow-Your-Preference: Towards Preference-Aligned Image Inpainting","created":"2025-09-27","cited_by_count":18},{"id":"2504.09209","title":"EchoMask: Speech-Queried Attention-based Mask Modeling for Holistic Co-Speech Motion Generation","created":"2025-04-12","cited_by_count":17},{"id":"2302.11306","title":"Human MotionFormer: Transferring Human Motions with Vision Transformers","created":"2023-02-22","cited_by_count":14},{"id":"2508.05580","title":"Follow-Your-Instruction: A Comprehensive MLLM Agent for World Data Synthesis","created":"2025-08-07","cited_by_count":10},{"id":"2505.19858","title":"A Unified Solution to Video Fusion: From Multi-Frame Learning to Benchmarking","created":"2025-05-26","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":"2506.01011","title":"Autoregressive Images Watermarking through Lexical Biasing: An Approach Resistant to Regeneration Attack","created":"2025-06-01","cited_by_count":8},{"id":"2412.16495","title":"Follow-Your-MultiPose: Tuning-Free Multi-Character Text-to-Video Generation via Pose Guidance","created":"2024-12-21","cited_by_count":7},{"id":"2508.09912","title":"E-4DGS: High-Fidelity Dynamic Reconstruction from the Multi-view Event Cameras","created":"2025-08-13","cited_by_count":7},{"id":"2505.15287","title":"GS2E: Gaussian Splatting is an Effective Data Generator for Event Stream Generation","created":"2025-05-21","cited_by_count":6},{"id":"2508.02408","title":"GR-Gaussian: Graph-Based Radiative Gaussian Splatting for Sparse-View CT Reconstruction","created":"2025-08-04","cited_by_count":5}],"next_cursor":null}