{"list":"other","total":59,"rows":[{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"1801.03924","title":"The Unreasonable Effectiveness of Deep Features as a Perceptual Metric","created":"2018-01-11","cited_by_count":11177},{"id":"2212.09748","title":"Scalable Diffusion Models with Transformers","created":"2022-12-19","cited_by_count":6054},{"id":"2302.05543","title":"Adding Conditional Control to Text-to-Image Diffusion Models","created":"2023-02-10","cited_by_count":5503},{"id":"2303.05499","title":"Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection","created":"2023-03-09","cited_by_count":3332},{"id":"2408.00714","title":"SAM 2: Segment Anything in Images and Videos","created":"2024-08-01","cited_by_count":2863},{"id":"2408.00118","title":"Gemma 2: Improving Open Language Models at a Practical Size","created":"2024-07-31","cited_by_count":1998},{"id":"2406.09414","title":"Depth Anything V2","created":"2024-06-13","cited_by_count":1422},{"id":"2302.08453","title":"T2I-Adapter: Learning Adapters to Dig out More Controllable Ability for Text-to-Image Diffusion Models","created":"2023-02-16","cited_by_count":1351},{"id":"1903.07291","title":"Semantic Image Synthesis with Spatially-Adaptive Normalization","created":"2019-03-18","cited_by_count":1299},{"id":"1406.2283","title":"Depth Map Prediction from a Single Image using a Multi-Scale Deep Network","created":"2014-06-09","cited_by_count":1274},{"id":"1711.11585","title":"High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs","created":"2017-11-30","cited_by_count":1179},{"id":"2107.10833","title":"Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Data","created":"2021-07-22","cited_by_count":970},{"id":"2501.03575","title":"Cosmos World Foundation Model Platform for Physical AI","created":"2025-01-07","cited_by_count":864},{"id":"1704.07813","title":"Unsupervised Learning of Depth and Ego-Motion from Video","created":"2017-04-25","cited_by_count":782},{"id":"2301.07093","title":"GLIGEN: Open-Set Grounded Text-to-Image Generation","created":"2023-01-17","cited_by_count":781},{"id":"2304.11277","title":"PyTorch FSDP: Experiences on Scaling Fully Sharded Data Parallel","created":"2023-04-21","cited_by_count":660},{"id":"2302.03011","title":"Structure and Content-Guided Video Synthesis with Diffusion Models","created":"2023-02-06","cited_by_count":590},{"id":"2311.18259","title":"Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectives","created":"2023-11-30","cited_by_count":490},{"id":"2302.07121","title":"Universal Guidance for Diffusion Models","created":"2023-02-14","cited_by_count":437},{"id":"1808.06601","title":"Video-to-Video Synthesis","created":"2018-08-20","cited_by_count":390},{"id":"2305.16322","title":"Uni-ControlNet: All-in-One Control to Text-to-Image Diffusion Models","created":"2023-05-25","cited_by_count":359},{"id":"2503.03751","title":"GEN3C: 3D-Informed World-Consistent Video Generation with Precise Camera Control","created":"2025-03-05","cited_by_count":341},{"id":"2211.04894","title":"Exploring Video Quality Assessment on User Generated Contents from Aesthetic and Technical Perspectives","created":"2022-11-09","cited_by_count":320},{"id":"2303.11926","title":"Exploring Object-Centric Temporal Modeling for Efficient Multi-View 3D Object Detection","created":"2023-03-21","cited_by_count":315},{"id":"2304.03373","title":"Training-Free Layout Control with Cross-Attention Guidance","created":"2023-04-06","cited_by_count":313},{"id":"2302.09778","title":"Composer: Creative and Controllable Image Synthesis with Composable Conditions","created":"2023-02-20","cited_by_count":304},{"id":"2406.06978","title":"Hydra-MDP: End-to-end Multimodal Planning with Multi-target Hydra-Distillation","created":"2024-06-11","cited_by_count":249},{"id":"2305.11147","title":"UniControl: A Unified Diffusion Model for Controllable Visual Generation In the Wild","created":"2023-05-18","cited_by_count":200},{"id":"1910.12713","title":"Few-shot Video-to-Video Synthesis","created":"2019-10-28","cited_by_count":197},{"id":"2410.07073","title":"Pixtral 12B","created":"2024-10-09","cited_by_count":179},{"id":"1802.08705","title":"PDDLStream: Integrating Symbolic Planners and Blackbox Samplers via Optimistic Adaptive Planning","created":"2018-02-23","cited_by_count":150},{"id":"2403.09630","title":"GenAD: Generalized Predictive Model for Autonomous Driving","created":"2024-03-14","cited_by_count":150},{"id":"2401.05252","title":"PIXART-{\\delta}: Fast and Controllable Image Generation with Latent Consistency Models","created":"2024-01-10","cited_by_count":141},{"id":"2207.00050","title":"Semantic Image Synthesis via Diffusion Models","created":"2022-06-30","cited_by_count":132},{"id":"2012.04781","title":"You Only Need Adversarial Supervision for Semantic Image Synthesis","created":"2020-12-08","cited_by_count":129},{"id":"2304.04269","title":"HumanSD: A Native Skeleton-Guided Diffusion Model for Human Image Generation","created":"2023-04-09","cited_by_count":105},{"id":"2006.09001","title":"RL-CycleGAN: Reinforcement Learning Aware Simulation-To-Real","created":"2020-06-16","cited_by_count":91},{"id":"2311.17061","title":"HumanGaussian: Text-Driven 3D Human Generation with Gaussian Splatting","created":"2023-11-28","cited_by_count":89},{"id":"2312.07509","title":"PEEKABOO: Interactive Video Generation via Masked-Diffusion","created":"2023-12-12","cited_by_count":76},{"id":"2112.05130","title":"Multimodal Conditional Image Synthesis with Product-of-Experts GANs","created":"2021-12-09","cited_by_count":75},{"id":"2011.03148","title":"RetinaGAN: An Object-aware Approach to Sim-to-Real Transfer","created":"2020-11-06","cited_by_count":70},{"id":"2007.08509","title":"World-Consistent Video-to-Video Synthesis","created":"2020-07-16","cited_by_count":69},{"id":"2310.08579","title":"HyperHuman: Hyper-Realistic Human Generation with Latent Structural Diffusion","created":"2023-10-12","cited_by_count":68},{"id":"2303.14412","title":"Freestyle Layout-to-Image Synthesis","created":"2023-03-25","cited_by_count":67},{"id":"2404.09967","title":"Ctrl-Adapter: An Efficient and Versatile Framework for Adapting Diverse Controls to Any Diffusion Model","created":"2024-04-15","cited_by_count":66},{"id":"2111.00956","title":"Robot Learning from Randomized Simulations: A Review","created":"2021-11-01","cited_by_count":63},{"id":"2412.03934","title":"InfiniCube: Unbounded and Controllable Dynamic 3D Driving Scene Generation with World-Guided Video Models","created":"2024-12-05","cited_by_count":56},{"id":"2311.02738","title":"Scenario Diffusion: Controllable Driving Scenario Generation With Diffusion","created":"2023-11-05","cited_by_count":47},{"id":"2109.07053","title":"Image Synthesis via Semantic Composition","created":"2021-09-15","cited_by_count":45},{"id":"2211.11742","title":"SceneComposer: Any-Level Semantic Image Synthesis","created":"2022-11-21","cited_by_count":43},{"id":"2403.01852","title":"PLACE: Adaptive Layout-Semantic Fusion for Semantic Image Synthesis","created":"2024-03-04","cited_by_count":20},{"id":"2406.18958","title":"AnyControl: Create Your Artwork with Versatile Control on Text-to-Image Generation","created":"2024-06-27","cited_by_count":20},{"id":"2203.16898","title":"Semantic-shape Adaptive Feature Modulation for Semantic Image Synthesis","created":"2022-03-31","cited_by_count":16},{"id":"2204.02854","title":"Retrieval-based Spatially Adaptive Normalization for Semantic Image Synthesis","created":"2022-04-06","cited_by_count":15},{"id":"2207.05049","title":"Fast-Vid2Vid: Spatial-Temporal Compression for Video-to-Video Synthesis","created":"2022-07-11","cited_by_count":12},{"id":"2404.09111","title":"Exploring Generative AI for Sim2Real in Driving Data Synthesis","created":"2024-04-14","cited_by_count":7},{"id":"2308.16071","title":"Semantic Image Synthesis via Class-Adaptive Cross-Attention","created":"2023-08-30","cited_by_count":5},{"id":"2308.08011","title":"Shortcut-V2V: Compression Framework for Video-to-Video Translation based on Temporal Redundancy Reduction","created":"2023-08-15","cited_by_count":2}],"next_cursor":null}