Showing 1–17 of 17 results
/ Date/ Name
Apr 23, 2026Context Unrolling in Omni ModelsDec 15, 2025Seedance 1.5 pro: A Native Audio-Visual Joint Generation Foundation ModelSep 24, 2025Seedream 4.0: Toward Next-generation Multimodal Image GenerationAug 28, 2025Mixture of Contexts for Long Video GenerationJun 10, 2025Seedance 1.0: Exploring the Boundaries of Video Generation ModelsApr 11, 2025Seaweed-7B: Cost-Effective Training of Video Generation Foundation ModelMar 13, 2025CameraCtrl II: Dynamic Scene Exploration via Camera-controlled Video Diffusion ModelsMar 21, 2024GRM: Large Gaussian Reconstruction Model for Efficient 3D Reconstruction and GenerationDec 4, 2023BerfScene: Bev-conditioned Equivariant Radiance Fields for Infinite 3D Scene GenerationAug 29, 2023Learning Modulated Transformation in GANsApr 4, 2023Revisiting the Evaluation of Image Synthesis with GANsJan 20, 2023Spatial Steerability of GANs via Self-Supervision from DiscriminatorDec 14, 2022Towards Smooth Video CompositionSep 20, 2022Improving GANs with A Dynamic DiscriminatorDec 20, 20213D-aware Image Synthesis via Learning Structural and Textural RepresentationsFeb 16, 2021Instance Localization for Self-supervised Detection PretrainingNov 13, 2019Learning Where to Focus for Efficient Video Object Detection