Generating explorable 3D scenes from a single image requires strong generative priors and accurate geometric representations suitable for downstream use. Current video diffusion models offer high-quality generation and implicitly encode multi-view geometric structure in latent space. However, existing feedforward latent scene decoders typically output volumetric 3D Gaussians that lack a well-defined surface, limiting their use in simulation or standard graphics pipelines. This motivates decoding surface-aligned primitives that are not only renderable but also closer to explicit geometric assets. We ask whether compressed video diffusion latents can be mapped directly to explicit surface primitives in a single pass. To this end, we introduce FLAT and, for the first time, show that triangle splats can be decoded directly from video diffusion latents. Compared with decoding 3D Gaussians, predicting flat primitives is notoriously more challenging due to high sensitivity to primitive orientations, oftentimes leading to poor gradient flow. FLAT solves with two key ingredients: a ray-centered rotation parameterization for triangle regression and a novel product window function that improves gradient flow during differentiable triangle rendering. On standard benchmarks, FLAT achieves significantly better geometric accuracy while maintaining competitive visual quality compared to state-of-the-art feedforward baselines. We further show that a lightweight test-time refinement step converts the predicted triangle soup into a fully opaque, game-engine-ready representation that supports real-time rendering. By evaluating 3DGS, 2DGS, and triangle splatting variants under an identical training setup, we provide the first systematic analysis of representation tradeoffs in feedforward scene generation. The project page is available at https://flat-splat.github.io
Visionary: The World Model Carrier Built on WebGPU-Powered Gaussian Splatting Platform
Shanghai AI Laboratory（上海人工智能实验室）；Sichuan University（四川大学）；The University of Tokyo（东京大学）；Shanghai Jiao Tong University（上海交通大学）；Northwestern Polytechnical University（西北工业大学）
360-GeoGS: Geometrically Consistent Feed-Forward 3D Gaussian Splatting Reconstruction for 360 Images
Shanghai Key Laboratory of Navigation and Location Based Services（上海导航与基于位置的服务关键实验室）；Shanghai Jiao Tong University（上海交通大学）；State Key Laboratory of Submarine Geoscience（海底地球科学国家重点实验室）；School of Automation and Intelligent Sensing（自动化与智能感知学院）
DeGenseGS: Geometrically and Semantically Decoupled Surgical Scene Understanding in 4D Gaussian Splatting
School of Automation, Southeast University（东南大学自动化学院）；School of Internet of Things, Nanjing University of Posts and Telecommunications（南京邮电大学物联网学院）；Department of Biomedical Engineering, National University of Singapore（新加坡国立大学生物医学工程系）
MetroGS: Efficient and Stable Reconstruction of Geometrically Accurate High-Fidelity Large-Scale Scenes
Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所）；University of Chinese Academy of Sciences（中国科学院大学）；Beihang University（北京航空航天大学）
TinySplat: Feedforward Approach for Generating Compact 3D Scene Representation
State Key Laboratory of Multimedia Information Processing, School of Computer Science, Peking University（多媒体信息处理国家重点实验室、计算机学院、北京大学）；School of Electronic and Computer Engineering, Peking University（电子与计算机工程学院、北京大学）；Wangxuan Institute of Computer Technology, State Key Laboratory of Multimedia Information Processing, Peking University（计算机技术王轩研究所、多媒体信息处理国家重点实验室、北京大学）
GS2E: Gaussian Splatting is an Effective Data Generator for Event Stream Generation
School of Electronic and Computer Engineering, Peking University（北京大学电子与计算机工程学院）；Holcombe Department of Electrical and Computer Engineering, Clemson University（克莱姆森大学霍尔科姆电子与计算机工程系）
Tsinghua University（清华大学）；Technical University of Munich（慕尼黑工业大学）；ETH Zurich（苏黎世联邦理工学院）；Munich Center for Machine Learning（慕尼黑机器学习中心）；Microsoft（微软）；Stanford University（斯坦福大学）
CityGaussianV2: Efficient and Geometrically Accurate Reconstruction for Large-Scale Scenes
Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；University of Chinese Academy of Sciences（中国科学院大学）；Shandong University（山东大学）；University of Science and Technology Beijing（北京科技大学）
PLANA3R: Zero-shot Metric Planar 3D Reconstruction via Feed-Forward Planar Splatting
The Hong Kong University of Science and Technology（香港科技大学）；Ant Group（蚂蚁集团）；Wuhan University（武汉大学）；Zhejiang University（浙江大学）；The Pennsylvania State University（宾夕法尼亚州立大学）
TRiGS: Temporal Rigid-Body Motion for Scalable 4D Gaussian Splatting
Sogang University（西江大学）；Pusan National University（釜山国立大学）；POSTECH（浦项科技大学）；Seoul National University（首尔国立大学）；Electronics and Telecommunications Research Institute（电子通信研究院）
GaussVid: Sparse-View Gaussian Splatting with 3D-Aware Video Diffusion Priors
The University of Hong Kong（香港大学）；School of Computing and Data Science, The University of Hong Kong（香港大学计算与数据科学学院）；Futurewei Technologies Inc（华为主流技术公司）
OracleGS: Grounding Generative Priors for Sparse-View Gaussian Splatting
ETH Zürich（苏黎世联邦理工学院）；Koç University（科卡大学）；KUIS AI Center（KUIS人工智能中心）；Technical University of Munich（慕尼黑技术大学）；Google（谷歌）；Munich Center for Machine Learning（慕尼黑机器学习中心）
JADE-GS: Joint Allocation of Deblurring Evidence for Event-Assisted 3D Gaussian Splatting
School of Mechatronic Engineering and Automation, Shanghai University（上海大学机电工程与自动化学院）；Shanghai Baoshan Shangda General Intelligent Robotics Research Institute（上海宝山尚大通用智能机器人研究院）；School of Computer Science and Technology, Tongji University（同济大学计算机科学与技术学院）
