The reward paid out highest when the video stopped moving

Quan-Dung Pham and colleagues at VinMotion and the University of Southern California have built HumanoidVLN, a physics-grounded simulator whose environments are drawn partly from gaussian splatting reconstructions of real interiors — and whose headline result is how badly current navigation models cope with having legs.

Why it matters: Vision-language navigation benchmarks have mostly assumed a wheeled robot gliding along a floor plan. A bipedal robot has to stay upright, its camera pitches and rolls with every step, and no two humanoid platforms are shaped alike.

Wei Zhang and colleagues at Northwestern Polytechnical University and vivo's BlueImage Lab identify a specific failure in how city-scale gaussian splats are built: each level of the octree is optimised in isolation, with no communication between them.

Why it matters: Octree-based anchor splatting is how the field currently scales to whole cities — coarse levels hold building masses, fine levels hold detail. It works, and the artefacts it produces have mostly been treated as the price of scale.

Zongjian Ding and colleagues at the Chinese Academy of Sciences, HKUST, Zhejiang University and the Beijing Institute of Technology report the highest published LERF-MASK accuracy for object extraction from a pre-built splat scene — with the scene frozen and no access to the cameras that built it.

Why it matters: Most 3D editing workflows receive a finished splat, not a capture session. The source images and reconstruction cameras are somebody else's, from months ago, and were never shipped with the asset.

Haeyun Choi, Minhyuk Jang and I-Gil Kim, at the University of Virginia and KT's R&D Center in Seoul, set themselves a deliberately punishing capture setting — two blurred frames, known intrinsics, nothing else — and get usable novel-view synthesis out of it.

Why it matters: Every splat pipeline is a negotiation with how carefully someone filmed. The published results assume a steady orbit and enough overlap; real capture is two frames grabbed while walking past.

Nienke Driessen and colleagues at TU Delft, Kiel, Adam Mickiewicz University and KAUST have built a wildfire simulator that burns gaussians — running ignition, heat transfer and flame propagation natively on a semantics-enriched splat reconstruction of a real boreal forest.

Why it matters: Physics-based wildfire models are good, and they mostly run on invented forests — synthetic environments where every tree's structure and fuel load is known because someone specified it. Real landscapes arrive as aerial imagery, incomplete and uncertain, which is exactly the case those models can't take.