papers

Publications (6)

cs.CV2025

On Scaling Up 3D Gaussian Splatting Training

Hexu Zhao, Haoyang Weng, Daohan Lu +4

3D Gaussian Splatting (3DGS) is increasingly popular for 3D reconstruction due to its superior visual quality and rendering speed. However, 3DGS training currently occurs on a sing…

cs.CV2026

Solaris: Building a Multiplayer Video World Model in Minecraft

Georgy Savva, Oscar Michel, Daohan Lu +6

Existing action-conditioned video generation models (video world models) are limited to single-agent perspectives, failing to capture the multi-agent interactions of real-world env…

cs.CV2020

Meta Deformation Network: Meta Functionals for Shape Correspondence

Daohan Lu, Yi Fang

We present a new technique named "Meta Deformation Network" for 3D shape matching via deformation, in which a deep neural network maps a reference shape onto the parameters of a se…

cs.CV2023

Content-Based Search for Deep Generative Models

Daohan Lu, Sheng-Yu Wang, Nupur Kumari +4

The growing proliferation of customized and pretrained generative models has made it infeasible for a user to be fully cognizant of every model in existence. To address this need,…

cs.LG2025

Out-of-Distribution Detection Methods Answer the Wrong Questions

Yucen Lily Li, Daohan Lu, Polina Kirichenko +4

To detect distribution shifts and improve model safety, many out-of-distribution (OOD) detection methods rely on the predictive uncertainty or features of supervised models trained…

cs.CV2025

Cambrian-S: Towards Spatial Supersensing in Video

Shusheng Yang, Jihan Yang, Pinzhi Huang +12

We argue that progress in true multimodal intelligence calls for a shift from reactive, task-driven systems and brute-force long context towards a broader paradigm of supersensing.…