From the 1 of 6 linked papers with an AI index.
6 papers
Steering Robustness into World Action Models via Mechanistic Interpretability and Optimal Control
Jihoon Hong, Julian Skifstad, Qiyue Dai +2
The paper investigates how to improve the robustness of World Action Models (WAMs) by analyzing their internal activations with mechanistic interpretability and applying a model‑ba…
Activation Steering of Video Generation Models via Reduced-Order Linear Optimal Control
Jihoon Hong, Alice Chan, Qiyue Dai +2
Text-to-video (T2V) models trained on large-scale web data can generate undesired content, motivating interventions that reduce harmful outputs without sacrificing visual quality.…
FieryGS: In-the-Wild Fire Synthesis with Physics-Integrated Gaussian Splatting
Qianfan Shen, Ningxiao Tao, Qiyu Dai +6
We consider the problem of synthesizing photorealistic, physically plausible combustion effects in in-the-wild 3D scenes. Traditional CFD and graphics pipelines can produce realist…
RefracGS: Novel View Synthesis Through Refractive Water Surfaces with 3D Gaussian Ray Tracing
Yiming Shao, Qiyu Dai, Chong Gao +6
Novel view synthesis (NVS) through non-planar refractive surfaces presents fundamental challenges due to severe, spatially varying optical distortions. While recent representations…
Robust Single-shot Structured Light 3D Imaging via Neural Feature Decoding
Jiaheng Li, Qiyu Dai, Lihan Li +4
We consider the problem of active 3D imaging using single-shot structured light systems, which are widely employed in commercial 3D sensing devices such as Apple Face ID and Intel…
RainyGS: Efficient Rain Synthesis with Physically-Based Gaussian Splatting
Qiyu Dai, Xingyu Ni, Qianfan Shen +3
We consider the problem of adding dynamic rain effects to in-the-wild scenes in a physically-correct manner. Recent advances in scene modeling have made significant progress, with…