3 papers
cs.LG2025
A Tale of Two Symmetries: Exploring the Loss Landscape of Equivariant Models
YuQing Xie, Tess Smidt
Equivariant neural networks have proven to be effective for tasks with known underlying symmetries. However, optimizing equivariant networks can be tricky and best training practic…
cs.LG2025
Matching the Optimal Denoiser in Point Cloud Diffusion with (Improved) Rotational Alignment
Ameya Daigavane, YuQing Xie, Bodhi P. Vani +3
Diffusion models are a popular class of generative models trained to reverse a noising process starting from a target data distribution. Training a diffusion model consists of lear…
cs.LG2025
The Price of Freedom: Exploring Expressivity and Runtime Tradeoffs in Equivariant Tensor Products
YuQing Xie, Ameya Daigavane, Mit Kotak +1
-equivariant neural networks have demonstrated success across a wide range of 3D modelling tasks. A fundamental operation in these networks is the tensor product, which inter…