4 papers
NNiT: Width-Agnostic Neural Network Generation with Structurally Aligned Weight Spaces
Jiwoo Kim, Swarajh Mehta, Hao-Lun Hsu +3
Generative modeling of neural network parameters is often tied to architectures because standard parameter representations rely on known weight-matrix dimensions. Generation is fur…
True Self-Supervised Novel View Synthesis is Transferable
Thomas W. Mitchel, Hyunwoo Ryu, Vincent Sitzmann
In this paper, we identify that the key criterion for determining whether a model is truly capable of novel view synthesis (NVS) is transferability: Whether any pose representation…
Scaling View Synthesis Transformers
Evan Kim, Hyunwoo Ryu, Thomas W. Mitchel +1
Geometry-free view synthesis transformers have recently achieved state-of-the-art performance in Novel View Synthesis (NVS), outperforming traditional approaches that rely on expli…
SE(3)-Equivariant Robot Learning and Control: A Tutorial Survey
Joohwan Seo, Soochul Yoo, Junwoo Chang +6
Recent advances in deep learning and Transformers have driven major breakthroughs in robotics by employing techniques such as imitation learning, reinforcement learning, and LLM-ba…