Nabla-R2D3 aligns 3D-native diffusion models with human preferences by backpropagating multi-view 2D reward gradients through the denoising process, improving reward without destroying the pretrained 3D prior.
Baking Symmetry into GFlowNets
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
GFlowNets have exhibited promising performance in generating diverse candidates with high rewards. These networks generate objects incrementally and aim to learn a policy that assigns probability of sampling objects in proportion to rewards. However, the current training pipelines of GFlowNets do not consider the presence of isomorphic actions, which are actions resulting in symmetric or isomorphic states. This lack of symmetry increases the amount of samples required for training GFlowNets and can result in inefficient and potentially incorrect flow functions. As a consequence, the reward and diversity of the generated objects decrease. In this study, our objective is to integrate symmetries into GFlowNets by identifying equivalent actions during the generation process. Experimental results using synthetic data demonstrate the promising performance of our proposed approaches.
citation-role summary
background 1
citation-polarity summary
fields
cs.GR 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Nabla-R2D3: Effective and Efficient 3D Diffusion Alignment with 2D Rewards
Nabla-R2D3 aligns 3D-native diffusion models with human preferences by backpropagating multi-view 2D reward gradients through the denoising process, improving reward without destroying the pretrained 3D prior.