Wristband Gaussian Loss deterministically Gaussianizes point embeddings via sphere-interval decomposition with a Lean-verified proof that the pushforward is uniform iff the source is N(0,I_d), plus efficient repulsion-energy computation and application to deterministic Gaussian autoencoders.
Title resolution pending
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
citation-role summary
background 4
citation-polarity summary
years
2026 6verdicts
UNVERDICTED 6roles
background 4polarities
background 4representative citing papers
EAM reformulates adjoint matching for diffusion fine-tuning with linear base drift to allow efficient deterministic sampling and closed-form adjoints while matching or exceeding prior performance.
BRIDGE improves coarse-mask local image editing in DiT models by routing background and subject paths separately and using a discrete geometric gate on positional embeddings to reduce mask-shape bias.
DFP is a one-step generative policy using Wasserstein gradient flow on a drifting model backbone, with a top-K behavior cloning surrogate, that reaches SOTA on Robomimic and OGBench manipulation tasks.
Gram-MMD is a texture-aware realism metric that computes MMD on upper-triangular Gram matrices from backbone activations, providing complementary information to semantic distributional metrics.
Stable Audio 3 develops fast latent diffusion models for variable-length audio generation and editing via a semantic-acoustic autoencoder and adversarial post-training.
citing papers explorer
-
The Wristband Gaussian Loss: Deterministic, Composable Latents via a Sphere-Interval Decomposition
Wristband Gaussian Loss deterministically Gaussianizes point embeddings via sphere-interval decomposition with a Lean-verified proof that the pushforward is uniform iff the source is N(0,I_d), plus efficient repulsion-energy computation and application to deterministic Gaussian autoencoders.
-
Efficient Adjoint Matching for Fine-tuning Diffusion Models
EAM reformulates adjoint matching for diffusion fine-tuning with linear base drift to allow efficient deterministic sampling and closed-form adjoints while matching or exceeding prior performance.
-
BRIDGE: Background Routing and Isolated Discrete Gating for Coarse-Mask Local Editing
BRIDGE improves coarse-mask local image editing in DiT models by routing background and subject paths separately and using a discrete geometric gate on positional embeddings to reduce mask-shape bias.
-
Drifting Field Policy: A One-Step Generative Policy via Wasserstein Gradient Flow
DFP is a one-step generative policy using Wasserstein gradient flow on a drifting model backbone, with a top-K behavior cloning surrogate, that reaches SOTA on Robomimic and OGBench manipulation tasks.
-
Gram-MMD: A Texture-Aware Metric for Image Realism Assessment
Gram-MMD is a texture-aware realism metric that computes MMD on upper-triangular Gram matrices from backbone activations, providing complementary information to semantic distributional metrics.
-
Stable Audio 3
Stable Audio 3 develops fast latent diffusion models for variable-length audio generation and editing via a semantic-acoustic autoencoder and adversarial post-training.