SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2512.10401 · ICML · 2025

Diffusion differentiable resampling

Zheng Zhao, Jennifer Andersson

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 5 functions out of this paper's own repositories and ran 0 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

RepositoryRoleRan
zgbkdlm/diffres canonical 0 of 5
FunctionStatusWhere it lives
energy Not yet run zgbkdlm/diffres/demos/two_rings.py
pointer only (licence: MPL-2.0) · get_code("9e457c09d2d09e8e")
kf_pred Not yet run zgbkdlm/diffres/diffres/gaussian_filters.py
pointer only (licence: MPL-2.0) · get_code("1531bcaadf796cbc")
logpdf_likelihood Not yet run zgbkdlm/diffres/demos/two_rings.py
pointer only (licence: MPL-2.0) · get_code("efa11d55cd5871f8")
logpdf_prior Not yet run zgbkdlm/diffres/demos/two_rings.py
pointer only (licence: MPL-2.0) · get_code("28bf86a3292f9089")
nnx_load Not yet run zgbkdlm/diffres/diffres/nns.py
pointer only (licence: MPL-2.0) · get_code("b03551eda9bbdcef")

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

This paper is concerned with differentiable resampling in the context of sequential Monte Carlo (e.g., particle filtering). Drawing on reparametrisation, we propose a new resampling method that is informative and instantly differentiable, based on a training-free diffusion model surrogate. We theoretically prove that our diffusion resampling method provides a consistent resampling distribution, and we show empirically that it outperforms the state-of-the-art differentiable resampling methods on multiple filtering and parameter estimation benchmarks. Finally, we show that it achieves competitive end-to-end performance when used in learning a complex dynamics-decoder model with high-dimensional image observations.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2512.10401")
get_code_for_paper("2512.10401")
have("2512.10401")

Connect an agent — have() is free.