AI Paper Atlas

Research map / Learning theory and algorithms / Optimal transport

Neural Hamilton--Jacobi Characteristic Flows for Optimal Transport

Yesom Park, Shu Liu, Mo Zhou, Stanley Osher

ICLR 2026 · Learning theory and algorithms › Optimal transport · approach: Transport map estimation · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
replace implicit HJ loss with PINN HJ-residual loss (ablation)NCF · Gaussian OT d=64UVP: 1.683 -> 0.858Improved
replace implicit HJ loss with PINN HJ-residual loss (ablation)NCF · Gaussian OT d=2UVP: 0.080 -> 0.010Improved
use NCF instead of MM-v1 (dual min-max ICNN)NCF · Gaussian OT d=32UVP: 0.374 vs 0.436Hurt
use NCF instead of MM-v1NCF · Gaussian OT d=2-16UVP: 0.161 -> 0.010 (d=2)Improved
use NCF instead of NOTNCF · Gaussian OT d=64UVP: 196.831 -> 0.858Improved
use NCF instead of MM-v1 for color transferNCF · Winter-Summer color transferhistogram intersection: 0.7295 -> 0.8914Improved
use NCF instead of NOT for color transferNCF · Gogh-Photograph color transferEMD: 0.0008 -> 0.0003Improved
use NCF instead of GNOT for class-conditional OTNCF · Fashion MNIST to MNISTaccuracy (%): 83.22 -> 83.42No clear effect
use NCF instead of GNOT for class-conditional OTNCF · Fashion MNIST to MNISTFID: 5.26 -> 18.27Hurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy