AI Paper Atlas

Research map / Probabilistic and scientific modeling / Variational and generative sampling

Discrete Adjoint Schrödinger Bridge Sampler

Wei Guo, Yuchen Zhu, Xiaochen Du, Juno Nam, Yongxin Chen, Rafael Gomez-Bombarelli, Guan-Horng Liu, Molei Tao, Jaemoo Choi

ICML 2026 · Probabilistic and scientific modeling › Variational and generative sampling · approach: Posterior sampling with diffusion guidance · 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
use discrete ASBS instead of LEAPSdiscrete neural sampler · Ising L=24 beta_hightraining runtime (h): 8.4 -> 0.2Improved
use discrete ASBS instead of MDNSdiscrete neural sampler · Ising L=24 beta_hightraining runtime (h): 16.8 -> 0.2Improved
use discrete ASBS instead of LEAPS at critical temperatureuniform-based sampler · Ising L=24 beta_criticalEW2: 96.5 -> 53.7Improved
use discrete ASBS instead of LEAPS at low temperatureuniform-based sampler · Ising L=24 beta_lowEW2: 176.6 -> 2.5Improved
use discrete ASBS instead of LEAPS at low temperatureuniform-based sampler · Potts L=16 beta_lowEW2: 90.5 -> 1.4Improved
use discrete ASBS instead of masked MDNS at high temperaturesampler · Ising L=24 beta_highEW2: 0.1 -> 5.4Hurt
use discrete ASBS instead of MDNS at critical temperaturesampler · Potts L=16 beta_criticalEW2: 1.9 -> 14.6Hurt
use adjoint matching loss instead of denoising matching for the controller (ablation)DASBS controller · Potts L=8 N=3 beta_high=0.5EW2 convergence speedImproved
add trajectory importance reweighting to training losses (ablation)DASBS · Potts L=8 N=3 beta_high=0.5convergence speedHurt
use non-memoryless noise schedule (alpha > 0) instead of memoryless (alpha = 0) (ablation)DASBS · Ising L=24 beta_high=0.282-pt correlation error and EW2Improved
vary gamma or alpha of schedule gamma/(t+alpha) away from optimum (ablation)DASBS · Ising L=24 beta_high=0.282-pt correlation error and EW2Mixed
use Metropolis-Hastings baseline at critical temperatureMH · Ising L=24 beta_criticalEW2: 53.7 -> 293.3Hurt

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