AI Paper Atlas

Research map / Learning theory and algorithms / Combinatorial and search optimization

Pareto-Conditioned Diffusion Models for Offline Multi-Objective Optimization

Jatan Shrestha, Santeri Heiskanen, Kari Hepola, Severi Rissanen, Pekka Jääskeläinen, Joni Pajarinen

ICLR 2026 · Learning theory and algorithms › Combinatorial and search optimization · approach: Multi-objective optimization · 2 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
add multi-objective reweighting to Ref. Dir. conditioning (ablation)PCD · MO-Swimmer-v2, RE34, C10/MOP2HV: 3.53 -> 3.69 (Swimmer); 10.11 -> 10.17 (RE34); 10.47 -> 10.59 (C10/MOP2)Improved
add reweighting to Ref. Dir. conditioning (ablation)PCD · ZDT2 and RegexHV: 7.89 -> 6.25 (ZDT2); 5.55 -> 4.80 (Regex)Hurt
use reweighting instead of pruning low-quality points (ablation)PCD · ZDT2HV: 5.64 -> 6.25Improved
use reweighting instead of pruning low-quality points (ablation)PCD · RE34 and C10/MOP2HV: 10.16 -> 10.17 (RE34); 10.55 -> 10.59 (C10/MOP2)Improved
use reference-direction conditioning instead of Ideal (ablation)PCD without reweighting · MO-Swimmer-v2HV: 1.76 -> 3.53Improved
use reference-direction conditioning instead of D(best) points (ablation)PCD without reweighting · RE34HV: 9.32 -> 10.11Improved
raise classifier-free guidance scale above 2.5 (ablation)PCD · five representative tasksnormalized HVNo clear effect
increase reweighting temperature tau above 0.05 (ablation)PCD · ZDT2normalized HV: up to 15%Improved
increase reweighting temperature tau (ablation)PCD · C10/MOP2normalized HVNo clear effect
use stochastic EDM sampler instead of deterministic (ablation)PCD · MO-Hopper-v2, RE34, ZDT2HV: 4.47 -> 5.95 (Hopper); 9.47 -> 10.17 (RE34); 5.00 -> 6.25 (ZDT2)Improved
use stochastic EDM sampler instead of deterministic (ablation)PCD · RegexHV: 5.56 -> 4.80Hurt
increase number of selected conditioning points J from 4 to 32 (ablation)PCD · RE34HV: 6.56 -> 10.17Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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