AI Paper Atlas

Research map / Probabilistic and scientific modeling / Molecules and proteins

Trajectory-Aware Heuristic Learning for Combinatorial Search

Mustafa Seddiqi, Marta Kersten-Oertel, Tiberiu Popa

ICML 2026 · Probabilistic and scientific modeling › Molecules and proteins · approach: Multimodal trajectory prediction

Read the paper

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 anchored HMM instead of step-based supervision with anchors (ablation)anchored HMM refinement · CubeLocalRank level-1 (HTM)Aggregate Rank@1: 0.413 vs. 0.399 (+1.4 pp)Improved
use learned emissions instead of uniform emissions in the HMM (ablation)anchored HMM refinement · CubeLocalRank level-1 (HTM)Aggregate Rank@1: 0.413 vs. 0.404 (+0.9 pp)Improved
add HMM forward-backward inference over prior-sampled pseudo-labeling (ablation)anchored HMM refinement · CubeLocalRank level-1 (HTM)Aggregate Rank@1: 0.413 vs. 0.381 (+3.2 pp)Improved
add neighbor consistency to goal-rooted restarts (ablation)CayleyPy-style restarts · CubeLocalRank level-1 (HTM)Aggregate Rank@1: 0.414 vs. 0.400 (+1.4 pp)Improved
add neighbor consistency to goal-rooted restarts (ablation)CayleyPy-style restarts · DeepCubeA HTM beam 2^18search optimality: 62.9% vs. 59.6% (+3.3 pp)Improved
add neighbor consistency to single-step trajectory pipeline (ablation)single-step pipeline · CubeLocalRank level-1 (HTM)Aggregate Rank@1: 0.422 vs. 0.382 (+4.0 pp)Improved
add neighbor consistency to single-step trajectory pipeline (ablation)single-step pipeline · DeepCubeA HTM beam 2^18search optimality: 63.3% vs. 58.1% (+5.2 pp)Improved
add neighbor consistency to scalar regression (ablation)regression objective · CubeLocalRank level-1 (HTM)Aggregate Rank@1: 0.418 vs. 0.399 (+1.9 pp)Improved
add classification and KL terms to regression plus neighbor consistency (ablation)training objective · CubeLocalRank level-1 (HTM)Aggregate Rank@1: 0.419 vs. 0.418 (+0.1 pp)No clear effect
scale training data from 10B to 52BOurs · DeepCubeA HTM beam 2^18optimality: 63.3% -> 68.1%Improved
scale training data from 10B to 52BCayleyPy-style · DeepCubeA HTM beam 2^18optimality: 59.6 -> 62.3Improved
scale training data from 10B to 52BOurs · DeepCubeA QTM beam 2^18optimality: 77.8% -> 80.5%Improved

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