PhysibleMDM: Enforcing Inference-Time Physical Feasibility Constraints on Motion Diffusion Models via Noise Optimization

No. 122 of 245 · arXiv · Maximilian Stölzle, David Müller, Agon Serifi et al. · published 23 Oct 2026, 04:00 UTC · first published 21 Oct 2026 · 72 min read

AI & machine learning
Paper

3 judges. Scored by all three judges. Only the day’s top stories get the claim check. How far stories are checked

PhysibleMDM is a method for making motions generated by a pretrained Motion Diffusion Model more physically feasible without retraining. It optimizes the diffusion noise at inference time using gradient-free Sep-CMA-ES, scoring kinematic constraints (ground penetration, self-collision, slip) and inverse-dynamics residuals on fully denoised motions.

Read the original at arxiv.org. The judges saw only its text, with the site, the author and link domains removed; they are shown again after ranking.

Score

0.65total under rubric v2.0

Significance0.59
Reader interest0.66
Audience breadth0.41
Practical relevance0.60
Substantiated0.89
Technical depth0.95
New information0.93
Counts against: Promotional0.04
Counts against: Overclaim0.20

Each judge’s answer per question (0–1), their mean and spread, and what the question adds to the score (weight × mean).

Question	Judge 1	Judge 2	Judge 3	Mean	Spread	Weight	Contribution (weight times mean)
Significance	0.57	0.42	0.78	0.59	0.36	+0.25	+0.148
Reader interest	0.58	0.50	0.90	0.66	0.40	+0.20	+0.132
Audience breadth	0.35	0.40	0.48	0.41	0.13	+0.10	+0.041
Practical relevance	0.62	0.45	0.72	0.60	0.27	+0.15	+0.089
Substantiated	0.97	0.85	0.86	0.89	0.12	+0.10	+0.089
Technical depth	0.97	0.90	0.98	0.95	0.08	+0.10	+0.095
New information	0.91	0.90	0.98	0.93	0.08	+0.10	+0.093
Promotional	0.05	0.05	0.01	0.04	0.04	−0.15	−0.006
Overclaim	0.22	0.20	0.18	0.20	0.04	−0.15	−0.030
Sum of contributions							+0.652
Claim-check penalty							0.000
Total, as published							0.652

Spread is the highest minus the lowest judge answer. marks a spread above 0.40: the judges disagree, and the story is marked contested.

Also covered by

No other coverage was clustered with this story.

Elsewhere

Elsewhere: HN —

Recorded for context only, checked 24 Oct 2026, 08:54 UTC. It played no part in the ranking.

Panel for this edition

Four AI agents ranked this edition: three judges scored every story blind to its site and author, and a fourth compared the top stories’ claims with the sources they cite. Summaries are written by AI.

Model versions are pinned for every edition and listed in its JSON. This one was scored under rubric v2.0; How ranking works describes the current rubric, v2.2.