Trendoday

ResWAM: Learning What Changes, Not What Stays, for World-Action Models

World-action models (WAMs) augment vision-language-action policies (VLAs) with future prediction so that the policy can anticipate how its actions will affect the physical world. Existing WAMs supervi

  • Upvotes6
–Rank now
#17Peak rank
1Days on list
70Score · 7d
Nov 18, 2026First seen
Rank · 7 days

About this paper

ResWAM combines visual residual learning in frozen DINOv3 features with a lightweight dual-branch DiT trained via conditional flow matching to improve vision-language-action policy success while lowering training and inference compute.

World-action models (WAMs) augment vision-language-action policies (VLAs) with future prediction so that the policy can anticipate how its actions will affect the physical world. Existing WAMs supervise complete future observations. However, observations typically change little over an action chunk, so the future loss is dominated by copying static background content rather than learning task-relevant robot and object motion, limiting policy learning. Moreover, existing WAMs rely on large video generation models or separate world models, incurring heavy training and inference compute that hinders closed-loop deployment. To improve policy performance, we propose visual residual learning,…

world-action modelsvision-language-action policiesfuture predictionvisual residual learningfrozen DINOv3 spaceresidual learning targetfeature rankdual-branch DiTaction branchresidual branch
Upvotes
6
Authors
5
Published
Nov 14, 2026

Summary and abstract excerpt via Hugging Face Papers ↗ · arXiv.

Trending history

ResWAM: Learning What Changes, Not What Stays, for World-Action Models was first seen on Hugging Face · Daily papers on Nov 18, 2026. Since then it has appeared in 11 checks on 1 different day. Its best position was #17 of 30, reached on Nov 18, 05:28 UTC. It dropped off the list after Nov 18, 23:28 UTC.

Rank history

Position on Hugging Face · Daily papers at every check (lower is better).

#1#11#20#30 03:2808:2813:2818:2823:28 Nov 18, 03:28 UTC · #22Nov 18, 05:28 UTC · #17Nov 18, 07:28 UTC · #18Nov 18, 09:28 UTC · #24Nov 18, 11:28 UTC · #25Nov 18, 13:28 UTC · #28Nov 18, 15:28 UTC · #26Nov 18, 17:28 UTC · #29Nov 18, 19:28 UTC · #29Nov 18, 21:28 UTC · #30Nov 18, 23:28 UTC · #29

Last 14 days

Best rank per day (UTC).

Nov 9today

Metric history

Platform metric as reported by Hugging Face.

0369 03:2808:2813:2818:2823:28 Nov 18, 03:28 UTC · 5Nov 18, 05:28 UTC · 8Nov 18, 07:28 UTC · 8Nov 18, 09:28 UTC · 9Nov 18, 11:28 UTC · 9Nov 18, 13:28 UTC · 4Nov 18, 15:28 UTC · 4Nov 18, 17:28 UTC · 4Nov 18, 19:28 UTC · 4Nov 18, 21:28 UTC · 4Nov 18, 23:28 UTC · 4

Questions

Is ResWAM: Learning What Changes, Not What Stays, for World-Action Models trending on HF Daily Papers right now?

Not at the moment. It was last on the list on Nov 18, 23:28 UTC, after 1 day of trending.

What is the highest rank ResWAM: Learning What Changes, Not What Stays, for World-Action Models reached?

#17 on Hugging Face · Daily papers, on Nov 18, 05:28 UTC. Trendoday checks this list every 120 minutes.

How long has ResWAM: Learning What Changes, Not What Stays, for World-Action Models been trending?

It was first seen on Nov 18, 2026 and has been on the list on 1 day (11 checks) since.