Papers
arxiv:2611.24789

HINT-WAM: Hindsight-Informed Training for World Action Models

Published on Nov 18
· Submitted by
Tuan Dat
on Nov 19
Authors:
,
,

Abstract

World action models (WAMs) have shown promising generalization and data efficiency in robot manipulation by coupling action generation with predictions of future visual dynamics. Translating these capabilities into reliable task execution, however, remains a challenge for existing post-training methods. Offline supervised fine-tuning provides dense supervision on expert trajectories, but its flow-matching action expert is trained only on noised demonstration actions and never on the intermediate states produced by its own sampler; task-specific adaptation can also compromise pretrained capabilities. On-policy reinforcement learning trains on the policy's own behavior, yet sparse task rewards make exploration and credit assignment difficult, while dense reward shaping still provides scalar evaluations rather than direct action targets. We introduce HINT-WAM, the first on-policy self-distillation framework that supervises the action expert on its own sampling trajectories using hindsight, the future video of the demonstration, as privileged information available to the WAM itself. For each demonstration observation, the student generates its action through its own denoising trajectory, and at the states along this trajectory the same model acts as a teacher conditioned additionally on this hindsight, providing a conditional action distribution as a dense training target, while the student sees only deployment-time inputs and needs no environmental rewards or simulator interaction. To transfer this supervision to a flow-matching action expert, HINT-WAM distills the teacher into the student with an energy score, a distribution-level objective that matches the teacher's action distribution from the student's own samples rather than regressing its velocity field. The project web is available in https://tuandattt.github.io/hintwam/.

Community

Paper submitter

Hi authors, thanks for the work. A quick question on Table 6: for HINT-WAM vs. velocity matching, 6.16 / 1.59 = 3.87 rather than the reported t = 3.62, and an exact sign test on 48 vs. 17 gives p = 0.00015 rather than 0.00042; the other rows reproduce. Details in this GitHub issue: https://github.com/tuandattt/hintwam_code/issues/2

This is an automated message from the Librarian Bot. I found the following papers similar to this paper.

The following papers were recommended by the Semantic Scholar API

Please give a thumbs up to this comment if you found it helpful!

If you want recommendations for any Paper on Hugging Face checkout this Space

You can directly ask Librarian Bot for paper recommendations by tagging it in a comment: @librarian-bot recommend

Sign up or log in to comment

Get this paper in your agent:

hf papers read 2611.24789
Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper 1

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2611.24789 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2611.24789 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.