cs.CVNov 18, 2026

Target-Consistent Action Guidance via Semi-Unbalanced Optimal Transport for Drifting World Models

Authors: Md Abtahi Majeed Chowdhury, Md Rifat Ur Rahman, Md Sakib Hossain Shovon, Jaesik Choi, Minhyuk Sung

Organizations: Bangladesh University of Engineering and Technology · KAIST

Abstract

Action-conditioned world models let robots imagine the outcomes of their actions for planning and offline policy evaluation, but these uses need many rollouts, which multi-step diffusion makes expensive. Drifting models move the iteration from inference to training and generate samples in one network pass. DriftWorld brought this paradigm to action-conditioned world models; to strengthen action following, it repels predictions from the current frame, a construction borrowed from classifier-free guidance. We show that this accentuation has a target bias: the push persists even when a prediction matches the recorded future, in kernel, balanced, and unbalanced Wasserstein drifting fields alike. We introduce Mass-Share Accentuation (MSA) to remove this bias. MSA treats the current frame as a counterfactual destination competing with the recorded future in a semi-relaxed optimal transport problem; subtracting the closed-form share of the correct future makes the guidance vanish at the target, and the remainder is shared by all predictions. We prove that the recorded future is the unique fixed point along the motion direction for collapsed predictions, and that the guidance fades with prediction error. On Push-T, Robomimic, and BridgeV2, where trained models under-react rather than overshoot, MSA improves action ranking, response slope, and moving-region error over latent-space baselines at no inference cost, though these benchmarks do not isolate bias removal as the cause.

Figures & tables

Explore similar work

CardsList
  1. DriftWorld: Fast World Modeling through Drifting

    Jul 16, 2026Susie Lu, Haonan Chen, Weirui Ye +1World Models for RoboticsWorld Model-Based Planning

  2. Feedback World Model Enables Precise Guidance of Diffusion Policy

    May 15, 2026Tuo An, Jindou Jia, Gen Li +8World Model LearningWorld Models for Robotics

  3. Decoupled Drift-Diffusion World Models for Consistent Future Frame Prediction

    Oct 13, 2026Anton Arapin, Aditya Singh, Yixin Wang +2Aleatoric UncertaintyAction-Conditioned World Models