AFTER: A World Model with Adaptive Fast--Slow Timescales for Error-Driven Retention

Haoyi Zhang, Qi Zhang, Yunfan Ren, Yi Bin, Lei Zhu, Heng Tao ShenarXiv 2026 · arXiv

TL;DR

AFTER-WM is a bio-inspired world model that enables robots to adapt to sudden, persistent changes in their physical dynamics (like picking up a heavy object or suffering a motor failure). By employing a dual-timescale mechanism—a fast correction that reacts immediately and a slow correction that retains information—it overcomes the traditional trade-off between responsiveness and stability, outperforming state-of-the-art models by 16%–34% in prediction accuracy.

What Problem Does This Paper Address?

In robotics, a "world model" is a simulator in the robot's head that predicts how its state will change based on its actions. However, real-world dynamics are rarely static. A robot might pick up a payload of unknown weight, or a joint might lose power.

Existing world models struggle with a three-way trade-off:

  1. Responsiveness: They need to react immediately to sudden changes to prevent error accumulation.
  2. Stability: They shouldn't overreact to transient "bumps" or sensor noise.
  3. Persistence: They must remember the new dynamics even during "imagination" (open-loop rollouts) when no new sensor data is coming in.

Most current models adapt at a single timescale, meaning they are either too jittery (unstable) or too sluggish (unresponsive).

Methods

Inspired by predictive coding in the human brain, the authors propose AFTER-WM (Adaptive Fast–slow Timescales for Error-driven Retention). The architecture consists of three main modules:

  • Predictive Correction: Instead of using slow, computationally expensive gradient updates at test time, the model uses one-step prediction errors to update "online memories" instantly.
  • Dual-timescale Adaptation: This is the core innovation. It maintains two internal states:
  • A Fast State that reacts at once to errors but fades quickly (providing responsiveness).
  • A Slow State that builds up gradually and persists (providing stability and long-term retention).
  • Multiple Internal Models: The system uses a "router" to dynamically reweight a set of pre-trained "expert" models based on which one best fits the current (potentially changed) dynamics.

The training happens in two stages: first, training the experts and router on short segments; second, training the memory networks to read changes from error patterns.

Figure 2. Architecture of AFTER-WM (Sec. 3). Supp. Sec. B.2 gives the full computation diagram.

Datasets

The authors evaluated AFTER-WM on six challenging datasets:

  • JSHC & ESCP-HC: Established benchmarks involving joint failures and scaling of physical properties (gravity, mass) in HalfCheetah models.
  • Panda, UR5e, & Hopper: Three new simulated datasets introduced by the authors featuring robot arms and a legged robot with changing payloads, friction, and motor strengths.
  • ALFA: A real-world dataset consisting of fixed-wing UAV flights with engine and control-surface faults.

Key Insights and Ideas

  • Bio-Mimicry Works: The human brain doesn't just have one "learning rate." By splitting adaptation into fast and slow pathways, AFTER-WM can distinguish between a temporary disturbance (like a bump) and a permanent change (like a heavier cup).
  • Retention is Crucial for Planning: In open-loop rollouts (where a robot "imagines" the next 40 steps), most adaptive models revert to their original dynamics because they stop receiving error signals. AFTER-WM’s slow state stays fixed during these rollouts, ensuring the "imagined" trajectory remains accurate to the new reality.
  • Error-Driven vs. Gradient-Driven: The paper demonstrates that updating a hidden state based on error is significantly more effective for real-time robotics than performing gradient descent on model parameters during deployment.

Key Results

AFTER-WM consistently outperformed ten competitive baselines, including RSSM (DreamerV3) and TD-MPC2.

  • Prediction Accuracy: In simulations, AFTER-WM’s multi-step mean error was 16%–34% lower than the strongest compared models.
  • Phase Performance: It was the most accurate model across all phases of change: immediately after a change (1–4 steps), during ongoing changes, and even when no change occurred.
  • Control Performance: In a joint-failure control task, AFTER-WM achieved the highest mean return, significantly outperforming the next best model (MOLe) by 13.8 points.
Figure 1. (a) Illustration, not data, of predictive coding. (b) Data: AFTER-WM’s error reduction over the closest compared model.

Limitations and Future Work

  • State Representation: The current model operates on low-dimensional state vectors (angles, velocities). The authors acknowledge that extending this to high-dimensional image observations (pixels) is a necessary next step for broader embodied AI applications.
  • Real-Robot Deployment: While the model was tested on real UAV flight data, the control experiments were limited to simulation. Testing the full closed-loop planning on physical robotic hardware remains future work.
  • Expert Diversity: The model relies on pre-trained experts. If the new dynamics are completely outside the scope of what the experts can represent, the adaptation might be limited.

Summary updated

Abstract

In robotics and embodied AI, a core challenge for world models is adapting to sudden, persistent, yet initially unknown changes in robot dynamics during interaction. For instance, when a robotic arm grasps an object with an unknown payload, the robot dynamics change suddenly. If the world model fails to adapt, its prediction errors accumulate over the open-loop rollout and ultimately mislead the robot's actions. Existing world models, however, struggle to simultaneously satisfy three critical requirements for dynamics adaptation: responsiveness, reacting promptly to sudden changes to curb prediction error accumulation; stability, distinguishing persistent changes from transient disturbances to prevent incorrect updates; and persistence, retaining the adapted dynamics without new observations so that later predictions do not revert to the old dynamics. Inspired by predictive coding in the human brain with multi-timescale adaptation, we propose AFTER-WM, a world model with Adaptive Fast-slow Timescales for Error-driven Retention, whose prediction errors drive a fast correction that fades and a slow correction that persists, while dynamically adjusting the combination weights of pre-trained experts without altering them, to overcome the trade-offs among responsiveness, stability and persistence. On five simulated robot datasets and real UAV data, AFTER-WM has a lower multi-step mean error than all ten compared models and the highest mean return in a joint-failure control task. In simulation, its multistep mean error is 16%-34% below the strongest compared model's and is also the lowest 1-4 steps after a change and under transient disturbances alone, and its step-40 error is the lowest as well, reflecting responsiveness, stability and persistence. All code (method, baselines, experiments) and datasets will be released online.
BibTeX
@misc{zhang2026after,
  author = {Haoyi Zhang and Qi Zhang and Yunfan Ren and Yi Bin and Lei Zhu and Heng Tao Shen},
  title = {{AFTER: A World Model with Adaptive Fast--Slow Timescales for Error-Driven Retention}},
  year = {2026},
  eprint = {2611.15215},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2611.15215},
}
Figure