# Supervise What Decides Success: Criterion-Aligned Auxiliary Losses for Latent World-Model Planning

arXiv: https://arxiv.org/abs/2610.01224 · HTML: https://mlsanity.com/paper/2610.01224/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Latent predictive world models, one of 11 directions in World models.
- Builds on 14 of its 44 references that are in the map.
- First posted on arXiv 1 Oct 2026.

## Placed in

- World models / [Latent predictive world models](https://mlsanity.com/wm/latent-predictive-world-models/)

## Builds on (most cited first, 14 of 14)

- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [DeepMind Control Suite](https://mlsanity.com/paper/1801.00690/) (2018)
- [V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning](https://mlsanity.com/paper/2506.09985/) (2025)
- [robosuite: A Modular Simulation Framework and Benchmark for Robot Learning](https://mlsanity.com/paper/2009.12293/) (2020)
- [LeWorldModel: Stable End-to-End Joint-Embedding Predictive Architecture from Pixels](https://mlsanity.com/paper/2603.19312/) (2026)
- [WorldArena: A Unified Benchmark for Evaluating Perception and Functional Utility of Embodied World Models](https://mlsanity.com/paper/2602.08971/) (2026)
- [How Many Random Seeds? Statistical Power Analysis in Deep Reinforcement Learning Experiments](https://mlsanity.com/paper/1806.08295/) (2018)
- [RoboWM-Bench: A Benchmark for Evaluating World Models in Robotic Manipulation](https://mlsanity.com/paper/2604.19092/) (2026)
- [Predictive but Not Plannable: RC-aux for Latent World Models](https://mlsanity.com/paper/2605.07278/) (2026)
- [Foresight: Failure Detection for Long-Horizon Robotic Manipulation with Action-Conditioned World Model Latents](https://mlsanity.com/paper/2606.23085/) (2026)
- [World Model Control by Trajectory Reachability Metrics](https://mlsanity.com/paper/2605.22164/) (2026)
- [Is Forward Prediction Enough? Physical State Grounding for JEPA World Models](https://mlsanity.com/paper/2608.06799/) (2026)
- [PhyLatent: Learning Dynamics-Relevant Representations for JEPA World Models](https://mlsanity.com/paper/2608.05720/) (2026)
- [Representing Positional Information in Generative World Models for Object Manipulation](https://mlsanity.com/paper/2409.12005/) (2024)

## Abstract (arXiv)

Latent world models plan by scoring candidate action sequences with distances in latent space. However, task success is judged by physical quantities, which we call the success-criterion quantities. In all four latent world models we examine, the end-effector position is encoded in the latent state with an error larger than the success criterion allows. Such a latent state cannot separate successful candidates from failing ones. We propose an auxiliary loss that uses success-criterion quantities as training targets, whereas existing latent world models take them only as inputs. During training, a linear head on the encoder and predictor outputs regresses the success-criterion quantities, and the regression error is added to the training loss. The head is discarded after training, so the model, its cost, and its inputs at test time are unchanged. This loss alone improves the success rate on PushT and cube by 3.5% and 3.4% (absolute), respectively, and both improvements are statistically significant. A success criterion thus specifies what a world model must retain in its latent state, and we show that it can serve directly as a training target.