# SteerQuant: Steering Quantization Error with Action-Guided Scaling in World-Action Models

arXiv: https://arxiv.org/abs/2609.39056 · HTML: https://mlsanity.com/paper/2609.39056/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Video-generation world models and simulators, one of 11 directions in World models.
- Builds on 10 of its 32 references that are in the map.
- First posted on arXiv 30 Sep 2026.

## Placed in

- World models / [Video-generation world models and simulators](https://mlsanity.com/wm/video-generation-world-models-and-simulators/)

## Builds on (most cited first, 10 of 10)

- [World Action Models are Zero-shot Policies](https://mlsanity.com/paper/2602.15922/) (2026)
- [Fast-WAM: Do World Action Models Need Test-time Future Imagination?](https://mlsanity.com/paper/2603.16666/) (2026)
- [Cosmos Policy: Fine-Tuning Video Models for Visuomotor Control and Planning](https://mlsanity.com/paper/2601.16163/) (2026)
- [Cosmos 3: Omnimodal World Models for Physical AI](https://mlsanity.com/paper/2606.02800/) (2026)
- [HALO: A Unified Vision-Language-Action Model for Embodied Multimodal Chain-of-Thought Reasoning](https://mlsanity.com/paper/2602.21157/) (2026)
- [ActQuant: Sub-4-bit Action-Guided Quantization for Vision-Language-Action Models](https://mlsanity.com/paper/2605.24011/) (2026)
- [TwinQuant: Learnable Subspace Decomposition for 4-Bit LLM Quantization](https://mlsanity.com/paper/2606.01556/) (2026)
- [MosaicQuant: Inlier-Outlier Disaggregation for Unified 4-Bit LLM Quantization](https://mlsanity.com/paper/2606.15652/) (2026)
- [QuantWAMs: Calibrating at the Right Granularity for World Action Models](https://mlsanity.com/paper/2607.28405/) (2026)
- [OnlineWM: Causality-Aware Active Online Learning for Effective World Modeling](https://mlsanity.com/paper/2609.23753/) (2026)

## Abstract (arXiv)

World-action models (WAMs) jointly generate future world states and actions through iterative denoising, using shared weights to process heterogeneous semantic streams of video, proprioceptive, and action tokens. Quantization reduces inference cost, but comparable numerical errors in different streams can have markedly different effects on final actions, making numerical accuracy alone insufficient for reliable control. We introduce SteerQuant, a 4-bit quantization framework for WAMs that steers errors toward computations with less influence on final actions. It maps how each stream's quantization errors affect final actions and uses this map to guide shared channel scaling. Activation scaling is further calibrated for each stream and denoising step to accommodate changes in activation ranges and action impact. This adapts quantization to different stream requirements without duplicating weights or increasing bit-widths for selected streams. To reduce the extra kernel launches and memory traffic introduced by scaling, we develop Rudder, a 4-bit inference engine for WAMs that fuses scaling and output compensation into low-bit kernels. Under W4A8 and W4A4, SteerQuant maintains mean LIBERO success within 0.8 percentage points of full precision, while delivering up to 2.23× denoising speedup over BF16 across three WAMs with reduced peak GPU memory usage. On a real dual-arm robot, W4A8 deployment achieves a 1.35× end-to-end inference speedup while maintaining average task success relative to BF16.