Predict Before You Deploy: Offline Prediction of Quantization-Induced Task Degradation for World Action Models

arXiv:2609.19441 · cs.RO, cs.AI · Submitted 2026-09-16 · Read on arXiv

cs.RO, cs.AI

Submitted: 2026-09-16

Updated: 2026-09-16

Comments: 9 pages, 3 figures, and 3 tables

Code: https://github.com/jiuyixu25/PreDE

Project page: https://dropbox.github.io/hqq_blog

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Quantization — 63× in this paper · explained in 12 episodes
• Calibration — 16× in this paper · explained in 7 episodes
• Benchmark — 7× in this paper · explained in 2 episodes
• Deferral — 7× in this paper · explained in 2 episodes
• Transformer — 5× in this paper · explained in 2 episodes
• Diffusion Model — 4× in this paper · explained in 8 episodes
• Diffusion Models — 4× in this paper · explained in 6 episodes
• Robustness — 2× in this paper · explained in 5 episodes
• Benchmarking — 1× in this paper · explained in 3 episodes
• CVF International Conference on Computer Vision — 1× in this paper
• Consistency — 1× in this paper · explained in 3 episodes
• Fine-Tuning — 1× in this paper · explained in 5 episodes
• Regret — 1× in this paper · explained in 3 episodes
• World Model — 1× in this paper · explained in 7 episodes

Sources

• Cosmos Policy: Fine-Tuning Video Models for Visuomotor Control and Planning
• Unified Video Action Model
• mimic-video: Video-Action Models for Generalizable Robot Control Beyond VLAs
• RynnVLA-002: A Unified Vision-Language-Action and World Model
• Fast-WAM: Do World Action Models Need Test-time Future Imagination?
• SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Models
• ViDiT-Q: Efficient and Accurate Quantization of Diffusion Transformers for Image and Video Generation
• OpenVLA: An Open-Source Vision-Language-Action Model
• Octo: An Open-Source Generalist Robot Policy
• A White Paper on Neural Network Quantization
• GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers
• QuantVLA: Scale-Calibrated Post-Training Quantization for Vision-Language-Action Models
• Mix-QVLA: Task-Evidence-Aware Mixed-Precision Quantization of Vision-Language-Action Models
• What Matters in Learning from Offline Human Demonstrations for Robot Manipulation
• RoboCasa: Large-Scale Simulation of Everyday Tasks for Generalist Robots

Related papers

• FMT x: An Efficient and Asymptotically Optimal Extension of the Fast Marching Tree for Dynamic Replanning
• MPCFormer: A physics-informed data-driven approach for explainable socially-aware autonomous driving
• RoboLab: A High-Fidelity Simulation Benchmark for Analysis of Task Generalist Policies
• HRDexDB: A 4D Dexterous Grasping Dataset Across Human and Multiple Robot Embodiments
• APT: Action Expert Pretraining Improves Instruction Generalization of Vision-Language-Action Policies
• Fine-tuning is Not Enough: A Parallel Framework for Collaborative Imitation and Reinforcement Learning in End-to-end Autonomous Driving