{"ID":23475910,"CreatedAt":"2026-09-18T01:09:05.407443952Z","UpdatedAt":"2026-09-20T18:11:56.143995915Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2609.19441","arxiv_id":"2609.19441","title":"Predict Before You Deploy: Offline Prediction of Quantization-Induced Task Degradation for World Action Models","abstract":"World action models (WAMs) rely on video-generation backbones, requiring substantial memory and compute for deployment. Post-training quantization reduces memory and can accelerate inference, but bit width, grouping, and quantizer choice define a large configuration space. Identifying configurations that preserve task performance through exhaustive closed-loop evaluation is costly. We propose PreDE (Predict Before You Deploy), a policy-calibrated framework for predicting quantization-induced task degradation from offline action deviations. Using closed-loop outcomes from a small development set, PreDE calibrates two thresholds and accepts, rejects, or defers new configurations using a fixed observation log. Under a within-setting label-ordering hypothesis, the rule issues decisions where all thresholds consistent with the development labels agree. Across five WAMs and four benchmark settings, quantization produces configuration-dependent task losses that cannot be explained by bit width alone or a shared deviation threshold. Across 28 held-out configurations from two policies, PreDE issued 21 decisions before observing closed-loop outcomes (75% coverage), all matching the observed acceptable or degraded labels. Deferred candidates included both acceptable outcomes and a 33-percentage-point loss. In 450 Franka Research 3 trials across two independently fine-tuned policies, all configurations assigned to high-deviation groups before testing showed significant degradation, while low-deviation comparisons showed no statistically significant degradation. On the real robot, W4A4 achieved a 1.37x action-query speedup and approximately 44% lower peak memory. These results support policy-specific behavioral calibration for quantization configuration selection while identifying candidates that require closed-loop evaluation. The code is available at https://github.com/jiuyixu25/PreDE.","short_abstract":"World action models (WAMs) rely on video-generation backbones, requiring substantial memory and compute for deployment. Post-training quantization reduces memory and can accelerate inference, but bit width, grouping, and quantizer choice define a large configuration space. Identifying configurations that preserve task...","url_abs":"https://arxiv.org/abs/2609.19441","url_pdf":"https://arxiv.org/pdf/2609.19441v1","authors":"[\"Jiuyi Xu\",\"Jinjia Guo\",\"Meida Chen\",\"Jing Du\",\"Yangming Shi\"]","published":"2026-09-16T21:25:37Z","proceeding":"cs.RO","tasks":"[\"cs.RO\",\"cs.AI\"]","methods":"[]","has_code":false,"code_links":[{"ID":639807,"CreatedAt":"2026-09-18T01:09:05.407443952Z","UpdatedAt":"2026-09-18T01:09:05.407443952Z","DeletedAt":null,"paper_id":23475910,"paper_url":"https://arxiv.org/abs/2609.19441","paper_title":"Predict Before You Deploy: Offline Prediction of Quantization-Induced Task Degradation for World Action Models","repo_url":"https://github.com/jiuyixu25/PreDE","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}