{"ID":5937185,"CreatedAt":"2026-07-07T03:14:33.014478982Z","UpdatedAt":"2026-07-09T08:57:31.292890551Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.04837","arxiv_id":"2607.04837","title":"Athena-WBC: Capability-Aligned Policy Experts for Long-Tail Humanoid Whole-Body Control","abstract":"Large-scale humanoid motion-tracking controllers are commonly improved by reallocating training effort: difficult motions are sampled more often, isolated into smaller subsets, or assigned to specialized experts. We show that this view is incomplete. In strong whole-body-control baselines, a residual set of feasible training clips remains unsolved even under targeted training, especially for high-dynamic transitions and balance-critical motions. These failures arise not only from insufficient exposure, but from a mismatch between the motion demands and the effective capability induced by the default training recipe. We propose Athena-WBC, a compact teacher-student pipeline with capability-aligned policy experts for long-tail humanoid whole-body control. Dynamic experts use a tracking-focused, constraint-aware objective that removes conservative effort and temporal-control penalties while preserving physical feasibility constraints; balance experts use a gravity curriculum to improve early-training survivability. The resulting privileged teachers are motion-routed for DAgger distillation and then compressed into a single controller with deployable observations followed by RL fine-tuning. Experiments on a full-size humanoid show improved recovery of training-set long-tail motions and better held-out tracking than a strong SONIC-recipe baseline, using only a small number of experts.","short_abstract":"Large-scale humanoid motion-tracking controllers are commonly improved by reallocating training effort: difficult motions are sampled more often, isolated into smaller subsets, or assigned to specialized experts. We show that this view is incomplete. In strong whole-body-control baselines, a residual set of feasible tr...","url_abs":"https://arxiv.org/abs/2607.04837","url_pdf":"https://arxiv.org/pdf/2607.04837v1","authors":"[\"Yuan Jiang\",\"Ningyuan Zhang\",\"Xicun Yang\",\"Shidi Li\",\"Yuzhi Jiang\",\"Zhiyi Rong\",\"Shuaikang Ma\",\"Chuanzheng Li\",\"Jie Chen\"]","published":"2026-07-06T09:10:04Z","proceeding":"cs.RO","tasks":"[\"cs.RO\"]","methods":"[]","has_code":false}