Unverified50% confidenceFactExact time
HoloBoxing adopts a hierarchical control architecture: freezing a pretrained whole-body controller and training only a compact upper-layer planner.
1
Sources
50%
Confidence
Long-term
Relevance
11/1/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedFreezing the whole-body controller and training only the upper-layer planner can avoid the catastrophic forgetting common in end-to-end training.74% similarUnverifiedThe solution is staged training: first train the booster paired with a rule-based tower, then freeze the booster and train the tower agent from scratch, and finally fine-tune the booster to work with the learned tower.72% similarUnverifiedThe approach of freezing the main model and training only a lightweight anchor generator provides a cost-controllable path for practical deployment.65% similarUnverifiedThe core design of HiRe-MoMa is to freeze an existing base policy and learn only additive correction residuals on top of its output, rather than training a mobile manipulation policy from scratch.64% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1124590API
curl https://kongchang.com/api/v1/knowledge/claims/1124590MCP
get_claim(id=1124590)