Distilling Instructions into Weights: Closed-Form Edits Fix a Robot Policy's Misreading
Overview
This paper introduces a method to repair instruction-following failures in generalist robot policies by directly editing model weights using closed-form distillation of explicit rewordings, avoiding gradients or new training data. The authors demonstrate that this approach significantly improves task success rates on held-out seeds compared to random edits or no edit, while releasing an open-source tool for end-to-end reproduction of the fix.
Generated from attributed reports · Updated 8 hours ago
Event evidence and corrections
0 attributed source owners. Ownership does not establish independent confirmation. Quantities are reported separately and are never added together.
Reported quantity · success episodes: 27 other · reported trials · Differing source assertions
“e before it reaches the bowl. Replaying 21 of these decisions under rewordings shows that it binds "in the bowl" to the wrong object. Closed-form instruction distillation copies the per-layer effect of an explicit rewording into the language model's MLP weights. On 128 held-out seeds, success rises from 27 to 106 episodes, with 81 fixed and 2 broken ($p=7\times10^{-22}$), while an update of the same size in random di”
Exact source · revision 1Source owner not reported
Reported quantity · success episodes: 8 other · reported trials · Differing source assertions
“rections leaves success unchanged. The edit also lifts two other tasks without detectable harm on the remaining 13, and a variant that stores 0.16% of the parameter count keeps most of its effect. Placed in the action expert or action head instead, the same distillation helps less or not at all. Our released tool reproduced the fix end to end on new held-out seeds, from 8/64 to 36/64. Edits aimed at perception, a mis”
Exact source · revision 1Source owner not reported
Report timeline
Follow attributed reports and material updates.
- arXiv Robotics — research abstractsSignalDistilling Instructions into Weights: Closed-Form Edits Fix a Robot Policy's Misreading
This paper introduces a method to repair instruction-following failures in generalist robot policies by directly editing model weights using closed-form distillation of explicit rewordings, avoiding gradients or new training data. The authors demonstrate that this approach significantly improves task success rates on held-out seeds compared to random edits or no edit, while releasing an open-source tool for end-to-end reproduction of the fix.
Event coverage history
There is not enough continuous observation data to show a trend.
Timezone · UTC
Article dates follow your selected timezone. Briefing editions use Hong Kong time (UTC+8).