Faster Imitation by Re-timing Demonstrations Within the Controller Limit
Overview
This paper addresses the collapse of imitation policies when demonstrations are sped up beyond two to three times their original rate.
Generated from attributed reports · Updated 3 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.
Environment: simulation
“alisable. Every command is then realisable by construction, the demonstrated geometry is preserved, and the speed-up lands only where the demonstrator left slack. On four simulated robomimic tasks, 200 held-out seeds per cell, a merge cap of two is at or above the frozen policy's success on all four, by 14 points on Square, and shortens the successful episodes. At matched tempo, uniform re-timing loses 9 and 16 point”
Exact source · revision 1Source owner not reported
Reported quantity · success improvement: 14 other · Basis not reported
“alisable. Every command is then realisable by construction, the demonstrated geometry is preserved, and the speed-up lands only where the demonstrator left slack. On four simulated robomimic tasks, 200 held-out seeds per cell, a merge cap of two is at or above the frozen policy's success on all four, by 14 points on Square, and shortens the successful episodes. At matched tempo, uniform re-timing loses 9 and 16 point”
Exact source · revision 1Source owner not reported
Reported quantity · loss on Square: 9 other · Basis not reported
“alisable. Every command is then realisable by construction, the demonstrated geometry is preserved, and the speed-up lands only where the demonstrator left slack. On four simulated robomimic tasks, 200 held-out seeds per cell, a merge cap of two is at or above the frozen policy's success on all four, by 14 points on Square, and shortens the successful episodes. At matched tempo, uniform re-timing loses 9 and 16 point”
Exact source · revision 1Source owner not reported
Reported quantity · loss on Can: 16 other · Basis not reported
“alisable. Every command is then realisable by construction, the demonstrated geometry is preserved, and the speed-up lands only where the demonstrator left slack. On four simulated robomimic tasks, 200 held-out seeds per cell, a merge cap of two is at or above the frozen policy's success on all four, by 14 points on Square, and shortens the successful episodes. At matched tempo, uniform re-timing loses 9 and 16 point”
Exact source · revision 1Source owner not reported
Reported quantity · merge cap: 2 other · Basis not reported
“alisable. Every command is then realisable by construction, the demonstrated geometry is preserved, and the speed-up lands only where the demonstrator left slack. On four simulated robomimic tasks, 200 held-out seeds per cell, a merge cap of two is at or above the frozen policy's success on all four, by 14 points on Square, and shortens the successful episodes. At matched tempo, uniform re-timing loses 9 and 16 point”
Exact source · revision 1Source owner not reported
Reported quantity · reference motions: 429 other · Basis not reported
“y tracker: re-timing 429 reference motions within its velocity envelope succeeds on 71% of clips at 2.3x, against 51% for uniform time scaling at 2x.”
Exact source · revision 1Source owner not reported
Reported quantity · seeds per cell: 200 other · Basis not reported
“alisable. Every command is then realisable by construction, the demonstrated geometry is preserved, and the speed-up lands only where the demonstrator left slack. On four simulated robomimic tasks, 200 held-out seeds per cell, a merge cap of two is at or above the frozen policy's success on all four, by 14 points on Square, and shortens the successful episodes. At matched tempo, uniform re-timing loses 9 and 16 point”
Exact source · revision 1Source owner not reported
Report timeline
Follow attributed reports and material updates.
- arXiv Robotics — research abstractsSignalFaster Imitation by Re-timing Demonstrations Within the Controller Limit
This paper addresses the collapse of imitation policies when demonstrations are sped up beyond two to three times their original rate.
Event coverage history
Current attention 5·Peak within the comparable range 5（2026-11-04 05:00 UTC）·Change within the comparable range over 24 hours –
The trend compares participants observed continuously; its scope may be narrower than current attention totals. Hover or click to explore hourly observations, or use the left and right arrow keys.
Timezone · UTC
Article dates follow your selected timezone. Briefing editions use Hong Kong time (UTC+8).