RealtimeWAM: How Fast Can I Run My World Action Model?
Overview
Source roundup from published reports. Claims below are attributed to their publishers, not independently verified. arXiv Robotics — research abstracts: RealtimeWAM: How Fast Can I Run My World Action Model?. This paper presents RealtimeWAM, a general, training-free framework for low-latency inference in World Action Models (WAMs). It addresses the high inference latency of WAMs by coordinating parallel execution with adaptiv…
Generated from attributed reports · Updated 46 minutes 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 · mean inference latencies: 24.09 other · Basis not reported · Differing source assertions
“lus. On an RTX 4090, measured mean inference latencies are 24.09 and 63.09 ms, corresponding to average speedups of 8.90$\times$ and 10.67$\times$. Average success rates are 82.75% and 87.41%, respectively, within 0.02 and 0.53 percentage points of native inference. Across five real-world tasks, RealtimeWAM improves average success rates over native inference by 17.2 and 37.2 percentage points on FastWAM and OpenWAM,”
Exact source · revision 1Source owner not reported
Reported quantity · mean inference latencies: 63.09 other · Basis not reported · Differing source assertions
“lus. On an RTX 4090, measured mean inference latencies are 24.09 and 63.09 ms, corresponding to average speedups of 8.90$\times$ and 10.67$\times$. Average success rates are 82.75% and 87.41%, respectively, within 0.02 and 0.53 percentage points of native inference. Across five real-world tasks, RealtimeWAM improves average success rates over native inference by 17.2 and 37.2 percentage points on FastWAM and OpenWAM,”
Exact source · revision 1Source owner not reported
Reported quantity · average speedups: 8.9 other · Basis not reported · Differing source assertions
“lus. On an RTX 4090, measured mean inference latencies are 24.09 and 63.09 ms, corresponding to average speedups of 8.90$\times$ and 10.67$\times$. Average success rates are 82.75% and 87.41%, respectively, within 0.02 and 0.53 percentage points of native inference. Across five real-world tasks, RealtimeWAM improves average success rates over native inference by 17.2 and 37.2 percentage points on FastWAM and OpenWAM,”
Exact source · revision 1Source owner not reported
Reported quantity · average speedups: 10.67 other · Basis not reported · Differing source assertions
“lus. On an RTX 4090, measured mean inference latencies are 24.09 and 63.09 ms, corresponding to average speedups of 8.90$\times$ and 10.67$\times$. Average success rates are 82.75% and 87.41%, respectively, within 0.02 and 0.53 percentage points of native inference. Across five real-world tasks, RealtimeWAM improves average success rates over native inference by 17.2 and 37.2 percentage points on FastWAM and OpenWAM,”
Exact source · revision 1Source owner not reported
Reported quantity · average success rates: 82.75 other · Basis not reported · Differing source assertions
“lus. On an RTX 4090, measured mean inference latencies are 24.09 and 63.09 ms, corresponding to average speedups of 8.90$\times$ and 10.67$\times$. Average success rates are 82.75% and 87.41%, respectively, within 0.02 and 0.53 percentage points of native inference. Across five real-world tasks, RealtimeWAM improves average success rates over native inference by 17.2 and 37.2 percentage points on FastWAM and OpenWAM,”
Exact source · revision 1Source owner not reported
Reported quantity · average success rates: 87.41 other · Basis not reported · Differing source assertions
“lus. On an RTX 4090, measured mean inference latencies are 24.09 and 63.09 ms, corresponding to average speedups of 8.90$\times$ and 10.67$\times$. Average success rates are 82.75% and 87.41%, respectively, within 0.02 and 0.53 percentage points of native inference. Across five real-world tasks, RealtimeWAM improves average success rates over native inference by 17.2 and 37.2 percentage points on FastWAM and OpenWAM,”
Exact source · revision 1Source owner not reported
Reported quantity · improves average success rates: 17.2 other · Basis not reported · Differing source assertions
“lus. On an RTX 4090, measured mean inference latencies are 24.09 and 63.09 ms, corresponding to average speedups of 8.90$\times$ and 10.67$\times$. Average success rates are 82.75% and 87.41%, respectively, within 0.02 and 0.53 percentage points of native inference. Across five real-world tasks, RealtimeWAM improves average success rates over native inference by 17.2 and 37.2 percentage points on FastWAM and OpenWAM,”
Exact source · revision 1Source owner not reported
Reported quantity · improves average success rates: 37.2 other · Basis not reported · Differing source assertions
“lus. On an RTX 4090, measured mean inference latencies are 24.09 and 63.09 ms, corresponding to average speedups of 8.90$\times$ and 10.67$\times$. Average success rates are 82.75% and 87.41%, respectively, within 0.02 and 0.53 percentage points of native inference. Across five real-world tasks, RealtimeWAM improves average success rates over native inference by 17.2 and 37.2 percentage points on FastWAM and OpenWAM,”
Exact source · revision 1Source owner not reported
Report timeline
Follow attributed reports and material updates.
- arXiv Robotics — research abstractsRealtimeWAM: How Fast Can I Run My World Action Model?
This paper presents RealtimeWAM, a general, training-free framework for low-latency inference in World Action Models (WAMs). It addresses the high inference latency of WAMs by coordinating parallel execution with adaptive computation, overlapping observation processing with prediction, and selectively reusing cached features. Evaluated on FastWAM and OpenWAM across RoboTwin, LIBERO, and LIBERO-Plus, RealtimeWAM achieves speedups of 8.90× and 10.67× with average success rates of 82.75% and 87.41%, respectively.
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).