All-For-One: Distilling Visual Foundation Models to a Fast, Memory-Efficient Visuomotor Policy
Overview
This paper introduces All-For-One (AFO), a two-stage distillation framework that leverages Visual Foundation Models (VFMs) as privileged information during training to create a lightweight, RGB-only student policy. By decoupling semantic representation learning from inference-time execution, AFO achieves over 30x fewer parameters than VFM-based encoders and 50x lower latency than its teacher in simulation benchmarks. Evaluated on Adroit and MetaWorld tasks in simulation as well as three real-world manipulation tasks, the method outperforms prior foundation-model-based approaches while addressing issues of high computational cost, temporal inconsistency, and distribution shift between static internet images and egocentric robot observations.
Generated from attributed reports · Updated 2 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
“knowledge is distilled in-distribution into a lightweight RGB-only student policy. Evaluated on two Adroit tasks and five MetaWorld tasks in simulation, as well as three real-world manipulation tasks, AFO outperforms prior foundation-model-based approaches while using over 30x fewer parameters than VFM-based encoders and 50x lower latency than its own teacher in simulation benchmarks, providing an efficient pathway f”
Exact source · revision 1Source owner not reported
Reported quantity · parameters: 30 other · Basis not reported
“knowledge is distilled in-distribution into a lightweight RGB-only student policy. Evaluated on two Adroit tasks and five MetaWorld tasks in simulation, as well as three real-world manipulation tasks, AFO outperforms prior foundation-model-based approaches while using over 30x fewer parameters than VFM-based encoders and 50x lower latency than its own teacher in simulation benchmarks, providing an efficient pathway f”
Exact source · revision 1Source owner not reported
Reported quantity · latency: 50 other · Basis not reported
“knowledge is distilled in-distribution into a lightweight RGB-only student policy. Evaluated on two Adroit tasks and five MetaWorld tasks in simulation, as well as three real-world manipulation tasks, AFO outperforms prior foundation-model-based approaches while using over 30x fewer parameters than VFM-based encoders and 50x lower latency than its own teacher in simulation benchmarks, providing an efficient pathway f”
Exact source · revision 1Source owner not reported
Report timeline
Follow attributed reports and material updates.
- arXiv Robotics — research abstractsSignalAll-For-One: Distilling Visual Foundation Models to a Fast, Memory-Efficient Visuomotor Policy
This paper introduces All-For-One (AFO), a two-stage distillation framework that leverages Visual Foundation Models (VFMs) as privileged information during training to create a lightweight, RGB-only student policy. By decoupling semantic representation learning from inference-time execution, AFO achieves over 30x fewer parameters than VFM-based encoders and 50x lower latency than its teacher in simulation benchmarks. Evaluated on Adroit and MetaWorld tasks in simulation as well as three real-world manipulation tasks, the method outperforms prior foundation-model-based approaches while addressing issues of high computational cost, temporal inconsistency, and distribution shift between static internet images and egocentric robot observations.
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).