analiza aiqbench
MorphAct addresses a critical bottleneck in embodied AI by introducing a framework that dynamically adjusts robot policy parameters based on interaction contexts, effectively resolving conflicts between competing task updates. This approach enables Vision-Language-Action models to achieve significant performance gains across diverse benchmarks without relying on operation labels or expert adapters. The work represents a meaningful advancement in scaling general intelligence for physical robots through adaptive parameterization rather than static shared weights.
MorphAct: Robot Policies Morphing with the Worlds They Act In
arXiv:2610.20019v1 Announce Type: cross Abstract: Progress toward general intelligence in the physical world requires scaling robot learning across diverse environments and interactions. However, existing robot policies use shared parameters that remain fixed across interaction contexts. When different operations favor competing parameter adjustments, fitting their mixture can leave individual operations insufficiently adapted. Our atomic-task diagnostics reveal competing update directions in both vision-language and action parameters, with source-improving updates increasing loss on other tasks. This motivates MorphAct, a contextual parameterization framework that dynamically adjusts robot policy parameters as interaction contexts change. Two coupled generators produce context-dependent low-rank updates for the vision-language and action modules. Their coupling follows the policy's computational dependency: vision-language updates shape the representations that condition action-side parameter generation. Both generators are trained jointly through the native action objective, without operation labels or expert-adapter targets. MorphAct improves performance across three VLA backbones on LIBERO and Meta-World, with gains of up to 16.30%. In real-world evaluation, it achieves gains of up to 14% over $\pi_{0.5}$. Ablations support the benefits of contextual parameter generation and representation coupling.
Abstract:Progress toward general intelligence in the physical world requires scaling robot learning across diverse environments and interactions. However, existing robot policies use shared parameters that remain fixed across interaction contexts. When different operations favor competing parameter adjustments, fitting their mixture can leave individual operations insufficiently adapted. Our atomic-task diagnostics reveal competing update directions in both vision-language and action parameters, with source-improving updates increasing loss on other tasks. This motivates MorphAct, a contextual parameterization framework that dynamically adjusts robot policy parameters as interaction contexts change. Two coupled generators produce context-dependent low-rank updates for the vision-language and action modules. Their coupling follows the policy's computational dependency: vision-language updates shape the representations that condition action-side parameter generation. Both generators are trained jointly through the native action objective, without operation labels or expert-adapter targets. MorphAct improves performance across three VLA backbones on LIBERO and Meta-World, with gains of up to 16.30%. In real-world evaluation, it achieves gains of up to 14% over $\pi_{0.5}$. Ablations support the benefits of contextual parameter generation and representation coupling.
25 pages. Project page: this https URL
Robotics (cs.RO); Artificial Intelligence (cs.AI)
arXiv:2610.20019 [cs.RO]
(or arXiv:2610.20019v1 [cs.RO] for this version)
https://doi.org/10.48550/arXiv.2610.20019 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 273 cuvinte
Subiecte conexe
NVIDIA Releases Cosmos 3: A Two-Tower Mixture-of-Transformers Foundation Model Unifying Physical Reasoning, World Generation, and Action Generation
MarkTechPost · 3 iun. 2026
Static In, Dynamic Out: Counterfactual Action Augmentation for Moving Object Manipulation
arXiv · 31 iul. 2026
The Machines that Make the Machines
NVIDIA · 7 oct. 2026
Coming of a New Sun
LessWrong · 3 aug. 2026