Differentiate-and-Inject: Enhancing VLAs via Functional Differentiation Induced by In-Parameter Structural Reasoning
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866912887542382592 |
|---|---|
| author | Hou, Jingyi Zhou, Leyu Jing, Chenchen Yang, Jinghan Yu, Xinbo He, Wei |
| author_facet | Hou, Jingyi Zhou, Leyu Jing, Chenchen Yang, Jinghan Yu, Xinbo He, Wei |
| contents | As robots are expected to perform increasingly diverse tasks, they must understand not only low-level actions but also the higher-level structure that determines how a task should unfold. Existing vision-language-action (VLA) models struggle with this form of task-level reasoning. They either depend on prompt-based in-context decomposition, which is unstable and sensitive to linguistic variations, or end-to-end long-horizon training, which requires large-scale demonstrations and entangles task-level reasoning with low-level control. We present in-parameter structured task reasoning (iSTAR), a framework for enhancing VLA models via functional differentiation induced by in-parameter structural reasoning. Instead of treating VLAs as monolithic policies, iSTAR embeds task-level semantic structure directly into model parameters, enabling differentiated task-level inference without external planners or handcrafted prompt inputs. This injected structure takes the form of implicit dynamic scene-graph knowledge that captures object relations, subtask semantics, and task-level dependencies in parameter space. Across diverse manipulation benchmarks, iSTAR achieves more reliable task decompositions and higher success rates than both in-context and end-to-end VLA baselines, demonstrating the effectiveness of parameter-space structural reasoning for functional differentiation and improved generalization across task variations. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_07541 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Differentiate-and-Inject: Enhancing VLAs via Functional Differentiation Induced by In-Parameter Structural Reasoning Hou, Jingyi Zhou, Leyu Jing, Chenchen Yang, Jinghan Yu, Xinbo He, Wei Robotics As robots are expected to perform increasingly diverse tasks, they must understand not only low-level actions but also the higher-level structure that determines how a task should unfold. Existing vision-language-action (VLA) models struggle with this form of task-level reasoning. They either depend on prompt-based in-context decomposition, which is unstable and sensitive to linguistic variations, or end-to-end long-horizon training, which requires large-scale demonstrations and entangles task-level reasoning with low-level control. We present in-parameter structured task reasoning (iSTAR), a framework for enhancing VLA models via functional differentiation induced by in-parameter structural reasoning. Instead of treating VLAs as monolithic policies, iSTAR embeds task-level semantic structure directly into model parameters, enabling differentiated task-level inference without external planners or handcrafted prompt inputs. This injected structure takes the form of implicit dynamic scene-graph knowledge that captures object relations, subtask semantics, and task-level dependencies in parameter space. Across diverse manipulation benchmarks, iSTAR achieves more reliable task decompositions and higher success rates than both in-context and end-to-end VLA baselines, demonstrating the effectiveness of parameter-space structural reasoning for functional differentiation and improved generalization across task variations. |
| title | Differentiate-and-Inject: Enhancing VLAs via Functional Differentiation Induced by In-Parameter Structural Reasoning |
| topic | Robotics |
| url | https://arxiv.org/abs/2602.07541 |