Salvato in:
| Autore principale: | |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2603.16044 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866917348855775232 |
|---|---|
| author | Shin, Dongik |
| author_facet | Shin, Dongik |
| contents | Generalization remains a core challenge in embodied AI, as robots must adapt to diverse environments. While OpenVLA represents the State-of-the-Art (SOTA) in Vision-Language-Action models by leveraging large-scale pre-training, its zero-shot performance can be limited when encountering completely new environments. This paper proposes a parameter-efficient fine-tuning strategy to enhance the linguistic generalization of OpenVLA by synthesizing a general instruction set for the Bridge Dataset V2. The paper leverages a Large Language Model (LLM) to generate a rich variety of semantically equivalent but structurally diverse commands for existing trajectories. In this experiment, Low-Rank Adaptation (LoRA) is implemented to fine-tune OpenVLA on augmented pairs, allowing the model to bridge the gap between complex natural language intent and robotic actions. Results demonstrate that the LoRA-enhanced model's robustness, suggesting that enriching the linguistic space of specialized datasets is crucial for embodied agents. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_16044 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Enhancing Linguistic Generalization of VLA: Fine-Tuning OpenVLA via Synthetic Instruction Augmentation Shin, Dongik Artificial Intelligence Generalization remains a core challenge in embodied AI, as robots must adapt to diverse environments. While OpenVLA represents the State-of-the-Art (SOTA) in Vision-Language-Action models by leveraging large-scale pre-training, its zero-shot performance can be limited when encountering completely new environments. This paper proposes a parameter-efficient fine-tuning strategy to enhance the linguistic generalization of OpenVLA by synthesizing a general instruction set for the Bridge Dataset V2. The paper leverages a Large Language Model (LLM) to generate a rich variety of semantically equivalent but structurally diverse commands for existing trajectories. In this experiment, Low-Rank Adaptation (LoRA) is implemented to fine-tune OpenVLA on augmented pairs, allowing the model to bridge the gap between complex natural language intent and robotic actions. Results demonstrate that the LoRA-enhanced model's robustness, suggesting that enriching the linguistic space of specialized datasets is crucial for embodied agents. |
| title | Enhancing Linguistic Generalization of VLA: Fine-Tuning OpenVLA via Synthetic Instruction Augmentation |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2603.16044 |