While generalist vision-language-action (VLA) models have enabled diverse open-world manipulation, real-world robotic assistance requires two critical capabilities they currently lack: personalization and reliable execution. First, executing an instruction like"make me a sandwich"requires grounding subtask decompositio...
Zixuan Wang, Yu-Qi Liu, Yu-Xin Chen et al.· 0 citations
This work introduces StarVLA-$\alpha, a simple yet strong baseline designed to study VLA design choices under controlled conditions that deliberately minimizes architectural and pipeline complexity to reduce experimental confounders and enable systematic analysis.
Jinhui Ye, Ning Gao, Sen-Qiao Yang et al.· arXiv.org· 49 citations· ⚡11
This work proposes VLAct, a VLA-oriented VLM backbone trained on broad, heterogeneous, multi-embodiment robot data before task-specific fine-tuning, showing that representation-centric continued pre-training can deliver highly competitive performance under a modest compute budget and is an important independent axis of...
Unified-MAS is proposed that decouples granular node implementation from topological orchestration via offline node synthesis via offline node synthesis and is robustness across different designer LLMs and its effectiveness on conventional tasks such as mathematical reasoning.
Hehai Lin, Yuliang Yan, Zixuan Wang et al.· arXiv.org· 2 citations
MemVLN is proposed, a novel VLN framework that achieves state-of-the-art performance with real-time inference efficiency (14 FPS) and introduces Procedural Memory for fast action with a compact vocabulary of atomic mid-level actions to bypass auto-regressive decoding latency.
