FastOPD is a framework that distills large Vision‑Language‑Action (VLA) models into lightweight versions by using on‑policy distillation with a flow map and a self‑consistency objective. The method trains a compact student to mimic the teacher’s dynamics, achieving performance close to the teacher while drastically reducing inference steps. Experiments on LIBERO, RoboTwin 2.0, and real‑robot deployments show significant latency reductions and higher success rates compared to existing few‑step distillation baselines.
arXiv:2607. 04171v3 Announce Type: replace-cross Abstract: Tiny Vision-Language-Action models are appealing for real-time robotic control, but reducing model scale often weakens two capabilities essential for manipulation: task-conditioned spatial grounding and coherent action generation.
arXiv:2607.04171v4 Announce Type: replace-cross Abstract: How can richer training supervision improve robot control while keeping the deployed policy compact? We present XS-VLA, a staged training fra...
arXiv:2609.08638v1 Announce Type: cross Abstract: An action chunk can span several stages of a manipulation task, yet a label for its first step describes only the current stage. We introduce Chunk-A...
arXiv:2608.22364v1 Announce Type: new Abstract: World action models (WAMs) couple visual future prediction with robot action generation, but accelerated students can lose task capabilities during dis...
arXiv:2606. 25800v1 Announce Type: new Abstract: Effective online adaptation of vision-language-action (VLA) models remains challenging, as sparse rewards provide weak supervision for high-dimensional autoregressive action policies.
arXiv:2607. 04171v1 Announce Type: cross Abstract: Large Vision-Language Models (LVLMs) have shown strong multimodal understanding and spatial grounding, but their computational cost limits real-time robotic control.
DriftOPD is a teacher‑free, rollout‑free framework that performs sequence‑level on‑policy distillation of continuous Vision‑Language‑Action (VLA) action experts. It decomposes the sequence‑level reverse‑KL divergence into a chunk‑level reverse‑KL term and a future‑potential term, optimizing them with a one‑step drifting objective and a Q‑function critic learned from offline demonstrations. Experiments on multiple VLA architectures in simulation and real‑world manipulation show that DriftOPD outperforms existing one‑step distillation baselines while matching the task success of multi‑step teacher policies.
arXiv:2606. 13578v1 Announce Type: cross Abstract: Scientific laboratories increasingly rely on AI systems to reason about experiments, but the physical act of doing science remains largely outside their reach.
arXiv:2610.03476v1 Announce Type: cross Abstract: Long-horizon mobile manipulation presents significant challenges due to compounding execution errors and capacity interference between locomotion and...
The paper introduces VLAct, a Vision‑Language‑Action model that focuses on representation‑centric continued pre‑training rather than merely scaling robot data. VLAct is trained on diverse, multi‑embodiment robot data and preserves a broad VLM prior while encouraging shared action semantics across embodiments. Experiments across simulation, real‑world, and unseen‑embodiment settings show that VLAct consistently outperforms existing industrial VLA systems, achieving high success rates with only a modest compute budget and open‑source data.
Vision-language-action (VLA) models commonly adopt an LLM-centric $V \to L \to A$ pathway, where visual observations are projected into the representation space of a large language model before being decoded into robot actions. Although effective, this design incurs substantial computation and memory overhead at every policy invocation.
EXPO-FT is a system that enables stable, sample‑efficient reinforcement learning fine‑tuning of pretrained Vision‑Language‑Action (VLA) policies. It achieves perfect success on a range of manipulation tasks—such as routing string lights, striking a pool ball, and inserting a flower into a wine bottle—using only about 19.1 minutes of online robot data. The approach outperforms both RL-from-scratch and existing VLA fine‑tuning methods, and the authors provide an open‑source codebase to support wider adoption.