arXiv:2608.29208v1 Announce Type: cross
Abstract: Vision-Language-Action (VLA) models, built upon Vision-Language Models (VLMs), have significantly enhanced robotic capabilities by leveraging interne...
By Sunghwan Han, Youngtae Han, Youngmin Yi
arXiv:2605. 21854v2 Announce Type: replace-cross Abstract: Vision-Language-Action (VLA) models have rapidly converged on a small set of architectural patterns: discrete-token autoregression (e.
By Zhi Liu
MambaAct introduces a compact Mamba-based action expert to replace the transformer-based expert in flow‑matching vision‑language‑action models, preserving the pretrained visual‑language prefix encoder while reducing the action expert size by tenfold. The new design employs a lightweight Context Compressor to embed vision‑language conditioning into each Mamba block, eliminating repeated token‑level cross‑attention. Experiments show a 64.8 % reduction in denoising latency on LIBERO and 58.8 % in real‑world deployment, with a modest 1.08 % increase in mean success rate across multiple fine‑tuning seeds.
By Khuyen Pham, Tran Nguyen Le, Edoardo Fazzari, Cesare Stefanini
The paper introduces a framework for Flow‑Matching Vision‑Language‑Action (VLA) models that allows independent adjustment of backbone depth, action expert depth, and denoising steps. Lightweight Exit Transformers are added at intermediate layers to enable early exits, and a KV Cache synthesis mechanism manages skipped layers so the action expert can exit deeper than the backbone. Experiments on SmolVLA and π0.5 across LIBERO and Meta‑World show that joint tuning of these compute axes reduces latency by 79.2 % and FLOPs by 31.8 %, while improving mean success rate by 5.6 %.
By Riccardo Andrea Izzo, Rimvydas Rubavicius, Gianluca Bardaro, Subramanian Ramamoorthy, Matteo Matteucci, Alessandro Suglia
CF‑VLA introduces a two‑stage coarse‑to‑fine approach for vision‑language‑action policies, replacing multi‑step sampling with a coarse initialization that constructs an action‑aware starting point and a single‑step refinement that corrects residual errors. The coarse stage learns a conditional posterior over endpoint velocity to transform Gaussian noise into a structured initialization, while the fine stage performs a fixed‑time refinement. Experiments on CALVIN and LIBERO demonstrate that CF‑VLA achieves a strong efficiency‑performance trade‑off, reducing action sampling latency by 75.4 % and achieving an 83.0 % real‑robot success rate, outperforming existing NFE=2 methods and matching or surpassing NFE=10 baselines.
By Fan Du, Feng Yan, Jianxiong Wu, Xinrun Xu, Weiye Zhang, Weinong Wang, Yu Guo, Bin Qian, Zhihai He, Fei Wang, Heng Yang
TOPS (Task‑Oriented Priors and Schedules) adapts flow‑based policies for language‑conditioned multi‑task robot manipulation by customizing the flow source prior and interpolation schedule per task without changing the network architecture. It constructs multimodal task sources from reverse‑mapped expert action sequences, allowing language instructions to select the generation start point, and adjusts the denoising schedule based on source‑target covariance mismatch to reduce velocity‑prediction risk. Experiments on LIBERO, LIBERO‑Plus, CALVIN, and real‑world tasks show significant performance gains, including a jump from 53.44 % to 69.67 % success on LIBERO‑10 with a single integration step and a five‑fold reduction in inference time.
By Tuo An, Chuhao Zhou, Jiahua Dong, Jingliang Li, Jiaqi Bai, Jindou Jia, Jianfei Yang