Preprint
Aug 2026
Algorithm-Architecture Co-Design for Efficient VLA Inference via Speculative Inference and Verification
Comprehensive evaluations on OpenVLA and RDT across LIBERO and ManiSkill benchmarks show that SpecVLA reduces end-to-end latency significantly while preserving task success rate, and achieves real-time robotic manipulation with both high efficiency and reliability.
Chunyu Qi, Zhuoran Song, Jian Weng et al.
· 0 citations