# DaDu-Corki: Algorithm-Architecture Co-Design for Embodied AI-powered Robotic Manipulation

arXiv: https://arxiv.org/abs/2407.04292 · HTML: https://mlsanity.com/paper/2407.04292/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Jul 2024.

## Built on by (most cited first, 13 of 13)

- [Qwen-RobotManip Technical Report: Alignment Unlocks Scale for Robotic Manipulation Foundation Models](https://mlsanity.com/paper/2606.17846/) (2026)
- [How Fast Can I Run My VLA? Demystifying VLA Inference Performance with VLA-Perf](https://mlsanity.com/paper/2602.18397/) (2026)
- [DaDu-E: Rethinking the Role of Large Language Model in Robotic Computing Pipeline](https://mlsanity.com/paper/2412.01663/) (2024)
- [CF-VLA: Efficient Coarse-to-Fine Action Generation for Vision-Language-Action Policies](https://mlsanity.com/paper/2604.24622/) (2026)
- [LightPlanner: Unleashing the Reasoning Capabilities of Lightweight Large Language Models in Task Planning](https://mlsanity.com/paper/2503.08508/) (2025)
- [BaseRT: Best-in-Class LLM Inference on Apple Silicon via Native Metal](https://mlsanity.com/paper/2607.00501/) (2026)
- [A Motion-Aware Vector Quantization Framework with Centroid Reuse for Efficient VLA Inference](https://mlsanity.com/paper/2607.24148/) (2026)
- [SkiP: When to Skip and When to Refine for Efficient Robot Manipulation](https://mlsanity.com/paper/2605.15536/) (2026)
- [BaseRT: Advancing Best-in-Class LLM Inference with Apple M5 Neural Accelerators](https://mlsanity.com/paper/2607.19438/) (2026)
- [Deltoris: Enabling Real-time VLA Inference in Embodied AI via Bit-level Sparsity and Speculative Inference](https://mlsanity.com/paper/2608.04428/) (2026)
- [Algorithm-Architecture Co-Design for Efficient VLA Inference via Speculative Inference and Verification](https://mlsanity.com/paper/2608.15636/) (2026)
- [APEX-RBD: Mixed-Precision Exploration Framework for Hardware-Efficient Robot Dynamics Accelerator Design](https://mlsanity.com/paper/2609.05161/) (2026)
- [VLA-ULAP: Interleaving Cloud VLA Calls with Ultra-Lightweight Local Action Prediction at the Edge](https://mlsanity.com/paper/2609.18663/) (2026)

## Abstract (arXiv)

Embodied AI robots have the potential to fundamentally improve the way human beings live and manufacture. Continued progress in the burgeoning field of using large language models to control robots depends critically on an efficient computing substrate, and this trend is strongly evident in manipulation tasks. In particular, today's computing systems for embodied AI robots for manipulation tasks are designed purely based on the interest of algorithm developers, where robot actions are divided into a discrete frame basis. Such an execution pipeline creates high latency and energy consumption. This paper proposes textscCorkixspace, an algorithm-architecture co-design framework for real-time embodied AI-powered robotic manipulation applications. We aim to decouple LLM inference, robotic control, and data communication in the embodied AI robots' compute pipeline. Instead of predicting action for one single frame, textscCorkixspace predicts the trajectory for the near future to reduce the frequency of LLM inference. The algorithm is coupled with a hardware that accelerates transforming trajectory into actual torque signals used to control robots and an execution pipeline that parallels data communication with computation. textscCorkixspace largely reduces LLM inference frequency by up to 5.1×, resulting in up to 5.9× speed up. The success rate improvement can be up to 13.9%.