← Search

Kunyun Wang

2 accepted papers

2026

Learning High-Frequency Continuous Action Chunks in Latent Space

ICML 2026poster

Modern robotic policies increasingly rely on action chunking to execute complex tasks in the physical world. While action chunking improves temporal consistency at moderate action frequencies, it becomes insufficient when the action frequency is further increased (e.g., to 60~Hz). At such high frequ…

Cited by 0SourceScholar
2025

Communication-Efficient Diffusion Denoising Parallelization via Reuse-then-Predict Mechanism

NeurIPS 2025poster

Diffusion models have emerged as a powerful class of generative models across various modalities, including image, video, and audio synthesis. However, their deployment is often limited by significant inference latency, primarily due to the inherently sequential nature of the denoising process. Whil…

Cited by 0SourceScholar