Autoregressive Policies Achieve Real-Time Execution via Constrained Decoding
What happened
A paper by Sangkyu Lee and other authors proposes that autoregressive policies can achieve real-time execution by adjusting the tokenization time horizon and applying constrained decoding, thereby guaranteeing strict latency bounds and supporting multi-trajectory decoding. The paper claims that in simulation and real environments, this policy significantly improves task completion speed compared with synchronous inference and consistently outperforms flow-matching policies of the same scale. The authors also claim that autoregressive policies have inherent advantages of faster convergence and better instruction-following generalization. This work was published at CoRL 2026 as a main conference paper.
AI 根据报道生成 · 2 days ago更新
Reporting timeline
Follow the reporting to explore different perspectives.
- arXiv cs.ROAutoregressive policies achieve real-time execution via tokenization horizon adjustment and constrained decoding
The paper proposes that autoregressive policies can achieve real-time execution by adjusting the tokenization horizon and applying constrained decoding, thereby guaranteeing strict latency bounds and enabling multi-trajectory decoding. In simulated and real-world environments, the autoregressive policy significantly improves task completion speed over synchronous inference and consistently outperforms equivalent-level flow-matching policies. The authors note that autoregressive policies also have inherent advantages of faster convergence and better generalization in instruction following. The work was published at CoRL 2026.
Activity for this event
- Current
- 3
- Peak
- 10Nov 9 14:00
- Past 24 hours
- -50%
The trend compares participants observed throughout the same period, so its range may be smaller than the current interest count. Move or tap to inspect each hour; use the arrow keys on a keyboard.