Vision-Language Models Are Joint Denoisers in Robotic Action Generation
Overview
This research introduces JADE, a framework that enables vision-language models (VLMs) and action experts to jointly refine robotic actions through structured action latents. By allowing the VLM to read noisy actions alongside visual observations and language instructions at every denoising step, JADE couples perception with control directly. The method achieves an average success rate of 12.67% on RoboDojo, outperforming other evaluated methods based on pi_0.5, and improves performance on RoboTwin 2.0 and four real-world bimanual tasks by 20.8 percentage points compared to the baseline.
Generated from attributed reports · Updated 2 hours ago
Event evidence and corrections
0 attributed source owners. Ownership does not establish independent confirmation. Quantities are reported separately and are never added together.
Reported quantity · Reported success rate: 12.67 percent · reported trials
“ves an average success rate of 12.67%, the highest among the evaluated $\pi_{0.5}$-based methods, and is competitive with recent VLA and WAM foundation models pretrained at scale. It also improves performance on RoboTwin 2.0 and raises the average success rate across four real-world bimanual tasks by 20.8 percentage points compared with $\pi_{0.5}$.”
Exact source · revision 1Source owner not reported
Report timeline
Follow attributed reports and material updates.
- arXiv Robotics — research abstractsSignalVision-Language Models Are Joint Denoisers in Robotic Action Generation
This research introduces JADE, a framework that enables vision-language models (VLMs) and action experts to jointly refine robotic actions through structured action latents. By allowing the VLM to read noisy actions alongside visual observations and language instructions at every denoising step, JADE couples perception with control directly. The method achieves an average success rate of 12.67% on RoboDojo, outperforming other evaluated methods based on pi_0.5, and improves performance on RoboTwin 2.0 and four real-world bimanual tasks by 20.8 percentage points compared to the baseline.
Event coverage history
There is not enough continuous observation data to show a trend.
Timezone · UTC
Article dates follow your selected timezone. Briefing editions use Hong Kong time (UTC+8).