# Zeyang Li

Published articles for Zeyang Li.

This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles.

## MIT researchers develop a generative AI method for enforcing hard constraints in safety-critical applications

DevFeed: [MIT researchers develop a generative AI method for enforcing hard constraints in safety-critical applications](<https://devfeed.tech/articles/new-method-enables-ai-for-safety-critical-situations-37975.md>)

Original publisher: [Read original article](<https://news.mit.edu/2026/new-method-enables-ai-safety-critical-situations-0914>)

Author: Adam Zewe | MIT News

Published: 2026-09-14T04:00:00Z

Content type: news

Language: en

Sources: [MIT AI News](<https://devfeed.tech/sources/mit-ai-news.md>)

Topics: [Generative AI](<https://devfeed.tech/topics/generative-ai.md>), [AI Models](<https://devfeed.tech/topics/ai-models.md>), [Algorithm](<https://devfeed.tech/topics/algorithm.md>), [Requirements](<https://devfeed.tech/topics/requirements.md>), [Computer vision](<https://devfeed.tech/topics/computer-vision.md>), [Robotics](<https://devfeed.tech/topics/robotics.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [ai-models](<https://devfeed.tech/tags/ai-models.md>), [algorithm](<https://devfeed.tech/tags/algorithm.md>), [algorithms](<https://devfeed.tech/tags/algorithms.md>), [artificial-intelligence](<https://devfeed.tech/tags/artificial-intelligence.md>), [computer-science-and-technology](<https://devfeed.tech/tags/computer-science-and-technology.md>), [computer-vision](<https://devfeed.tech/tags/computer-vision.md>), [diffusion-models](<https://devfeed.tech/tags/diffusion-models.md>), [electrical-engineering-and-computer-science-eecs](<https://devfeed.tech/tags/electrical-engineering-and-computer-science-eecs.md>), [flow-matching](<https://devfeed.tech/tags/flow-matching.md>), [generative-ai](<https://devfeed.tech/tags/generative-ai.md>), [hard-constrained-sampling](<https://devfeed.tech/tags/hard-constrained-sampling.md>), [hardflow](<https://devfeed.tech/tags/hardflow.md>), [idss](<https://devfeed.tech/tags/idss.md>), [kaveh-alim](<https://devfeed.tech/tags/kaveh-alim.md>), [laboratory-for-information-and-decision-systems-lids](<https://devfeed.tech/tags/laboratory-for-information-and-decision-systems-lids.md>), [machine-learning](<https://devfeed.tech/tags/machine-learning.md>), [mechanical-engineering](<https://devfeed.tech/tags/mechanical-engineering.md>), [mit-schwarzman-college-of-computing](<https://devfeed.tech/tags/mit-schwarzman-college-of-computing.md>), [navid-azizan](<https://devfeed.tech/tags/navid-azizan.md>), [optimal-control](<https://devfeed.tech/tags/optimal-control.md>), [paper](<https://devfeed.tech/tags/paper.md>), [requirements](<https://devfeed.tech/tags/requirements.md>), [research](<https://devfeed.tech/tags/research.md>), [robotics](<https://devfeed.tech/tags/robotics.md>), [safe-ai](<https://devfeed.tech/tags/safe-ai.md>), [school-of-engineering](<https://devfeed.tech/tags/school-of-engineering.md>), [trajectory-optimization](<https://devfeed.tech/tags/trajectory-optimization.md>), [zeyang-li](<https://devfeed.tech/tags/zeyang-li.md>)

### AI overview

MIT researchers developed a deployment-time technique that lets pretrained generative AI models explore solutions while enforcing hard constraints on final outputs. Experiments in robotics, physical-process control, and computer vision found that the method satisfied required constraints and identified better solutions than existing techniques.

### Source excerpt

The "HardFlow" algorithm could help generative AI models produce high-quality outputs that obey strict requirements when "pretty close" doesn't cut it.