Vision researcher argues JEPA follow-up papers are overclaimed

burny_tech · x · 2026-11-21

@WangYw251, a vision researcher, kicked off a thread arguing that follow-up papers building on JEPA (joint-embedding predictive architecture) are overclaimed, promising specific reasons. Notes the takeaways are personal opinions, written with the help of Opus 5.5 Max. The quoted teaser only previews the thread's critique.

Original post →

More from Research

Research channel →