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.
More from Research
- Smaller experiments win: the Kaggle lesson for doing more AI research with less compute — strickvl · 2026-11-21
- Ramez Naam extrapolation: AI a decade away from completing 98% of hour-long human tasks — GaryMarcus · 2026-11-21
- Colgate paper: LLM roleplay hits 90% of human test-retest reliability in purchase-intent research — 2C_ornot2C · 2026-11-21
- Riemann Hypothesis proof gets full formal verification, experts call it 'very human math' — Kyrannio · 2026-11-21
- Claims surface: Navier-Stokes and Riemann proofs via LEAN, by OpenAI and Claude — BasketVolleyball11 · 2026-11-21
- Hassabis predicted 2 years for AI to crack a Millennium Prize problem; 6 months later, both Riemann and Navier–Stokes have proposed solutions — Hesamation · 2026-11-21