"Recurrent depth" is just weight tying, not true arbitrary-depth recurrence
snwy_me · x · 2026-09-03
@llllvvuu challenges the hype around "recurrent depth": the technique appears to be essentially weight tying — reusing the same weights across layers — rather than genuine arbitrary-depth recurrence, making it an odd thing to make a big deal out of.
Related event: Looped Transformer Debate: Just Deeper Networks or Real Recurrence?(8 posts)→
More from Research
- TRACE Open-Sourced: Migrating G1 Controller to Full-Size Humanoid H2 in 8 Hours on One GPU — zhengyiluo · 2026-10-18
- Humanoid Robot Funding Tops $3B as Brian Potter Explains the VLA Models Driving Robots — scottleibrand · 2026-10-18
- Terence Tao on 'War Footing' as OpenAI Claims Navier-Stokes Solve Shakes Mathematics — AlexTensor · 2026-10-18
- Univ. of Tokyo paper: why your recorded voice feels eerie — a vocal uncanny valley — ssh4net · 2026-10-18
- MIT's SANDO Drone Planner Avoids Every Moving Obstacle Across 12 Real Flights — Olivier__OG · 2026-10-18
- No-backprop pretraining speedup of 2.3x claimed, inspired by mech interp essay — CatAstro_Piyush · 2026-10-18