kalomaze: STE works fine under backprop even for binary weights and latents
kalomaze · x · 2026-09-30
Responding to skepticism about straight-through estimators, kalomaze argues STE works unironically fine under backprop even in the binary-weights case, noting it also powers autoencoders that learn binary latent spaces at the bottleneck — pointing to LFQ and the BitNet papers as evidence.
More from Research
- Claude sets NIST circuit record: AES S-Box in 28 AND-gates, 131 total — jedisct1 · 2026-09-30
- Not every model failure is lack of capability: Terminal-Bench evals hide safety declines — abeirami · 2026-09-30
- NVIDIA's Physis-Lang puts physics reasoning in captions, tops Physics-IQ with Cosmos 3 — NVIDIAAI · 2026-09-30
- Laser on a 3D printer turns Kapton tape into laser-induced graphene with PWM control — johnowhitaker · 2026-09-30
- COLM paper: narrative choices alone give AI fiction away, even without AI-speak — MohitIyyer · 2026-09-30
- CMU Study Examines How Content Creators Responsibly Use Generative AI Tools — steph_milani · 2026-09-30