MIT Poggio team publishes PNAS paper on how biological synapses self-assemble gradient learning
neurovium · x · 2026-10-10
Tomaso Poggio's group at MIT's McGovern Institute (with Qianli Liao, Ziyin Liu, Yule Gan, et al.) published a PNAS paper titled "How biological synapses self-assemble gradient learning," exploring how synaptic self-organization can give rise to gradient-descent-like learning without explicit backpropagation — relevant both to neuroscience and to designing new learning algorithms.
More from Research
- EMNLP paper: diffusion LMs internally encode latent denoising timestep representations — gsarti_ · 2026-10-23
- KU Leuven and VIB open two Group Leader professorships in AI for Biology, start 2027 — jpillowtime · 2026-10-23
- Subspace Tuning curbs LLM catastrophic forgetting by freezing principal singular directions — scottniekum · 2026-10-23
- Perceptic launches PercepticOS, an AI workspace for 'scientific superintelligence' — nathanbenaich · 2026-10-23
- EPFL's Bosselut to talk long context as test-time learning at ELLIS seminar — andre_t_martins · 2026-10-23
- DRATS: Adaptive Task Sampling Boosts Worst-Task Performance in Multi-Task RL — Cohere · 2026-10-23