DeepMind's Recirculation Enables Recursive Self-Improvement Without Retraining
omarsar0 · x · 2026-08-23
Google DeepMind proposes 'Recirculation,' a training-free approach to evolve model architectures. By feeding activations back during prefill, the model acts as a dynamical system at inference time, tracking belief states without retraining. This addresses the layer-depth limitation of feedforward transformers in long generations. Generation cost remains flat as serial work is confined to the prefill phase.
Related event: DeepMind's Recirculation Evolves Transformers Without Retraining(3 posts)→
More from Research
- Intelligence is proportional to data: reorder tasks by data volume and the jagged frontier becomes a spiral — sebkrier · 2026-10-16
- Doc2Harness: New benchmark finds best coding agent passes only 53% across 329 cases — _akhaliq · 2026-10-16
- Stanford's Fei-Fei Li team open-sources OpenWAM, a unified world-action model framework for robots — jiqizhixin · 2026-10-16
- NVIDIA's TacitVLA: robots reason without reading their own thoughts, 3.4x lower latency — arankomatsuzaki · 2026-10-16
- Cohere Labs world model course session 4: DreamerV1-V4 architectures in one go — Cohere_Labs · 2026-10-16
- GPT-6.1 Sol audit finds 6% of arXiv papers had false main theorems, down to 1.5% recently — nitarshan · 2026-10-16