Recirculation: Off-the-shelf models self-modify for instant inference boost
TheGradient · x · 2026-08-20
This paper introduces "Recirculation," an inference-time architectural enhancement for off-the-shelf foundation models that significantly reduces perplexity and boosts accuracy without retraining.
Key Details:
- Mechanism: Introduces a specific form of recurrence allowing the model to act as a dynamical system to track belief states, overcoming depth limitations in feedforward transformers.
- Efficiency: Incurs essentially zero latency cost during generation (requires serial processing only in the prefill phase).
- Performance: An adaptive variant achieves a 23% reduction in perplexity and a 21% accuracy increase on GSM8k for the Gemma3 family.
The approach suggests a route for architectural evolution guided by a trained network's properties.
Related event: DeepMind's Recirculation boosts LLM reasoning without retraining(10 posts)→
More from Models
- Prediction: frontier AI revenue growth could slow even as AI usage keeps rising — yi111 · 2026-10-16
- Nolla Health Post-Trains Nemotron 3.5 VL: Visual Diagnosis Jumps from 35% to 66.8% — LoganGrasby · 2026-10-16
- Dev argues coding models now beat nearly all engineers in every branch of software — zack_overflow · 2026-10-16
- Prediction: Chinese frontier models could match GPT-6 by March 2027 — teortaxesTex · 2026-10-16
- Liquid AI's d1-ultra, #1 on Artificial Analysis Decision Index, lands on Vercel — JosephJacks_ · 2026-10-16
- Weekly AI roundup: Claude Haiku 5.5 cuts prices ~90%, Gemini 4 Argon output jumps to 1M tokens — DeepLearningAI · 2026-10-16