这篇论文教会你一种骚操作：不重新训练，就能让现成模型在推理时多思考几轮，MMLU-Pro和GPQA分数都涨了，值得看看。
研究人员在论文《Training-Free Looped Transformers via Numerical ODE Integration》中提出一种无需重新训练即可提升冻结大模型性能的方法。该方法将每一层视为解常微分方程的一步，用多个小阻尼步骤替换原始大步骤，使模型获得更多推理时间。在MMLU-Pro上取得+2.64分提升，在GPQA上取得+2.01分提升，并在87%的测试组合中保持正向效果。
Researchers just made frozen AI models smarter wit…
Researchers just made frozen AI models smarter without retraining them.
Large language models run each input through their layers exactly once.
Researchers asked a simple question.
Can you squeeze more reasoning out of a finished model without retraining it?
A new paper called "Training-Free Looped Transformers via Numerical ODE Integration" says yes.
The trick is treating each layer as one step in solving a math equation.
Looping a layer naively breaks things, since later layers expect a specific input.
So instead they replace one big step with several smaller damped ones.
This gives frozen models extra thinking time at inference.
What makes this practical:
> No fine-tuning required > Works on existing checkpoints > Strongest on hard knowledge tests
Gains reached +2.64 points on MMLU-Pro and +2.01 on GPQA.
It held positive across 87% of tested combinations.
If old weights hide this much capacity, what else are we leaving unused?
- Fireworks AI06-16 22:11原文