Saved in:
| Main Author: | |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2507.04300 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911041566277632 |
|---|---|
| author | Qi, Feng |
| author_facet | Qi, Feng |
| contents | We propose Quick Feedforward (QF) Learning, a novel knowledge consolidation framework for transformer-based models that enables efficient transfer of instruction derived knowledge into model weights through feedforward activations without any gradient back propagation. Unlike traditional finetuning, QF updates are computed in closed form, require minimal parameter modification, and preserve prior knowledge. Importantly, QF allows models to train and infer within the same runtime environment, making the process more resource efficient and closely aligned with how the human brain operates. Code and models are open sourced on GitHub. I hope QF Learning inspires a more efficient and brain-like paradigm for AI systems. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_04300 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | QF: Quick Feedforward AI Model Training without Gradient Back Propagation Qi, Feng Machine Learning Artificial Intelligence Neurons and Cognition We propose Quick Feedforward (QF) Learning, a novel knowledge consolidation framework for transformer-based models that enables efficient transfer of instruction derived knowledge into model weights through feedforward activations without any gradient back propagation. Unlike traditional finetuning, QF updates are computed in closed form, require minimal parameter modification, and preserve prior knowledge. Importantly, QF allows models to train and infer within the same runtime environment, making the process more resource efficient and closely aligned with how the human brain operates. Code and models are open sourced on GitHub. I hope QF Learning inspires a more efficient and brain-like paradigm for AI systems. |
| title | QF: Quick Feedforward AI Model Training without Gradient Back Propagation |
| topic | Machine Learning Artificial Intelligence Neurons and Cognition |
| url | https://arxiv.org/abs/2507.04300 |