Sakana AI research scientist Rujikorn (Tan) Charakorn recently presented Doc-to-LoRA at @MLCollective’s DLCT journal club, covering hypernetworks, cost amortization, and future directions. A very lively discussion followed. Many thanks to the organizers!
https://www.youtube.com/watch?v=jb_0XcBMJQU
We’re excited to introduce Doc-to-LoRA and Text-to-LoRA, two related research exploring how to make LLM customization faster and more accessible.
https://pub.sakana.ai/doc-to-lora/
By training a Hypernetwork to generate LoRA adapters on the fly, these methods allow models to instantly internalize new information or adapt to new tasks.
Biological systems naturally rely on two key cognitive abilities: durable long-term memory to store facts, and rapid adaptation to handle new tasks given limited sensory cues. While modern LLMs are highly capable, they still lack this flexibility. Traditionally, adding long-term memory or adapting an LLM to a specific downstream task requires an expensive and time-consuming model update, such as fine-tuning or context distillation, or relies on memory-intensive long prompts.
To bypass these limitations, our work focuses on the concept of cost amortization. We pay the meta-training cost once to train a hypernetwork capable of producing tasks or document specific LoRAs on demand. This turns what used to be a heavy engineering pipeline into a single, inexpensive forward pass. Instead of performing per-task optimization, the hypernetwork meta-learns update rules to instantly modify an LLM given a new task description or a long document.
In our experiments, Text-to-LoRA successfully specializes models to unseen tasks using just a natural language description. Building on this, Doc-to-LoRA is able to internalize factual documents. On a needle-in-a-haystack task, Doc-to-LoRA achieves near-perfect accuracy on instances five times longer than the base model's context window. It can even generalize to transfer visual information from a vision-language model into a text-only LLM, allowing it to classify images purely through internalized weights.
Importantly, both methods run with sub-second latency, enabling rapid experimentation while avoiding the overhead of traditional model updates. This approach is a step towards lowering the technical barriers of model customization, allowing end-users to specialize foundation models via simple text inputs. We have released our code and papers for the community to explore.
Doc-to-LoRA Paper: https://arxiv.org/abs/2602.15902 Code: https://github.com/SakanaAI/Doc-to-LoRA
Text-to-LoRA Paper: https://arxiv.org/abs/2506.06105 Code: https://github.com/SakanaAI/Text-to-LoRA
