Newest papers

Scaling Parameter-Efficient Fine-Tuning for Brain Encoding

Zhuofan Josh Ying, Guanglong Sun, Nolan Ho, Kieran Liu, Rui Yang, Andrew Chen, Nikolaus Kriegeskorte, PONY MA, Hossein Adeli · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.26802 · cited by 0 works (OpenAlex) · open-access PDF

Korean

이 뇌 암호화 집합 모델은 자극에 대한 신경 반응을 예측하는 것을 목표로합니다. 가장 널리 사용되는 접근법은 얼어 붙은 사전 훈련 된 척추에서 읽을 수 있습니다. 신경 데이터를 사용하여 대형 모델을 처음부터 훈련하거나 작업 사전 훈련 후에 완전히 정렬하도록 훈련하십시오. 신경 데이터의 비용이 비싸고 제한되기 때문에 신경 응답을 예측하는 것이 어려워졌습니다. 파라미터 효율적인 미세 조정 (PEFT)은 창문을 사용하는 대신 단일 통로에서 여러 시간점을 예측하는 신경 척추의 원인 구조를 활용하여 효과적으로 매우 큰 사전 훈련 된 척추를 효과적으로 적응시킬 수 있습니다. 이것은 104B 파라미터까지

Machine translation (Meta M2M100); the English original follows.

Abstract

Brain encoding models aim to predict neural responses to stimuli. The most widely used approach fits readouts from frozen pretrained backbones. Using neural data to train large models from scratch or fully fine-tune them after task-pretraining has proven difficult because neural data is costly and limited. We show that parameter-efficient fine-tuning (PEFT) enables us to effectively adapt very large pretrained backbones for brain encoding with a small number of trainable parameters. To make it computationally practical, we exploit the backbone's causal structure to predict multiple timepoints in a single pass instead of using sliding windows, significantly reducing feature-extraction cost. This enables efficient fine-tuning of multimodal backbones with up to 104B parameters, the largest model adapted for brain encoding to our knowledge. Trained with a low-rank adapter (LoRA) and a lightweight readout, our approach consistently improves brain encoding performance across nine diverse multimodal backbones. On the same Qwen3-Omni backbone as the prior state-of-the-art (SoTA), our method BrainLoRA achieves the best published performance on the Algonauts 2025 Challenge. We also show the adapted multimodal backbones remain interpretable: modality attribution recovers the canonical sensory topography that prior work often obtains by construction from separate unimodal encoders, and neural adaptation increases the contribution of audio inputs and cross-modal mixing within the backbone. To scale out the number of adapted models, we develop a multi-LoRA kernel that accelerates joint training of multiple LoRAs on a shared backbone. This enables an ensemble of 200+ adapted models that ranks first on the public Algonauts post-challenge leaderboard at the time of writing. Together, our results highlight PEFT as an efficient and powerful paradigm for brain encoding.

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Topics: Computer science, Encoding (memory), Artificial intelligence, Exploit, Artificial neural network, Modality (human–computer interaction)

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange