{"ID":6621235,"CreatedAt":"2026-07-15T01:01:48.440468303Z","UpdatedAt":"2026-07-15T03:28:55.185153975Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.12079","arxiv_id":"2607.12079","title":"The Capacity of Thought: Benchmarking Llama 3.2 in Semantic fMRI Neural Language Decoding and Improving the Huth Encoding-Model Baseline","abstract":"Decoding continuous language from fMRI signals remains a core challenge in non-invasive brain-computer interface research. We present two complementary investigations. First, we improve the Huth et al. ridge regression encoding pipeline through expanded voxel selection (10K-\u003e15K), substitution of GPT-2 medium for GPT-1 as the beam-search proposal model, and GPU-accelerated bootstrap training, achieving mean METEOR = 0.149 and BLEU-1 = 0.200 across three held-out narratives for subject UTS03 -- an 11% relative METEOR gain over our replication baseline. Second, we introduce fMRIFlamingo, which maps BOLD activity to a frozen Llama-3.2-1B with trainable gated cross-attention layers via a learned brain tokenizer and a Perceiver Resampler. Despite achieving 42.86% Top-1 accuracy on a 1-in-100 ranking task, well above chance, a blind control ablation with zeroed fMRI inputs yields near-identical scores, revealing that apparent decoding success is driven primarily by the frozen language prior rather than by neural input. These results demonstrate that high-capacity language models do not inherently improve fMRI decoding and can actively obscure failures without rigorous blind-control evaluation.","short_abstract":"Decoding continuous language from fMRI signals remains a core challenge in non-invasive brain-computer interface research. We present two complementary investigations. First, we improve the Huth et al. ridge regression encoding pipeline through expanded voxel selection (10K-\u003e15K), substitution of GPT-2 medium for GPT-1...","url_abs":"https://arxiv.org/abs/2607.12079","url_pdf":"https://arxiv.org/pdf/2607.12079v1","authors":"[\"Milos Suvakovic\",\"Dom Marhoefer\",\"Glenn Grant-Richards\",\"Aidan Pinero\"]","published":"2026-07-13T18:56:17Z","proceeding":"cs.CL","tasks":"[\"cs.CL\"]","methods":"[\"Language Model\"]","has_code":false}