arXiv:2608. 01968v1 Announce Type: new Abstract: Transformer models are most often understood through what they do: their benchmark performance, generation quality, or behavior on downstream tasks.
arXiv:2606. 09287v1 Announce Type: new Abstract: Understanding how transformer representations evolve across layers, not merely what they encode, remains an open problem in mechanistic interpretability.
arXiv:2606. 27242v1 Announce Type: new Abstract: Training-free source selection for LLM families with shared vocabularies arises in scientific string domains such as SMILES, protein, and genomic sequences, where candidate corpora share a tokenizer but differ in prediction targets.
arXiv:2606. 07559v1 Announce Type: cross Abstract: Fine-tuning a language model on contexts whose correct completion has a near-synonym competitor often fails silently.
arXiv:2606. 07559v2 Announce Type: replace-cross Abstract: Fine-tuning a language model often fails silently when its correct completion must outrank a near-synonym competitor.
arXiv:2608. 05160v1 Announce Type: new Abstract: We introduce the Ignition Index (I), a validated scalar metric that operationalizes Global Workspace Theory's (GWT) all-or-none ignition prediction in transformer language models.
arXiv:2607. 24519v1 Announce Type: cross Abstract: Pretrained EEG foundation models are increasingly proposed for clinical decoding, but their transfer across populations and robustness to negative controls remain unclear.
arXiv:2608. 12447v1 Announce Type: new Abstract: Trained transformer models develop privileged bases: coordinate axes whose statistics differ from the rest of the residual stream.
arXiv:2512. 22227v3 Announce Type: replace-cross Abstract: We investigate whether graded states of mind form spectrum-like structure in transformer representation spaces.
arXiv:2607. 24519v2 Announce Type: replace Abstract: Pretrained EEG foundation models are proposed for clinical decoding, but whether reported gains transfer across populations or survive negative controls is unclear.
Pretrained EEG foundation models are increasingly proposed for clinical decoding, but their transfer across populations and robustness to negative controls remain unclear. We benchmark six models (LaBraM, EEGMamba, CBraMod, REVE, BENDR, and BIOT) on five clinical tasks across four datasets using frozen linear probes with leave-one-subject-out, subject-grouped, or explicitly identified recording-level splits.
arXiv:2603. 01568v2 Announce Type: replace Abstract: Efficient coding theory predicts that biological perceptual systems compress sensory input optimally under resource constraints, with the systematic structure of errors reflecting the geometry of that compression.
arXiv:2607. 26192v1 Announce Type: new Abstract: Input-dependent controller coefficients are often treated as evidence of dynamic inference or computational savings.