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:2603.18908v5 Announce Type: replace Abstract: Independently trained language models often learn compatible late-stage representations, despite differences in training objectives, architectures,...
The paper investigates drift detection in deep learning models, showing that sharing a deep encoder alone does not eliminate confounding in task-comparison scores. By introducing a conditional two‑discriminator discrepancy into the embedding space, the authors create a two‑axis gate that remains stable under input rotations and accurately tracks label‑permutation drift. This approach outperforms traditional exchange or novelty triggers, achieving high AUROC in distinguishing semantic novelty from photometric shift across multiple backbones and datasets.
The paper demonstrates that sharing a deep encoder alone does not eliminate the confounding effects in task-comparison scores. By introducing a conditional two‑discriminator discrepancy within the embedding space, the authors achieve robust detection of task changes, maintaining stability under input rotations and accurately tracking label‑permutation drift. This approach, integrated into a mixture‑of‑heads framework, outperforms traditional novelty triggers and generalizes across multiple backbones and datasets, including ImageNet‑21k ViT‑B/16, DINOv2, and CIFAR‑100.
arXiv:2607. 22676v1 Announce Type: new Abstract: Post-training is a key mechanism for adapting large language models to downstream tasks.
arXiv:2510.01030v2 Announce Type: replace Abstract: The human ability to translate diverse perceptual and linguistic inputs into structured behavior has been thought to rest on learning robust repres...
The paper challenges the assumption that improving cross‑lingual alignment automatically enhances cross‑lingual transfer. Using XLM‑R models aligned on token, sentence, and masked‑language‑modeling objectives across four language pairs, the authors evaluate zero‑shot transfer on part‑of‑speech tagging and sentence classification. They find that embedding‑based alignment metrics poorly predict downstream performance and that alignment and task gradients are often nearly orthogonal, especially when operating at different representational levels.
The paper investigates whether layer-wise visual‑text similarity in multimodal large language models (MLLMs) truly reflects content‑level cross‑modal interaction. By injecting Gaussian noise into the visual stream of 13 MLLMs, the authors show that task accuracy drops sharply while traditional scalar alignment metrics (CKA, SVCCA, MIR, principal‑angle cosine) fail to distinguish corrupted from clean inputs, a phenomenon they term the alignment illusion. They propose the principal‑angle gap (PA gap) as a more reliable geometric diagnostic that correlates better with task performance and reveals when internal geometry diverges from accuracy.
arXiv:2602. 12952v3 Announce Type: replace Abstract: Adapting large pre-trained models to downstream tasks often produces task-specific parameter updates that are expensive to relearn for every model variant.
arXiv:2606. 18703v1 Announce Type: new Abstract: Pretrained biological language models expose per-token probability distributions through masked-token prediction, providing the likelihood interface central to sequence design, variant scoring, and mechanistic interpretation.
arXiv:2602. 01893v2 Announce Type: replace-cross Abstract: We present a geometric framework for analysing multi-head attention in large language models (LLMs).
The paper extends mechanistic interpretability of large language models by modeling concepts as low‑dimensional non‑linear manifolds rather than linear subspaces. It introduces a concept‑based alignment (CBA) score to compare these manifolds across layers and models, revealing block structures in intermediate layers, a shift from syntax‑dominated to mixed syntactic‑semantic concepts, and training‑dependent multilingual sharing. The study also shows that alignment patterns differ across model families and training stages, with adjacent stages aligning more closely than distant ones.
arXiv:2607. 06831v1 Announce Type: cross Abstract: Speech-to-text alignment means finding the temporal boundaries of each word in the audio.