arXiv:2605. 25848v2 Announce Type: replace-cross Abstract: A concept probe is only as reliable as the layer it is taken from.
arXiv:2605. 24856v2 Announce Type: replace-cross Abstract: Concept formation in transformer language models is a depth-extended process, not a single-layer event: a concept becomes separable across one or more contiguous regions of the residual stream - its Concept Allocation Zone (CAZ).
arXiv:2608. 10251v1 Announce Type: cross Abstract: A transformer's answer lives on one axis: the direction its unembedding reads.
arXiv:2603. 13259v2 Announce Type: replace-cross Abstract: When a decoder-only transformer is forced to process matched correct and incorrect single-token continuations of a factual query, the two pathways through hidden-state space diverge in a specific way: displacement vectors from the query-only representation maintain approximately equal magnitude but rotate apart in direction.
The paper investigates where the ‘refusal’ behavior of language models resides across different architectures. It finds that a single direction in the residual stream governs refusal in transformers, and that the same direction—after a rigid rotation—also governs refusal in state‑space models (SSMs). By aligning these directions and applying a detector‑triggered gate, the authors demonstrate that refusal can be effectively transferred across transformer, SSM, recurrent, and hybrid architectures, showing that safety tooling can be ported by re‑estimating the direction at each architecture’s write site rather than rebuilding it from scratch.
arXiv:2608. 12652v1 Announce Type: cross Abstract: Benchmark contamination is diagnosed today with n-gram overlap, with likelihood-based membership inference, or with canary strings, and each needs something usually unavailable: the training corpus, a well-chosen test statistic, or foresight at dataset release.
arXiv:2607. 18348v1 Announce Type: cross Abstract: We propose a transition-centred geometric analysis of transformer residual streams.
arXiv:2605.00915v2 Announce Type: replace Abstract: Probing frozen vision transformers typically uses permutation-invariant aggregation (GAP or $\texttt{[CLS]}$), treating patch tokens as an unstruct...
arXiv:2608.21008v1 Announce Type: new Abstract: Mobile AR frameworks attach a metric pose prior to every casual phone capture, and turning it into reconstruction-grade poses cheaply on CPU is the ste...
arXiv:2607. 17962v1 Announce Type: cross Abstract: TabPFN is a transformer-based foundation model for tabular prediction that performs inference without task-specific training by conditioning on a support set and query inputs.
arXiv:2607. 05268v1 Announce Type: cross Abstract: Whether a hyperbolic representation model uses its geometry cannot be read off its curvature parameter: what matters is the dimensionless operating point $\sqrt{c}\rho$ and whether the radial and cone machinery is active there.
arXiv:2609. 12591v1 Announce Type: new Abstract: Foundation models are increasingly adapted through fine-tuning, model editing, and alignment procedures while retaining previously acquired capabilities.
4D radar complements dense image semantics with long-range geometry and radial motion, but existing radar--camera detectors largely solve \emph{where} to align the modalities while leaving \emph{wheth...