arXiv:2608. 03294v1 Announce Type: new Abstract: We study the problem of learning multi-head softmax attention from black-box input-output access.
arXiv:2607. 18759v1 Announce Type: new Abstract: Transformers with relative positional encodings often extrapolate to sequences longer than those seen during training, whereas transformers with learned absolute encodings typically do not.
arXiv:2609. 03129v1 Announce Type: cross Abstract: Several classical machine-learning methods, such as KRRs and SVRs, are both computationally and analytically tractable since their estimators either admit closed-form expressions or are obtained by minimizing convex training objectives; neither feature is generally available for deep neural networks.
arXiv:2509. 20848v2 Announce Type: replace-cross Abstract: In the classic point location problem, one is given an arbitrary dataset $X \subset \mathbb{R}^d$ of $n$ points with query access to an unknown halfspace $f : \mathbb{R}^d \to \{0,1\}$, and the goal is to learn the label of every point in $X$.
arXiv:2607. 23050v1 Announce Type: new Abstract: Neural scaling laws describe how loss decreases as models, data, and compute grow, but they do not answer a prior question: for a fixed task, what is the minimum model capacity required to solve it?
arXiv:2606. 07205v1 Announce Type: cross Abstract: The attention mechanism is a cornerstone of modern transformer architectures.
arXiv:2609.06685v1 Announce Type: cross Abstract: We derive an exact gradient-step representation of the RoPE-softmax forward pass. For every deterministic RoPE-softmax attention head with arbitrary...
arXiv:2608. 09558v1 Announce Type: new Abstract: How expressive is prompting a transformer?
arXiv:2608. 26052v1 Announce Type: new Abstract: Choosing the rank of a low-rank adaptation (LoRA) update is usually an empirical task.
arXiv:2411. 16073v4 Announce Type: replace-cross Abstract: Inspired by the Well-initialized Lottery Ticket Hypothesis (WLTH), we introduce Soft-TransFormers (Soft-TF), a continual learning framework that adapts a frozen pre-trained Transformer through task-specific soft subnetworks: real-valued multiplicative masks over the query, key, value, and output projections of selected self-attention layers.
arXiv:2609.21523v1 Announce Type: new Abstract: A system may be compressed before its downstream task is fully known. We ask how much retained state is then necessary and how much can be saved by lim...
arXiv:2609.01129v1 Announce Type: new Abstract: We identify a recurrent algebraic regularity in Transformer attention: a sparse subset of effective OV operators $T=OV^\top$ nearly closes under compos...
The paper investigates how transformer language models perform few‑shot learning for a simple addition task, showing that the ability is concentrated in a handful of attention heads. Using dimensionality reduction, the authors identify low‑dimensional subspaces—three heads with six‑dimensional spaces in Llama‑3‑8B‑Instruct—where specific dimensions encode the units digit via trigonometric patterns and magnitude via low‑frequency components. They also derive a mathematical identity linking aggregator and extractor subspaces, enabling tracking of information flow from examples to the final prediction.