arXiv Machine Learning
Aug 12
Off-Axis, On Purpose: Where a Transformer Computes Concepts and Why it Does So
arXiv:2608. 10251v1 Announce Type: cross Abstract: A transformer's answer lives on one axis: the direction its unembedding reads.
Scaled Idempotence in Transformer Attention: Paired OV Geometry and Shared-Value Algebras
Related stories
arXiv Machine Learning
Sep 2
Multi-Head Self Attention is a Parameter Identification Mechanism
arXiv:2609.01231v1 Announce Type: new Abstract: We prove that a multi-head scaled dot product attention can be viewed as a parameter identification strategy. The ratio of unidentified parameters to t...
arXiv AI
Aug 18
LORA-CRAFT: Cross-layer Rank Adaptation via Frozen Tucker Decomposition of Pre-trained Attention Weights
arXiv:2602. 17510v2 Announce Type: replace-cross Abstract: We introduce LoRA-CRAFT (\textbf{C}ross-layer \textbf{R}ank \textbf{A}daptation via \textbf{F}rozen \textbf{T}ucker), abbreviated CRAFT throughout, an extremely parameter-efficient fine-tuning (PEFT) method that applies Tucker tensor decomposition to pre-trained attention weight matrices stacked across transformer layers and trains only small square adaptation matrices on the resulting frozen Tucker factors.
arXiv Machine Learning
Jul 7
CORA: Per-Slice Coherent Orthogonal Rotation for SVD-based Low-Rank Adaptation
arXiv:2607. 02576v1 Announce Type: cross Abstract: Parameter-Efficient Fine-Tuning (PEFT) commonly adapts pretrained weights through low-rank updates, and recent methods further exploit the singular value decomposition (SVD) of the base weight for initialization or subspace selection.
arXiv AI
Jul 23
Geometric Attention: A Regime-Explicit Operator Semantics for Transformer Attention
arXiv:2601. 11618v2 Announce Type: replace-cross Abstract: Geometric Attention (GA) specifies an attention layer by four independent inputs: a finite carrier (what indices are addressable), an evidence-kernel rule (how masked proto-scores and a link induce nonnegative weights), a probe family (which observables are treated as admissible), and an anchor/update rule (which representative kernel is selected and how it is applied).
arXiv AI
Jun 3
Exact equivariance, kept through training, buys zero-shot generalisation across the symmetry group
arXiv:2606. 03003v1 Announce Type: cross Abstract: A latent world model built from an equivariant encoder $E$ and an equivariant predictor $f$ inherits a provable symmetry of its training loss: when the world's dynamics genuinely carries a group $G$ acting on latents by an orthogonal representation $\rho(g)$, the one-step prediction relMSE is exactly invariant across the whole group, so fitting the dynamics on a restricted slice of orientations mathematically determines it on the entire orbit (j\v{u} y\=i f\v{a}n s\=an).
arXiv AI
Jun 4
Do Transformers Need Three Projections? Systematic Study of QKV Variants
arXiv:2606. 04032v1 Announce Type: cross Abstract: Transformers have become the standard solution for various AI tasks, with the query, key, and value (QKV) attention formulation playing a central role.
arXiv Machine Learning
Jun 29
A Unified Framework for Vision Transformers Equivariant to Discrete Subgroups of $\mathrm{O}(2)$
arXiv:2606. 27864v1 Announce Type: cross Abstract: Vision transformers have become a dominant architecture for visual recognition.
arXiv Machine Learning
Jul 20
Looped Latent Attention: Cross-Loop KV Compression for Looped Transformers
arXiv:2607. 15456v1 Announce Type: new Abstract: Looped, weight-tied Transformers reduce parameters by reusing a block, but decoding still stores a separate K/V cache for every recurrence step.
arXiv Machine Learning
2d ago
Block-Wise Differentiable Sinkhorn Attention: Tail-Refinement Gradients with a Gap-Aware Dustbin Bridge
The paper presents a block‑wise differentiable Sinkhorn attention mechanism designed for long‑context balanced entropic optimal transport on TPU hardware. By stopping a $T$‑step Sinkhorn solve and unrolling a short refinement tail, the authors derive an exact surrogate gradient that achieves efficient block‑wise cost and memory usage. Experimental results on synthetic masked problems and a Pfam protein‑family screen demonstrate high numerical accuracy and sustained throughput on TPU v6e‑8, with notable improvements in reconstruction and sparse cross‑entropy metrics.
arXiv Machine Learning
Jun 25
Why Do Accumulated Transformations Extrapolate?
arXiv:2606. 24975v1 Announce Type: new Abstract: PaTH Attention showed that replacing RoPE's position-indexed rotations with accumulated data-dependent Householder reflections yields strong length extrapolation, though performance degrades at extreme context lengths.
Hugging Face Trending Papers
Jun 28
Dead-Direction Conditioners: Gauge-Equivariant Preconditioning for Deep Networks
A deep network's loss is invariant to continuous symmetries of its parameters: the logit shift, the ReLU rescaling, the LayerNorm scale, the per-head attention rotation. Adam's per-coordinate preconditioner drifts along each symmetry orbit, which pulls the trajectory off the symmetry quotient where the optimization lives and blurs the singular-learning rate the quotient makes readable.