The paper introduces Outlier-Aware Attention Linearization (OAL), a method that improves linearized softmax attention by explicitly accounting for a few outlier dimensions that disproportionately affect query-key dot products. OAL builds on a second-order Taylor approximation, uses a Hadamard-product formulation to expose dimension-specific contributions, and groups dimensions with similar scales to share coefficients while treating outliers separately. Experiments on Qwen2.5-0.5B show an 8.9% reduction in frozen-attention output MSE, and fine-tuning with LoRA lowers WikiText-103 perplexity from 31.71 to 27.50 while boosting performance on PIQA, HellaSwag, and ARC-E.
arXiv:2605. 18848v3 Announce Type: replace Abstract: This paper introduces Exact Linear Attention (ELA), a mechanism that achieves linear computational complexity for Transformer attention by exploiting the exact decomposition property of kernel functions, thereby eliminating approximation error.
arXiv:2607. 20214v1 Announce Type: cross Abstract: The quadratic $N\times N$ attention score matrix remains a central obstacle to extending Transformers to longer input lengths.
arXiv:2509. 07963v2 Announce Type: replace Abstract: The core component of attention is the scoring function, which transforms the inputs into low-dimensional queries and keys and takes the dot product of each pair.
arXiv:2610.14219v1 Announce Type: cross Abstract: Softmax attention in Transformers suffers from quadratic complexity in sequence length, making it impractical for long-context applications. Linear a...
arXiv:2606. 01294v1 Announce Type: cross Abstract: Linear attention reduces the quadratic cost of softmax attention by maintaining a recurrent fast-weight state, but it consistently lags on in-context retrieval and long-context tasks.
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:2609.14127v1 Announce Type: cross Abstract: We derive exact local responses for attention interventions, allowing candidate edits to be scored from a cached baseline and one backward pass. The...
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:2606. 05899v1 Announce Type: new Abstract: We develop a high-dimensional statistical theory of low-rank adaptation (LoRA) in attention models, capturing the interplay between pre-training and fine-tuning.
The paper establishes rigorous trainability results for multi-headed attention layers and Low Rank Adaptation (LoRA) models under stochastic training methods. By proving that the empirical regression loss induces a Poincaré inequality with constants independent of data dimension for LoRA and independent of head dimensions for multi-head attention, the authors show that a stochastic differential equation mimicking SGD converges to the loss minima. These results hold without assumptions on data or model size, providing the first theoretical guarantees for training such architectures.
arXiv:2609.13141v1 Announce Type: new Abstract: Post-training attention sparsification reduces the quadratic cumulative attention cost of pretrained Transformers by selecting a small set of context u...
arXiv:2504. 17768v3 Announce Type: replace-cross Abstract: Sparse attention offers a promising strategy to extend long-context capabilities in Transformer LLMs, yet its efficiency-accuracy trade-offs remain unclear due to the lack of comprehensive evaluation.