arXiv Computation and Language
Hybrid Gated Attention
Read the original on arXiv Computation and Language →The Flow has not summarised this story yet — read it at arXiv Computation and Language.
Related stories
arXiv Computation and Language
Aug 31
Semantic Head Specialization Guides Hybrid ViT Attention for Multimodal LLMs
The paper introduces Semantic Head Specialization (SHS), a phenomenon where Vision Transformer (ViT) attention heads specialize as either object- or background-focused, most evident under full attention. It proposes the SHS-Index to quantify this specialization, demonstrating its ability to distinguish full-attention from chunk-window ViTs and its strong correlation with downstream benchmark performance. Leveraging insights into window interaction, token serialization, and local softmax allocation, the authors design Ariadne Attention, a hybrid attention mechanism that matches full-attention performance on 22 image and video tasks while reducing attention compute by 6.5×.
arXiv Computation and Language
4d ago
GatedV: Self-Gated Values for Transformer Language Models
The paper introduces GatedV, an attention variant that applies the SiLU activation only to the value matrix before aggregation, adding no extra trainable parameters. Experiments on a decoder‑only Transformer show that, with matched parameter counts and training budgets, GatedV consistently lowers held‑out perplexity—by 2.0% at 2.33M parameters and 2.4% at 26.16M parameters—across multiple seeds. Ablations indicate that the performance gains are not fully captured by simple affine rescaling of values, and a benchmark on NVIDIA DGX Spark reports a modest 0.7% increase in full‑context forward latency for the larger model.
arXiv AI
Oct 12
MS-GLA: Multi-Scale Gated Linear Attention for Addressing Representational Bottlenecks via Multi-Temporal Resolution
MS-GLA introduces Multi-Scale Gated Linear Attention, distributing attention heads across multiple temporal resolutions to address representational bottlenecks in GLA Transformers. Coarser resolutions pool longer token spans for long‑range dependencies, while finer heads capture local syntax, and a learnable fusion layer recombines outputs dynamically. Experiments on language modeling, recall‑intensive tasks, and long‑context generalization show MS‑GLA outperforms GLA with up to 18.9% improvement on recall tasks and 9.5% lower perplexity on language modeling benchmarks.
arXiv AI
Jul 21
Attentions Under the Microscope: A Comparative Study of Resource Utilization for Variants of Self-Attention
arXiv:2507. 07247v2 Announce Type: replace-cross Abstract: As large language models (LLMs) and visual language models (VLMs) grow in scale and application, attention mechanisms have become a central computational bottleneck due to their high memory and time complexity.
arXiv Computation and Language
Oct 12
Multi-Stream Attention Residuals
The paper introduces Multi-Stream Attention Residuals (MSAR), an extension of Attention Residuals that applies multi-head depth attention inspired by multi-head sequence attention. MSAR uses multi-scale causal convolutions to provide diverse contextual views for each head, then adaptively mixes the retrieved streams into a single-stream input, avoiding persistent multi-stream storage. Across 12 downstream benchmarks at 18B and 28B MoE scales, MSAR outperforms prior residual variants and achieves a 1.58× compute speedup over the standard residual baseline.
arXiv AI
Oct 12
Kairos: Toward a Byte-Level Foundation Model for Every Modality
Kairos is a byte‑level foundation model that integrates bidirectional gated‑DeltaNet linear attention, sliding‑window attention, block‑wise Attention‑Residual aggregation, a sparse Mixture‑of‑Experts feed‑forward layer, and a multi‑scale byte‑level codec. It is trained with a uniform‑noise denoising objective over a single byte space shared by text, image, audio, video, lidar, and control streams, and the authors provide code‑derived algorithms for each component, including a cross‑session recurrent‑state memory gate. Convergence sanity checks on a 440‑byte text sentence show that the two attention variants reach a minimum loss near 10⁻³, and the implementation appears to optimize, though generalization and multimodal performance remain to be evaluated in future pretraining runs.