A Visual Guide to Attention Variants in Modern LLMs

Beyond Standard LLMs

Linear Attention Hybrids, Text Diffusion, Code World Models, and Small Recursive Transformers

Mechanistic Insights into Functional Sparsity in Multimodal LLMs via CoRe Heads

arXiv:2606. 05843v1 Announce Type: cross Abstract: While Multimodal Large Language Models (MLLMs) demonstrate remarkable proficiency on complex vision-language tasks, the mechanisms by which they extract query-relevant visual features from complex, noisy contexts remain opaque.

Rethinking the Role of Efficient Attention in Hybrid Architectures

arXiv:2606. 15378v1 Announce Type: cross Abstract: Modern language models increasingly adopt hybrid architectures that combine full attention with efficient attention modules, such as sliding-window attention (SWA) and recurrent sequence mixers.

EyeMulator: Improving Code Language Models by Mimicking Human Visual Attention

arXiv:2508. 16771v3 Announce Type: replace-cross Abstract: Code Language Models (CodeLLMs) learn token importance from data correlations, whereas human developers attend selectively to semantically salient code.

Formalizing and Mitigating Structural Distortion in LLM Attention for Graph Reasoning

arXiv:2606. 15633v2 Announce Type: replace Abstract: Large Language Models (LLMs) have shown promise for reasoning over Text-Attributed Graphs (TAGs).

Formalizing and Mitigating Structural Distortion in LLM Attention for Zero-Shot Graph Reasoning

arXiv:2606. 15633v1 Announce Type: new Abstract: Large Language Models (LLMs) have shown promise for reasoning over Text-Attributed Graphs (TAGs).

Massive Activations in Hybrid Linear Attention Large Language Models: Pre-Attention Spikes and Inter-Spike Plateaus

We present the first systematic study of Massive activations (MAs) in layer-interleaved HLA LLMs and uncover two architecture-aligned morphologies: MAs consistently spike immediately before full attention layers, forming pre-attention spikes (PAS), and can persist through intervening linear attention layers, giving rise to inter-spike plateaus (ISP). As full attention becomes denser, successive PAS become increasingly connected through ISP, ultimately recovering the stable MA morphology of full attention LLMs.

Eigenvalues as a Metric for Memory Dynamics in Sequence Models

arXiv:2510. 09379v2 Announce Type: replace Abstract: While softmax attention drives state-of-the-art performance in sequence modeling, its quadratic complexity motivates linear alternatives such as state space models (SSMs).

Perceiver IO: a scalable, fully-attentional model that works on any modality

The Wiola Architecture for Efficient Small Language Models

We present Wiola, a fully original Small Language Model (SLM) architecture built from first principles, sharing no structural lineage with any existing model family including GPT, LLaMA, Mistral, or Falcon. Wiola introduces five independently novel components: (i) Spiral Rotary Positional Encoding (SRPE), which embeds token positions on a three-dimensional helical manifold combining absolute, relative, and hierarchical positional signals; (ii) Gated Cross-Layer Attention (GCLA), providing each decoder layer with soft cross-attention access to compressed summaries of two preceding layers for inter-layer coherence; (iii) Adaptive Token Merging (ATM), which dynamically merges se mantically redundant adjacent tokens in middle network layers to reduce attention complexity without information loss; (iv) Dual Stream Feed-Forward (DSFF), replacing the conventional MLP with two parallel streams fused by a learned per-dimension gate; and (v) WiolaRMSNorm, a modified normalisation introducing a per-dimension learned offset vector that prevents representation collapse.

The Wiola Architecture for Efficient Small Language Models

arXiv:2607. 01394v1 Announce Type: new Abstract: We present Wiola, a fully original Small Language Model (SLM) architecture built from first principles, sharing no structural lineage with any existing model family including GPT, LLaMA, Mistral, or Falcon.

RePo: Language Models with Context Re-Positioning

arXiv:2512. 14391v3 Announce Type: replace-cross Abstract: In-context learning is fundamental to modern Large Language Models (LLMs); however, prevailing architectures impose a rigid and fixed contextual structure by assigning linear or constant positional indices.