AI Paper Atlas

Research map / Architectures and efficiency / Attention and transformers

Bayesian Attention Mechanism: A Probabilistic Framework for Positional Encoding and Context Length Extrapolation

Arthur S. Bianchessi, Yasmin C. Aguirre, Rodrigo C. Barros, Lucas S. Kupssinskü

ICLR 2026 · Architectures and efficiency › Attention and transformers · approach: Sparse attention for long-context LLMs · 2 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add Scaled Softmax (SSMax) to BAM (ablation)BAM · Wikipedia (512 tokens)perplexity: 18.9281 -> 18.6897Improved
add Scaled Softmax (SSMax) to BAM (ablation)BAM · FineWeb (512 tokens)perplexity: 22.2640 -> 22.1363Improved
add Scaled Softmax (SSMax) to RoPE (ablation)RoPE · Wikipedia (512 tokens)perplexity: 18.3599 -> 20.1854Hurt
add Scaled Softmax (SSMax) to RoPE (ablation)RoPE · FineWeb (512 tokens)perplexity: 22.4428 -> 24.4507Hurt
add Scaled Softmax (SSMax) to NoPE (ablation)NoPE · Wikipedia (512 tokens)perplexity: 19.8609 -> 20.3899Hurt
add Scaled Softmax (SSMax) to NoPE (ablation)NoPE · FineWeb (512 tokens)perplexity: 23.7898 -> 23.7581Improved
add Scaled Softmax (SSMax) to ALiBi (ablation)ALiBi · Wikipedia and FineWeb (512 tokens)perplexity: 18.5452 -> 18.4967 (Wikipedia); 22.1771 -> 22.2125 (FineWeb)Mixed
add Scaled Softmax (SSMax) to Sinusoidal (ablation)Sinusoidal · Wikipedia and FineWeb (512 tokens)perplexity: 18.9310 -> 19.1467 (Wikipedia); 22.3573 -> 22.3150 (FineWeb)Mixed
use BAM instead of ALiBi positional priorALiBi · Wikipedia (512 tokens)perplexity: 18.5452 -> 18.9281Hurt
use BAM instead of SinusoidalSinusoidal · FineWeb (512 tokens)perplexity: 22.3573 -> 22.2640Improved
use BAM instead of Sinusoidal, RoPE and NoPE for passkey retrieval beyond training lengthSinusoidal/RoPE/NoPE · Passkey retrievalaccuracy: only BAM retained high accuracy up to 32,000 tokensImproved
add BAM SSMax to ALiBi baseline for passkey retrievalALiBi · Passkey retrievalaccuracy: perfect accuracy beyond 64x training lengthImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy