AI Paper Atlas

Research map / Architectures and efficiency / Attention and transformers

Hippoformer: Integrating Hippocampus-inspired Spatial Memory with Transformers

Tiantian Li, Xingxing Cao, Yifei Wang, Xiaojiao Yang, Xiaolong Zou, Bo Hong

ICLR 2026 · Architectures and efficiency › Attention and transformers · approach: Transformer expressivity and learnability

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
replace TEM with mm-TEM (hierarchical MLP relational memory)TEM · 2D grid predictiontest accuracy / training efficiency: about 60% after 20,000 steps -> nearly 90% within 5,000 stepsImproved
add auxiliary relational loss L_g2g (ablation)mm-TEM · 2D grid predictiongeneralization accuracyImproved
add auxiliary relational loss L_s2g (ablation)mm-TEM · 2D grid predictiongeneralization accuracyImproved
add all auxiliary relational memory losses (ablation)mm-TEM · 2D grid predictiongeneralization accuracyImproved
combine one-layer Transformer with mm-TEM (Hippoformer) instead of mm-TEM alonemm-TEM · 3D environment 1-step errorerror (1e-3): 5.10 -> 1.27Improved
combine mm-TEM with Transformer instead of Transformer aloneTransformer · 3D environment multi-step imaginationerror (1e-3): 36.13 -> 9.71Improved
combine mm-TEM with Transformer instead of TitansTitans · 3D environment multi-step imaginationerror (1e-3): 33.42 -> 9.71Improved
combine Transformer with mm-TEM versus Transformer alone for 1-stepTransformer · 3D environment 1-step errorerror (1e-3): 1.29 -> 1.27No clear effect
increase memory update interval mb (ablation)mm-TEM · 2D grid predictiongrid scale: coarser grids at larger mb; single-step accuracy reducedMixed
add mm-TEM path integration with higher grid scoremm-TEM · 2D grid multi-step accuracycorrelation: r = 0.647Improved
evaluate mm-TEM vs Titans and Transformer under counterclockwise shiftmm-TEM · circular-grid testaccuracy: over 90% vs drops of up to 30%Improved

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