AI Paper Atlas

Research map / Vision-language and multimodal / Human and embodied modeling

The Mechanistic Emergence of Symbol Grounding in Language Models

Shuyu Wu, Ziqiao Ma, Xiaoxi Luo, Yidong Huang, Josue Torres-Fonseca, Freda Shi, Joyce Chai

ICML 2026 · Vision-language and multimodal › Human and embodied modeling · approach: Visual grounding transformers · 0 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
zero out aggregate heads (vs random heads of equal number) (ablation)12-layer Transformer on CHILDES, 20k steps · CHILDES grounding (match condition)surprisal: 4.77 -> 5.62 (control 4.76)Hurt
zero out gather heads (vs random heads of equal number) (ablation)12-layer Transformer on CHILDES, 20k steps · CHILDES grounding (match condition)surprisal: 4.69 vs control 4.79No clear effect
zero out aggregate heads (vs random heads) (ablation)12-layer Transformer on Visual Dialog, 300k steps, 70% threshold · Visual Dialog image-groundedsurprisal: 7.69 -> 8.96 (control 8.11)Hurt
zero out aggregate heads (vs random heads) (ablation)12-layer Transformer on Visual Dialog, 300k steps, 90% threshold · Visual Dialog image-groundedsurprisal: 7.69 -> 8.40 (control 7.87)Hurt
train Transformer or Mamba-2 (vs unidirectional LSTM) on grounded data (ablation)4-layer models on CHILDES · CHILDES groundingmatch vs mismatch surprisal gapImproved
grounding information gain increases beyond co-occurrence statisticsTransformer and Mamba-2 · CHILDES groundingR2 with log co-occurrenceMixed
replace CHILDES text environment with image patches (DINOv2) as environmental ground12-layer Transformer · Visual Dialoggrounding information gainMixed

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