AI Paper Atlas

Research map / Vision-language and multimodal / Robot action and navigation

ENACT: Evaluating Embodied Cognition with World Modeling of Egocentric Interaction

Qineng Wang, Wenlong Huang, Yu Zhou, Hang Yin, Tianwei Bao, Jianwen Lyu, Weiyu Liu, Ruohan Zhang, Jiajun Wu, Li Fei-Fei, Manling Li

ICLR 2026 · Vision-language and multimodal › Robot action and navigation · approach: Embodied multimodal LLM agents · 15 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
increase interaction horizon L from 3 to 10GPT-5 · ENACT forwardpairwise accuracy: 84.62 -> 46.93Hurt
increase interaction horizon L from 3 to 10GPT-5 · ENACT inversepairwise accuracy: 86.28 -> 55.33Hurt
switch task from forward to inverse world modelingGPT-5 · ENACT L=10pairwise accuracy: 46.93 -> 55.33Improved
use real-world imagery instead of simulator (ablation)InternVL3.5-241B-A28B · ENACT real-worldpairwise accuracyNo clear effect
change rendering realism (Realistic, Path Tracing, Ray Tracing Only) (ablation)GPT-5 mini · ENACT simulation, L in {3,6,9}pairwise accuracyNo clear effect
widen camera aperture to 60, 80 or fisheye vs 40 (ablation)GPT-5 mini · ENACT simulationpairwise accuracyHurt
change camera aperture from 40 to 30 (ablation)GPT-5 mini · ENACT simulationpairwise accuracyNo clear effect
raise camera height by 0.5 m (ablation)GPT-5 mini · ENACT forwardpairwise accuracy: Delta=-0.13Hurt
raise camera height by 0.5 m (ablation)GPT-5 mini · ENACT inversepairwise accuracy: Delta=-0.06No clear effect
lower camera height by 0.25 m (ablation)GPT-5 mini · ENACT simulationpairwise accuracyNo clear effect
change robot appearance (white, random, skin color) (ablation)GPT-5 mini · ENACT simulationpairwise accuracyNo clear effect
left vs right hand actionsVLMs (GPT-5 mini) · ENACT forward, hand predicatesmixing rate: 9.38% left->right vs 4.67% right->leftMixed

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