AI Paper Atlas

Research map / 3D vision / Human pose estimation

Ego-Human Motion Prediction with 3D-Aware LLM

Yujin Bae, Jaewoo Jeong, HYEONSEONG KIM, KUK-JIN YOON

ECCV 2026 · 3D vision › Human pose estimation · approach: Human motion prediction · 1 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
jointly decode pose and language in a single pass with 3D scene and GRPO (Ego3DLM vs UniEgoMotion)Ego3DLM · Nymeria future motion prediction (3 modes)JPE: 424.3 -> 364.5Improved
Ego3DLM vs UniEgoMotion on motion trackingEgo3DLM · Nymeria motion trackingAPE: 152.2 -> 96.4Improved
single-pass joint decoding vs separate decoding (EgoLM)Ego3DLM · Nymeria past motion narrationBleu-4: 0.0649 -> 0.1107Improved
add 3D scene input (ablation)Ego3DLM SFT · Nymeria motion trackingAPE: 105.8 -> 98.3Improved
add semantic QA pretraining (ablation)Ego3DLM SFT · Nymeria motion trackingAPE: 122.1 -> 98.3Improved
add spatial QA pretraining (ablation)Ego3DLM SFT · Nymeria future motion prediction (3 modes)JPE: 378.3 -> 368.3Improved
add spatial scene reasoning (SSR) step before outputs (ablation)Ego3DLM SFT · Nymeria future motion descriptionR@3: 0.2638 -> 0.2706Improved
add inter-modal matching reward on top of motion+text rewards (ablation)Ego3DLM GRPO · Nymeria future motion prediction (3 modes)JPE: 369.6 -> 364.5No clear effect
add inter-modal matching reward (ablation)Ego3DLM GRPO · Nymeria future motion descriptionR@3: 0.2726 -> 0.2911Improved
GRPO finetuning over SFT only (ablation)Ego3DLM · Nymeria motion trackingAPE: 98.3 -> 96.4Improved
add motion reward alone vs SFT only (ablation)Ego3DLM GRPO · Nymeria future motion prediction (3 modes)FID: 0.0190 -> 0.0149Improved
add 3D scene to baselines (ablation)UniEgoMotion · Nymeria future motion prediction (3 modes)JPE: 439.5 -> 424.3Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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