AI Paper Atlas

Research map / Multi-agent systems and games / Human-AI and goal-conditioned

Towards Human-like Virtual Beings: Simulating Human Behavior in 3D Scenes

Chen Liang, Wenguan Wang, Yi Yang

ICCV 2025 · Multi-agent systems and games › Human-AI and goal-conditioned · approach: Embodied agent learning · 3 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 active tree search instead of one-pass planning (ablation)ACTOR · BehaviorHub Dynamic subsetGSR: 0.140 -> 0.235Improved
add hierarchical behavior prior (ablation)ACTOR · BehaviorHub Dynamic subsetGSR: 0.235 -> 0.261Improved
add value functions (ablation)ACTOR · BehaviorHub Dynamic subsetGSR: 0.261 -> 0.306Improved
use MCTS instead of greedy search (ablation)ACTOR · BehaviorHub Dynamic subsetGSR: 0.244 -> 0.306Improved
use MCTS instead of beam search (ablation)ACTOR · BehaviorHub Dynamic subsetGSR: 0.287 -> 0.306Improved
use GPT-4 instead of GPT-3.5 as LLM core (ablation)ACTOR · BehaviorHub Dynamic subsetGSR: 0.176 -> 0.306Improved
use GPT-3.5 instead of Vicuna-7b as LLM core (ablation)ACTOR · BehaviorHub Dynamic subsetGSR: 0.092 -> 0.176Improved
pre-train on BehaviorHub before fine-tuningscene-aware motion generation model · PROXMPJPE: 242.50 -> 201.56Improved
pre-train on BehaviorHub before fine-tuningMDM · HumanML3DFID: 0.544 -> 0.471Improved

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