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
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add active tree search instead of one-pass planning (ablation) | ACTOR · BehaviorHub Dynamic subset | GSR: 0.140 -> 0.235 | Improved |
| add hierarchical behavior prior (ablation) | ACTOR · BehaviorHub Dynamic subset | GSR: 0.235 -> 0.261 | Improved |
| add value functions (ablation) | ACTOR · BehaviorHub Dynamic subset | GSR: 0.261 -> 0.306 | Improved |
| use MCTS instead of greedy search (ablation) | ACTOR · BehaviorHub Dynamic subset | GSR: 0.244 -> 0.306 | Improved |
| use MCTS instead of beam search (ablation) | ACTOR · BehaviorHub Dynamic subset | GSR: 0.287 -> 0.306 | Improved |
| use GPT-4 instead of GPT-3.5 as LLM core (ablation) | ACTOR · BehaviorHub Dynamic subset | GSR: 0.176 -> 0.306 | Improved |
| use GPT-3.5 instead of Vicuna-7b as LLM core (ablation) | ACTOR · BehaviorHub Dynamic subset | GSR: 0.092 -> 0.176 | Improved |
| pre-train on BehaviorHub before fine-tuning | scene-aware motion generation model · PROX | MPJPE: 242.50 -> 201.56 | Improved |
| pre-train on BehaviorHub before fine-tuning | MDM · HumanML3D | FID: 0.544 -> 0.471 | Improved |
Closest papers by meaning
- Habitat 3.0: A Co-Habitat for Humans, Avatars, and Robots (ICLR 2024 · similarity 0.87)
- An Embodied Generalist Agent in 3D World (ICML 2024 · similarity 0.86)
- WANDR: Intention-guided Human Motion Generation (CVPR 2024 · similarity 0.86)
- SimWorld Studio: Automatic Environment Generation with Evolving Coding Agent for Embodied Agent Learning (NeurIPS 2026 · similarity 0.86)
- Human-Aware Vision-and-Language Navigation: Bridging Simulation to Reality with Dynamic Human Interactions (NeurIPS 2024 · similarity 0.86)
- AgentStudio: A Toolkit for Building General Virtual Agents (ICLR 2025 · similarity 0.86)
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.
