Research map / Multi-agent systems and games / LLM agents
Thinking Ahead: Foresight Intelligence in MLLMs and World Model
Zhantao Gong, Liaoyuan Fan, Qing Guo, Xun Xu, Xulei Yang, Shijie Li
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 |
|---|---|---|---|
| finetune Qwen3-VL-8B on FSU-QA training split | Qwen3-VL-8B · FSU-Bench | accuracy | Improved |
| add Epona-predicted video and trajectory as input | VLMs · FSU-Bench (Epona) | accuracy | Improved |
| add DrivingWorld-predicted video and trajectory as input | VLMs · FSU-Bench (DrivingWorld) | accuracy | Improved |
| replace WM predictions with those from a different scene (shuffled control) (ablation) | VLMs with WM inputs · FSU-Bench | accuracy | Hurt |
| add predicted trajectory only (Epona) | Claude-Sonnet-4.5 · FSU-Bench Pedestrian Intent, Risk Area | accuracy | Improved |
| add predicted video only (Epona) | GPT-5 · FSU-Bench Rel. Dist., E-V Rel. Pos. | accuracy | Improved |
Closest papers by meaning
- OneVL: One-Step Latent Reasoning and Planning with Vision-Language Explanation (NeurIPS 2026 · similarity 0.85)
- DriveFuture: Future-Aware Latent World Models for Autonomous Driving (NeurIPS 2026 · similarity 0.84)
- FutureSightDrive: Thinking Visually with Spatio-Temporal CoT for Autonomous Driving (NeurIPS 2025 · similarity 0.84)
- LaST-VLA: Thinking in Latent Spatio-Temporal Space for Vision-Language-Action in Autonomous Driving (NeurIPS 2026 · similarity 0.84)
- ThinkJEPA: Empowering Latent World Models with Large Vision-Language Reasoning Model (NeurIPS 2026 · similarity 0.84)
- FutureSim: Replaying World Events to Evaluate Adaptive Agents (NeurIPS 2026 · similarity 0.83)
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.
