MBZUAI IFM 发布开放世界模型 PAN 2
MBZUAI IFM 发布 PAN 2 开放世界模型
MBZUAI 基础模型研究所（IFM）发布开放基础世界模型 PAN 2，面向物理智能的模拟式推理，让智能体先推演再行动。它由 LLM 负责概念推理、29B 从零训练的扩散模型负责感知生成；去掉 LLM 后多步任务仅 8.7% 步骤正确、无计划完成，两者配合则步骤正确率 75.1%、完整完成 34.0% 的计划，为 IFM 测试模型中最高。更多细节见技术博客 ifm.ai/pan/。
Rohan Paul· @rohanpaul_ai · X·2026-11-11 02:20· 48 分钟前AI 评分48
AI 导读
MBZUAI 基础模型研究所（IFM）发布开放基础世界模型 PAN 2，面向物理智能的模拟式推理，让智能体先推演再行动。它由 LLM 负责概念推理、29B 从零训练的扩散模型负责感知生成；去掉 LLM 后多步任务仅 8.7% 步骤正确、无计划完成，两者配合则步骤正确率 75.1%、完整完成 34.0% 的计划，为 IFM 测试模型中最高。
正文 · 原文
MBZUAI's Institute of Foundation Models (IFM) just released PAN 2, an open foundation world model for physical intelligence.
It's built towards simulative reasoning: letting an agent play out what happens before it acts.
It works with two kinds of reasoning, each with its own job:
Conceptual: an LLM works out what happens, when, and how the camera moves, then writes it down as text.
Perceptual: a 29B diffusion model, trained from scratch, turns that text into what you see.
Take the LLM out, and multi-step tasks fall apart: 8.7% of steps right, no plan finished. Getting the order of actions right is the LLM's job.
With both, PAN 2 gets 75.1% of steps right and finishes 34.0% of plans in full, the highest among the models IFM tested. Every step has to hold for a plan to work.
More details in the technical blog:
[1/1]
来源：Rohan Paul · x.com
来源：RadarAI · aihot.news