SCAI-JHU

MindZero-gw-tom-Qwen3-VL-4B-Instruct

Deploy Dedicated

Dedicated Endpoints

Run this model inference on single tenant GPU with unmatched speed and reliability at scale.

Learn more

Container

Run this model inference with full control and performance in your environment.

Learn more

Get help setting up a custom Dedicated Endpoints.

Talk with our engineer to get a quote for reserved GPU instances with discounts.

README

License: apache-2.0

TL;DR

MindZero trains (M)LLMs to perform efficient and robust online mental reasoning without any mental-state annotations. During training, the model is rewarded for generating mental-state hypotheses that maximize the likelihood of observed actions, as estimated by a planner — analogous to model-based ToM reasoning. After training, MindZero internalizes this reasoning into fast single-pass inference.

Evaluation

Table
Base model	Checkpoint	Gridworld-QA
Qwen/Qwen3-VL-4B-Instruct	MindZero-gw-tom-Qwen3-VL-4B-Instruct	95.0
Qwen/Qwen3-VL-8B-Instruct	MindZero-gw-tom-Qwen3-VL-8B-Instruct	92.3

Citation

bibtex
@inproceedings{zhang2026mindzero,
  title     = {MindZero: Learning Online Mental Reasoning With Zero Annotations},
  author    = {Shunchi Zhang and Jin Lu and Chuanyang Jin and Yichao Zhou and Zhining Zhang and Tianmin Shu},
  booktitle = {Proceedings of the 43rd International Conference on Machine Learning (ICML)},
  year      = {2026}
}