中文 Apply now

PhAI Labs · Technology

Technology for scientific discovery

PhAI Labs' technical work turns on one question: how can AI systems take part in real scientific discovery. DFM is the research paradigm we propose for it; its technical report and the works released independently since are collected at the end of this page.

Jump to papers

  1. Scientific question
  2. Model training
  3. Tool use
  4. Real experiments
  5. External evidence
  6. Capability growth

DFM · Discovery Foundation Models

A research paradigm around Discovery Intelligence

DFM (Discovery Foundation Models) is neither a single model nor a software framework that forces every system through one pipeline. It is the research paradigm, capability definition and system organisation that PhAI Labs proposes around Discovery Intelligence: through formal definitions, process diagrams, system instances and real scientific cases, it turns “discovery” from a vague notion into a capability of model systems that can be learned, executed and evaluated.

Swipe to see the whole diagram

DFM technical report ↗GitHub ↗

Papers·6 in total

Technical reports and papers

The public research record of PhAI Labs: technical reports, preprints and conference papers.

  1. Turns “discovery” into a capability of model systems that can be learned, executed and evaluated.

    Discovery Foundation Models: Toward Open-Ended Discovery Intelligence

    Ling Yang, Zhenfei Yin, Yingcheng Wu

    PhAI Labs Technical Report

  2. An interactive Scientific Agent: recursive self-improvement in real research interaction, exploring Recursive-in-Recursive Self-Improvement (RSI in RSI).

    ScienceBuddy: Recursive-in-Recursive Self-Improvement for Interactive Scientific Agents

    Shuhan Xue*, Jianyuan Zhong*, Ziyuan Nan*, Wenbin Li, Zhaochen Yu, Jinchao Ding, Qiang Gao, Pengyu Zhan, Yuntong Zhang, Tian Cheng, Zhenfei Yin, Yingcheng Wu, Ling Yang

    PhAI Labs Technical Report

  3. Infrastructure for scientific experience: real scientific code, tasks, environments and reinforcement-learning training.

    ScienceIDE: Turning World's Scientific Codebase into Agent Learnable Environments

    Hejia Geng*, Zesen Huang*, Haoyang Li, Wenbin Li, Koutian Wu, Zihan Zhou, Yuanbo Pang, Weihao Liu, Zigong Xu, Zhiping Li, Zongzheng Zhang, Chuanfei Dong, Jiankai Sun, Tianzhe Zheng, Fengyu Xie, Yue Ma, Yueheng Shi, Junkai Wang, Tong Xie, Zonglin Di, Xianrong Liu, Qucheng Gao, Yimin Liu, Jiaming Pan, Sheng Huang, Xiao-Han Ma, Lanqing Yuan, Zhenlin Zhu, Ziang Liu, Ziyang Xu, Kangkai Liang, Jiayi Xian, Zehong Zhao, Taigao Ma, Fuming Chang, Yuanzhe Hu, Liuwei Xu, Xianzhe Tang, Jingxu Xie, Peijin Zhang, Qiang Gao, Chengyi Xing, Zhe Zhao, Xi Wang, Leo Wang, Fang Wu, Yaopeng Xing, Xing Meng, Zhenfei Yin, Yingcheng Wu, Ling Yang

    PhAI Labs Technical Report

  4. Cross-domain state prediction, intervention simulation and scientific diagnosis.

    JEPA-Anything: Learning Predictive Models across Different Worlds

    Taoyong Cui, Zhongyao Wang, Xinyue Xu, Weiyang Liu, Zhaochen Yu, Yuying Zhang, Qiang Gao, Mengyue Yang, Wanli Ouyang, Pheng Ann Heng, Yingcheng Wu, Zhenfei Yin, Ling Yang

    PhAI Labs Technical Report

  5. Built on JEPA-Anything: world-model predictions pick which candidates to test for real; feedback improves the policy or workflow, and the world model once its predictions prove unreliable; only updates that pass their checks are kept.

    RSI-Anything: Unlocking Recursive Self-Improvement with World Models

    Taoyong Cui, Pinxian Zeng, Wanghan Xu, Hao Xiao, Shuhan Xue, Qiang Gao, Wanli Ouyang, Pheng Ann Heng, Zhenfei Yin, Yingcheng Wu, Ling Yang

    PhAI Labs Technical Report

  6. Multi-agent evolutionary search grows research trees of hypotheses and compiles selected ones into executable tasks; the kept research record trains the model, refines the workflow and is applied to fresh questions.

    DiscoveryRSI: Recursively Learning to Discover Valuable Hypotheses

    Jianyuan Zhong*, Chenwei Wu*, Zhaochen Yu*, Xixian Jiang, Jiajun Fan, Xuewei Li, Hao Xiao, Xilin Dai, Junyang Wang, Jiaru Zou, Zhiqing Cui, Boyuan Zheng, Jing Xiong, Zhen Zhang, Qiang Gao, Michael Morley, Luis Nakayama, Qiang Xu, Liyue Shen, Tao Gui, Leo Anthony Celi, James Zou, Zhenfei Yin, Yingcheng Wu, Ling Yang

    PhAI Labs Technical Report