Abby Xu

AI for Science, PM @PhAILabs Building｜Learning｜Exploring

[Abby Xu @abbyxuu]

📑 DFM technical report: https://t.co/SLfTOZNSth

🔗 DFM research roadmap: https://t.co/VSsZisI5YO

🏠 More about PhAI Labs: https://t.co/HrLyfFS0q0

[PhAI Labs @PhAILabs]

Scientific discovery often requires changing the question itself.

Today, PhAI Labs releases the technical report for Discovery Foundation Models (DFM), a research direction for AI systems that can identify valuable unknowns, formulate questions, develop hypotheses, design experiments, and revise their understanding as evidence comes in.

The goal is not just to complete one investigation. What a system learns should carry into the next—as reusable methods, accumulated research experience, and better decisions about what to explore.

The report introduces a reference architecture, the science infrastructure we're developing, and a wet-lab case study.

🔬 Alongside the report, we're opening the DFM Scientist Collaboration Program.

Have a scientific question you'd like to explore with AI? We're inviting scientists, research teams, and experimental platforms to collaborate on meaningful open problems with real opportunities for validation.

🙌 Program details & application:
https://t.co/w4S6OlvKAS

📅 Over the next three days, we'll introduce three related research efforts:
Sep 16 — ScienceBuddy · AI research companion
Sep 17 — ScienceIDE · Scientific integrated development platform
Sep 18 — JEPA-Anything · Cross-domain scientific world models

A research direction we're pursuing with @Charles_Y_Wu @LingYang_PU @zhenfei_yin_yzf

📑 DFM technical report:
https://t.co/nRwgHLSkWv
🔗 DFM research roadmap:
https://t.co/fqYzVlXZYP
🏠 More about PhAI Labs:
https://t.co/ZoGBNWHjki

#PhAILabs #DFM

[Abby Xu @abbyxuu]

If you're a PhD or a researcher, and you use AI for research every single day, you know exactly what I'm talking about!!!

🔗 https://t.co/WArwZB1JBx
💻 https://t.co/ljG0axPO3T

#PhAILabs #AIforScience #AI #sciencebuddy #research

[Abby Xu @abbyxuu]

@Mollyarby14B 😆

[Abby Xu @abbyxuu]

🚀 Meet ScienceBuddy — a totally FREE AI research workspace!

🔗 https://t.co/9peva9bpIT

You can research, design, execute, and verify — all in one place.

And yes, you can use GPT-6! Plus, GPU-accelerated computing and our JEV framework.

👀 Would love for you to give it a try! And seriously, tell me what you think. Good or bad, I want to hear it!!!

#PhAILabs #AIforScience #AI #sciencebuddy #research

[Abby Xu @abbyxuu]

@joeomnomnom 😆😆

[Abby Xu @abbyxuu]

@lialcama3332 Thx!!

[Abby Xu @abbyxuu]

https://t.co/H8B0R6LckF

[Abby Xu @abbyxuu]

717 GitHub ⭐️stars in just 4 days :)

Can we hit 1,000 by the end of this week?
Who's betting YES? 👀

[Abby Xu @abbyxuu]

https://t.co/WTdSxn1d6N

[Abby Xu @abbyxuu]

And a little sneak peek… 👀

We've got a major new research paper coming out next week.

Stay tuned. Can't wait to share it with you all! 🚀

[Abby Xu @abbyxuu]

Been getting a lot of encouraging comments lately. Makes me really happy :)

Huge thanks to everyone who's been following and supporting me and @PhAILabs! 💙

#AI #AIforscience #RSI #science

[Abby Xu @abbyxuu]

Been getting a lot of encouraging comments lately. Makes me really happy :)

Huge thanks to everyone who's been following and supporting me and @PhAILabs! 💙

#AI #AIforscience #RSI #science

[Abby Xu @abbyxuu]

Haha, we'll do our best to prove you right! 🚀

[fomo_waves @DIRTYLILREBEL]

@abbyxuu @PhAILabs Was skeptical about the science push at first but phai might actually pull this off

[Abby Xu @abbyxuu]

https://t.co/I53pz8hxVT

[Abby Xu @abbyxuu]

@PrinceK10366014 no😂, you can take a look at the paper. We also have open-source data, so you can give it a try~

[Abby Xu @abbyxuu]

https://t.co/2D2GStKoC1

[Abby Xu @abbyxuu]

Early start at @PhAILabs today ☀️

Coffee, a fresh mind, and another day building in AI for Science.

Let's get to work! 🔬

#AI #phailabs #RSI #JEAP #AIforScience

[Abby Xu @abbyxuu]

📄 Paper: https://t.co/3aHu8HLxz3
💻 Code: https://t.co/H8B0R6LckF

[Abby Xu @abbyxuu]

@ivanrei45935210 😄

[Abby Xu @abbyxuu]

📄Full Paper: https://t.co/3aHu8HLxz3

💻Full Code: https://t.co/H8B0R6LckF

#RSI #AI4S #AI #JEPA

[Abby Xu @abbyxuu]

1 framework, 4 different domains

💻 Code-repair success: 26.3% → 31.2%, with the coder fixed

🖥️ GUI agent task: 39.4% fewer actions, with higher completion

🔬 Lab-planning scores: 21.80% → 46.01% over five policy versions

🧪 Mean best observed reaction yield: 96.15% vs. 82.16% for Bayesian optimization, under the same 40-experiment budget

[Abby Xu @abbyxuu]

@sseedseed6969 yesss!! lets go ➡️ https://t.co/H8B0R6LckF

[Abby Xu @abbyxuu]

@bugzyfn yep! lets go➡️ https://t.co/VSsZisI5YO

[Abby Xu @abbyxuu]

📑 DFM technical report: https://t.co/SLfTOZNSth

🔗 DFM research roadmap: https://t.co/VSsZisI5YO

🏠 More about PhAI Labs: https://t.co/HrLyfFS0q0

[PhAI Labs @PhAILabs]

Scientific discovery often requires changing the question itself.

Today, PhAI Labs releases the technical report for Discovery Foundation Models (DFM), a research direction for AI systems that can identify valuable unknowns, formulate questions, develop hypotheses, design experiments, and revise their understanding as evidence comes in.

The goal is not just to complete one investigation. What a system learns should carry into the next—as reusable methods, accumulated research experience, and better decisions about what to explore.

The report introduces a reference architecture, the science infrastructure we're developing, and a wet-lab case study.

🔬 Alongside the report, we're opening the DFM Scientist Collaboration Program.

Have a scientific question you'd like to explore with AI? We're inviting scientists, research teams, and experimental platforms to collaborate on meaningful open problems with real opportunities for validation.

🙌 Program details & application:
https://t.co/w4S6OlvKAS

📅 Over the next three days, we'll introduce three related research efforts:
Sep 16 — ScienceBuddy · AI research companion
Sep 17 — ScienceIDE · Scientific integrated development platform
Sep 18 — JEPA-Anything · Cross-domain scientific world models

A research direction we're pursuing with @Charles_Y_Wu @LingYang_PU @zhenfei_yin_yzf

📑 DFM technical report:
https://t.co/nRwgHLSkWv
🔗 DFM research roadmap:
https://t.co/fqYzVlXZYP
🏠 More about PhAI Labs:
https://t.co/ZoGBNWHjki

#PhAILabs #DFM