Senior Applied Scientist @Microsoft #OAR | PhD @nlp_usc | X-@GoogleDeepMind @allen_ai @AmazonScience @UCLA | Common Ground Reasoning for Communicative Agents
Bellevue, WA
Joined July 2011
- Tweets386
- Following911
- Followers2.7K
- Likes2.5K
Pei Zhou retweeted
Our paper has been accepted to EMNLP 2026 🎉
LLM-simulated conversations are increasingly used to model human social behavior, from social media prototyping to replacing human studies in social science.
But can LLMs truly simulate human group behavior?
arxiv.org/abs/2603.17094
Pei Zhou retweeted
Excited to share our new work on Reinforcing Human Behavior Simulation via Verbal Feedback.
Can human simulators learn from feedback, not just rewards?
Most RL for LLMs turns feedback into a single score. But human behavior is rarely just right or wrong. It is social, contextual, subjective, and multi-dimensional.
A score can tell the model what is better. Verbal feedback can tell it why.
Meet DITTO + SOUL.
Paper: arxiv.org/abs/2605.20506
Code: github.com/sunnweiwei/OdysSi…
Model: huggingface.co/sunweiwei/Dit…
Pei Zhou retweeted
Thrilled to announce that our paper “WildFeedback: Aligning LLMs with In-situ User Interactions and Feedback” has been accepted to ACL 2026!
We turn real-world user interactions into powerful alignment signals, pushing LLMs beyond static datasets toward learning from the wild.
Pei Zhou retweeted
[1/6] Can AI fix office feuds humans can’t? 🤝 Check out our recent paper accepted at ACL Findings — ProMediate, the first testbed for evaluating proactive AI mediators in complex, multi-party negotiations. Our evaluations include socio-cognitive assessment and dynamic group outcome tracking.
Pei Zhou retweeted
A lot of useful training data can't be shared due to privacy. How do we create synthetic training data without data owners ever sharing their content?
🚀 Introducing 𝐃𝐏-𝐑𝐅𝐓: using RL to train LLMs to generate high-fidelity domain data without seeing a single private sample.
Pei Zhou retweeted
For decades, we’ve trained AI to chase rewards. But humans don’t just optimize outcomes. We experience, reflect, then learn.
Can AI do the same?
Introducing 𝐄𝐱𝐩𝐞𝐫𝐢𝐞𝐧𝐭𝐢𝐚𝐥 𝐑𝐞𝐢𝐧𝐟𝐨𝐫𝐜𝐞𝐦𝐞𝐧𝐭 𝐋𝐞𝐚𝐫𝐧𝐢𝐧𝐠, a step toward AI that truly learn from experience.
Send your most proud open source projects our way, MLEs! Pretty sure this is an extremely exciting opportunity where you’ll be diving into solving impactful challenges with cutting edge science and research at the core.
We (Microsoft's Office of Applied Research) have a few openings for exceptional Research Engineers / MLEs to train, test, and scale the next-gen enterprise agentic systems to millions of copilot users. Apply today if you are up for the task!
jobs.careers.microsoft.com/g…
Pei Zhou retweeted
I couldn’t make it to #ACL2025, but excited to share our paper GenTool from @MSFTResearch and @EdinburghUni!
aclanthology.org/2025.findin…
We introduce GenTool: a training framework that simulates zero-to-one and weak-to-strong tool transitions to boost tool generalization in LLMs.
Having thoughts on how to build the future of human-agent group collaboration and can’t wait to enhance current frontier model’s social/communciation intelligence?
Join us🔻! There’re lots of fun chats to be had 💬😎
Pei Zhou retweeted
Heading to #NAACL2025 w/ @peizNLP @soshsihao We are hiring full-time scientists on LLM post training, long-context reasoning, agents, and reinforcement finetuning. Please reach out if you are interested in chatting at the conference!
Pei Zhou retweeted
Internship alert! We have an immediate part-time research intern opening at Microsoft’s Office of Applied Research to improve LLM reasoning. Please reach out if you or your students are interested!
Pei Zhou retweeted
Many @Microsoft Office of Applied Research #OAR members will attend @NeurIPSConf this week: @ylongqi @BahaarehS @peizNLP @sharma_ashish_2 @soshsihao @bhecht & myself. We are hiring (both spring & summer) research interns, FTEs and postdocs. Please reach out if you're interested!
Pei Zhou retweeted
Friends and colleagues! I'm on the academic job market in Fall 24/Spring 25.
My research intersects NLP, IR, and HCI and I develop interactive and personalized models to aid workflows where knowledge workers find, consume, and produce information. Please help spread the word! 🧵
ALT I'm interested in assisting knowledge workflows where knowledge workers find, consume, and produce information. This graphic shows how i see my work laid out.
A bit late to the #EMNLP2024 party but hyped to talk to folks tmr abt anything from complex real-world reasoning, simulation for generalization, interactive learning to (hiring links below!!) Office of Applied Research and best bars in Miami 😋
Ph.D. research intern (Spring and Summer): jobs.careers.microsoft.com/g…
FTE: jobs.careers.microsoft.com/g…
Catch @soshsihao and me for more info!!
Join @_jennhu 's lab doing awesome cool research at CogSci x AI✨
I'd apply if time rewinds :)
I'm recruiting PhD students + postdocs for my lab, coming to @JohnsHopkins in Fall 2025!
Our brand new lab is at the intersection of cognitive science and AI, using computational + behavioral methods to understand how language works in minds and machines.
Details below! (1/4)
Pei Zhou retweeted
Life update: I defended my Ph.D. thesis and have joined @Microsoft's Office of Applied Research (OAR)!
One big takeaway from my Ph.D study is that -- research is all about translating ideas into impacts. I feel blessed to work with talented researchers who share the same values!
🚨 Hiring Alert! 🚨
Heading to #COLM in Philly? The Office of Applied Research is hiring interns and full-time researchers! Join us to work on cutting-edge projects like interactive learning, LLM reasoning, synthetic data, personalization, human-AI collaboration, and [INJECT YOUR IDEA]!!
DM us here or connect via Whova to grab coffee! 🍁☕️
Meet @Microsoft Office of Applied Research at @COLM_conf: @peizNLP @mengtingwan @sharma_ashish_2 @soshsihao @MSheshera and myself. We are hiring interns, postdocs, FTEs to shape and redefine the future of GenAI, M365 Copilot and productivity. Please reach out!