
Ph.D.@S3DatCMU | Trustworthy and Safe AI, LLM & Agent
Joined October 2022
- Tweets17
- Following105
- Followers45
- Likes105
🚀 Excited to present our work at #ASE2026 next week in Munich! 🇩🇪
“Safeguarding LLM Agents from Misalignment through Provenance Analysis”
🗓️ Tue, Oct 13, 11:30
📍 Forum 2
🔗 Artifact: github.com/cmu-soda/Provenan…
📄 Preprint: arxiv.org/abs/2607.01236
#LLMAgents #AISafety #SE4AI
If you’re working on making trustworthiness engineerable for LLM-based systems, this workshop may be a good opportunity!
📣 Call for Papers: #LLMTrust2026 @FSEconf
Engineering trustworthy LLM systems + responsible LLM use in SE (evidence, tests, metrics, audits, artifacts).
🗓️ Deadline (AoE): Feb 12, 2026
llmtrust2026.github.io/
Building trustworthy LLM systems is a software engineering problem: testing & validation, RAG/agents, prompt injection & red-teaming, monitoring/observability, provenance & governance.
Submit to LLMTrust @ #FSE2026 ➜ llmtrust2026.github.io/ #LLMTrust #LLM
🚀 Super cool research by Parv on applying constrained decoding to RFM!
Yining She retweeted
Super proud to share our new RSS 2025 work! I have been working on this with my collaborators for a while now and the sheer complexity of deploying CBFs in the field with perceptual inputs has been so exciting! Come chat with us about it at RSS!
🚀 Excited to present our work at #ICSE2025 next week in Ottawa!
FairSense: Long-term Fairness Analysis of ML-enabled Systems
🗓️Wed, April 30th, 17:00-17:15
📍SE for AI with Security Session @ Room 210
📄Preprint: arxiv.org/abs/2501.01665
Let’s connect and chat!
Yining She retweeted
Thrilled to share our work on accelerating neurosymbolic methods for robotics!
STLCG++ encodes logical constraints in a computational graph, achieving 100-1000× faster quantitative evaluation—enabling real-time symbolic reasoning for traj opt, policy learning, & more.
🧵 [1/n]
Thrilled to see the amazing work my lab mate @Parvkpr has done at @ScaFoAI !
We've opened the waitlist for General Robot Intelligence Development (GRID) Beta! Accelerate robotics dev with our open, free & cloud-based IDE. Zero setup needed. Develop & deploy advanced skills with foundation models and rapid prototyping
🔗: grid.scaledfoundations.ai/
🧵(1/6)
Yining She retweeted
My postdoc, @sumonbis, is on the job market this year! He's done lots of fantastic work in SE4ML, with a focus on improving the fairness of ML-driven systems. If your department is hiring this year, I'd strongly recommend inviting him for a visit!
I am on the academic job market this year ‼️
I am a #software engineering researcher focusing on the SE4AI area, especially designing fairness and safety of #ML models and systems.
Feel free to reach out.
sumonbis.github.io
Yining She retweeted
🎓Applying for @SCSatCMU's PhD program, and seeking feedback as an underrepresented applicant?
This is an excellent chance to get quality feedback from CMU students, who've been through the same process! Plz apply by Sep 30: cs.cmu.edu/~gasp
📢 Are you an underrepresented applicant for @SCSatCMU PhD program? We're here to help!
@daye_nam and I are leading SCS GASP. We match PhD applicants with student mentors for application feedback.
To be considered, please complete the form by Sep 30: cs.cmu.edu/~gasp
Yining She retweeted
Great write up from @willknight in @WIRED about @sarahbmyers, @mer__edith and my new piece:
➡️The rhetoric of "open" AI is misleading. Why? In short, because AI is controlled by Big Tech.
wired.com/story/the-myth-of-…
Yining She retweeted
The Statement of Purpose may be the toughest part of the #gradschool application. Join #SoftwareEngineering PhD director @p0nk to talk about your SOP during his Nov 15 Grad School Q&A session on Zoom (3-4PM) Learn more + Register (required) at s3d.cmu.edu/gradzoom/index.h…

















