PhD Student at Georgia Tech ECE | Agentic AI and Mech Interp
Atlanta
Joined April 2024
- Tweets15
- Following319
- Followers28
- Likes240
Danial Saeedi retweeted
Protein fitness landscapes are simpler under evolutionary distributions!
We show that much of the high-order epistasis observed in fitness landscapes is substantially diminished when analyzed under their natural evolutionary distributions. biorxiv.org/content/10.64898… (1/n)
🚀 New preprint: What happens when AI agents investigate the origins of life?
We introduce ASTRA, a multi-agent system that reconstructed 2,850 plausible pathways for amino acid synthesis.
📄 chemrxiv.org/doi/abs/10.2643…
🌐 astraagents.github.io/
At #CVPR2026? Come by ExHall F 508 on Sun, Jun 7, 11:45 AM–1:45 PM MDT to chat about cryoSENSE — using compressive sensing with sparse and diffusion priors to enable higher-throughput cryo-EM while preserving structural resolution.
#CryoEM #ComputationalImaging
Danial Saeedi retweeted
🚨 New paper by my PhD student William Yuan.
Conventional wisdom: stochasticity slows down sampling.
Our result: in discrete diffusion, stochasticity can actually correct errors.
📌 We show this through strong data processing inequalities, proving that increasing stochasticity can contract accumulated sampling errors.
⚡ Inspired by this, we introduce Discrete Churn and Restart Sampling (DCRS) a training-free inference algorithm that leverages controlled stochasticity for error correction.
🔥 Up to 10× faster sampling on benchmarks while maintaining competitive quality.
Paper: arxiv.org/abs/2605.26582
Sharing a thoughtful LessWrong piece by my colleague @darin_tsui on AI as biology’s digital microscope: how mechanistic interpretability can help turn biological AI models from black boxes into tools for discovery:
lesswrong.com/posts/BxziXpLC…
#LessWrong #MechInterp
Danial Saeedi retweeted
Can we learn how protein language models (pLMs) work?👀
As a matter of fact, yes! I'm excited to shared that our paper, "Protein Circuit Tracing via Cross-layer Transcoders", has been accepted into ICML 2026! Check out our findings at protmech.github.io/ (1/n)
Danial Saeedi retweeted
Thrilled to share that cryoSENSE has been accepted to #CVPR2026 🎉. Thanks to the amazing team: @zain_shabeeb, @saeedi_daniel, @darin_tsui, and @amiraliagz
@gatechengineers @GTChBE @GeorgiaTech_ECE
New preprint🚨: cryoSENSE. We show that diffusion models as generative priors, along with sparse priors, can boost electron microscopy data throughput by reconstructing high-resolution cryo-EM images from compressed measurements arxiv.org/abs/2511.12931
Danial Saeedi retweeted
Proud of this work from our lab; moving closer to a mechanistic understanding of protein language models.
Danial Saeedi retweeted
🚨Excited to share ProtoMech: a framework for discovering the computational circuits inside protein language models (pLMs)!
pLMs like ESM2 are powerful, but the computational mechanisms, or circuits, underlying their predictions remain poorly understood. (1/n)
🚀 Our new paper is out in PNAS Nexus!
We introduce LifeTracer, a machine-learning framework that analyzes high-res mass-spectrometry data from meteorites and Earth samples to distinguish abiotic vs biotic organics, helping future sample-return missions search for life.
Paper:
academic.oup.com/pnasnexus/a…
Project website: life-tracer.github.io/
#NASA #Meteorites #OriginOfLife
Danial Saeedi retweeted
New preprint🚨: cryoSENSE. We show that diffusion models as generative priors, along with sparse priors, can boost electron microscopy data throughput by reconstructing high-resolution cryo-EM images from compressed measurements arxiv.org/abs/2511.12931
Danial Saeedi retweeted
It’s here! #Agents4Science recording is now on YouTube!
🏆 3 Best Paper talks
⚡️ 11 Spotlights
🧠 Panel on the future of AI agent-driven science
📚 Lessons + surprises from this first-of-its kind conf
Full analysis of submissions + reviews coming soon! youtube.com/watch?v=7pXqAeed…
Danial Saeedi retweeted
AstroAgents: A Multi-Agent AI for Hypothesis Generation from Mass Spectrometry Data
astrobiology.com/2025/04/ast… #astrobiology #astrochemistry #AI
