3 citations · 5 across the 4 of their papers we have counts for
5 papers
How Intervention History Changes AI Agent Sabotage on Subsequent Tasks
Daniel Saeedi, Amirali Aghazadeh
AI control evaluations often reset agents' memory between tasks, although deployed agents may retain records of prior interventions. We ask whether learning that an earlier attack…
Circuit Tracing in Autoregressive Protein Language Models
Darin Tsui, William Deinzer, Daniel Saeedi +1
Protein language models (pLMs) can generate novel protein sequences with properties beyond those observed in nature, yet the mechanisms underlying protein generation remain poorly…
Protein Circuit Tracing via Cross-layer Transcoders
Darin Tsui, Kunal Talreja, Daniel Saeedi +1
Protein language models (pLMs) have emerged as powerful predictors of protein structure and function. However, the computational circuits underlying their predictions remain poorly…
cryoSENSE: Compressive Sensing Enables High-throughput Microscopy with Sparse and Generative Priors on the Protein Cryo-EM Image Manifold
Zain Shabeeb, Daniel Saeedi, Darin Tsui +2
Cryo-electron microscopy (cryo-EM) enables the atomic-resolution visualization of biomolecules; however, modern direct detectors generate data volumes that far exceed the available…
AstroAgents: A Multi-Agent AI for Hypothesis Generation from Mass Spectrometry Data
Daniel Saeedi, Denise Buckner, Jose C. Aponte +1
With upcoming sample return missions across the solar system and the increasing availability of mass spectrometry data, there is an urgent need for methods that analyze such data w…