13 citations · 24 across the 20 of their papers we have counts for
7 papers · 1 filter
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…
Cylindrical Geodesic Flow Matching for Quasiperiodic Physiological Signal Transformation
Onur Selim Kilic, Afra Nawar, Cem Okan Yaldiz +6
Paired translation between quasiperiodic physiological waveforms (i.e., recovering a target oscillatory signal from the source) is central to the interpretation of cardiovascular s…
Learning Task-Specific Antibody Representations via Function-Aware Masking
Ayan Goel, Thomas A. Walton, Amirali Aghazadeh
Antibody-specific language models pretrained via masked language modeling (MLM) learn representations that are critical for downstream sequence design and property prediction tasks…
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…
On the Error-Correcting Effects of Stochasticity in Discrete Diffusion
William Yuan, Sungwon Jeong, Amirali Aghazadeh
Discrete diffusion models achieve strong performance in text and image generation, but their inference remains slow and must inherently balance sampling efficiency and sample quali…
Structure-Aware Masking for Protein Representation Learning
Thomas Walton, Ayan Goel, Amirali Aghazadeh
Masked language modeling (MLM) is the standard objective for training protein language models, typically implemented by randomly masking individual residues at a fixed rate (e.g.,…
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…