13 citations · 24 across the 20 of their papers we have counts for
22 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…
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…
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…
SpecMER: Fast Protein Generation with K-mer Guided Speculative Decoding
Thomas Walton, Darin Tsui, Aryan Musharaf +1
Autoregressive models have transformed protein engineering by enabling the generation of novel protein sequences beyond those found in nature. However, their sequential inference i…
Sparse Autoencoders for Low- Protein Function Prediction and Design
Darin Tsui, Kunal Talreja, Amirali Aghazadeh
Predicting protein function from amino acid sequence remains a central challenge in data-scarce (low-) regimes, limiting machine learning-guided protein design when only small a…
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…
Efficient Algorithm for Sparse Fourier Transform of Generalized -ary Functions
Darin Tsui, Kunal Talreja, Amirali Aghazadeh
Computing the Fourier transform of a -ary function , which maps -ary sequences to real numbers, is an important problem in mathemati…
SHAP zero Explains Biological Sequence Models with Near-zero Marginal Cost for Future Queries
Darin Tsui, Aryan Musharaf, Yigit Efe Erginbas +2
The growing adoption of machine learning models for biological sequences has intensified the need for interpretable predictions, with Shapley values emerging as a theoretically gro…
On Recovering Higher-order Interactions from Protein Language Models
Darin Tsui, Amirali Aghazadeh
Protein language models leverage evolutionary information to perform state-of-the-art 3D structure and zero-shot variant prediction. Yet, extracting and explaining all the mutation…
ProtiGeno: a prokaryotic short gene finder using protein language models
Tony Tu, Gautham Krishna, Amirali Aghazadeh
Prokaryotic gene prediction plays an important role in understanding the biology of organisms and their function with applications in medicine and biotechnology. Although the curre…
Efficiently Computing Sparse Fourier Transforms of -ary Functions
Yigit Efe Erginbas, Justin Singh Kang, Amirali Aghazadeh +1
Fourier transformations of pseudo-Boolean functions are popular tools for analyzing functions of binary sequences. Real-world functions often have structures that manifest in a spa…
Spectral Regularization Allows Data-frugal Learning over Combinatorial Spaces
Amirali Aghazadeh, Nived Rajaraman, Tony Tu +1
Data-driven machine learning models are being increasingly employed in several important inference problems in biology, chemistry, and physics which require learning over combinato…
Group-Structured Adversarial Training
Farzan Farnia, Amirali Aghazadeh, James Zou +1
Robust training methods against perturbations to the input data have received great attention in the machine learning literature. A standard approach in this direction is adversari…
BEAR: Sketching BFGS Algorithm for Ultra-High Dimensional Feature Selection in Sublinear Memory
Amirali Aghazadeh, Vipul Gupta, Alex DeWeese +2
We consider feature selection for applications in machine learning where the dimensionality of the data is so large that it exceeds the working memory of the (local) computing mach…
MISSION: Ultra Large-Scale Feature Selection using Count-Sketches
Amirali Aghazadeh, Ryan Spring, Daniel LeJeune +3
Feature selection is an important challenge in machine learning. It plays a crucial role in the explainability of machine-driven decisions that are rapidly permeating throughout mo…
Insense: Incoherent Sensor Selection for Sparse Signals
Amirali Aghazadeh, Mohammad Golbabaee, Andrew S. Lan +1
Sensor selection refers to the problem of intelligently selecting a small subset of a collection of available sensors to reduce the sensing cost while preserving signal acquisition…
Near-Isometric Binary Hashing for Large-scale Datasets
Amirali Aghazadeh, Andrew Lan, Anshumali Shrivastava +1
We develop a scalable algorithm to learn binary hash codes for indexing large-scale datasets. Near-isometric binary hashing (NIBH) is a data-dependent hashing scheme that quantizes…