19 citations · 52 across the 12 of their papers we have counts for
12 papers
ReSAE: Residualized Sparse Autoencoders for Multi-Layer Transformer Interventions
Prathyush Poduval, Calvin Yeung, Neel Desai +1
Sparse autoencoders are usually trained one layer at a time, even though transformer residual stream activations are strongly coupled across depth. This creates a practical problem…
Residualized Temporal Sparse Autoencoders for Interpreting Diffusion Models
Calvin Yeung, Prathyush Poduval, Ali Zakeri +2
Text-to-image diffusion models generate images by iterative denoising, so their internal layers produce trajectories of activations rather than single static representations. Spars…
Vestigial pairing from fluctuating magnetism and triplet superconductivity
Yanek Verghis, Denis Sedov, Jakob Weßling +2
We study the finite-temperature vestigial superconducting phases of a two-dimensional system of fluctuating spin-triplet pairing and spin magnetism. Denoting the respective primary…
Enabling Group Fairness in Graph Unlearning via Bi-level Debiasing
Yezi Liu, Prathyush Poduval, Wenjun Huang +3
Graph unlearning is a crucial approach for protecting user privacy by erasing the influence of user data on trained graph models. Recent developments in graph unlearning methods ha…
Explainable Differential Privacy-Hyperdimensional Computing for Balancing Privacy and Transparency in Additive Manufacturing Monitoring
Fardin Jalil Piran, Prathyush P. Poduval, Hamza Errahmouni Barkam +2
Machine Learning (ML) models integrated with in-situ sensing offer transformative solutions for defect detection in Additive Manufacturing (AM), but this integration brings critica…
Hyperdimensional Quantum Factorization
Prathyush Poduval, Zhuowen Zou, Alvaro Velasquez +1
This paper presents a quantum algorithm for efficiently decoding hypervectors, a crucial process in extracting atomic elements from hypervectors - an essential task in Hyperdimensi…
Self-Attention Based Semantic Decomposition in Vector Symbolic Architectures
Calvin Yeung, Prathyush Poduval, Mohsen Imani
Vector Symbolic Architectures (VSAs) have emerged as a novel framework for enabling interpretable machine learning algorithms equipped with the ability to reason and explain their…
Perfectly localized Majorana corner modes in fermionic lattices
Prathyush P. Poduval, Thomas L. Schmidt, Andreas Haller
Focusing on examples of Majorana zero modes on the corners of a two-dimensional lattice, we introduce a method to find parameter regions where the Majorana modes are perfectly loca…
Apparent Kondo effect in Moiré TMD bilayers: Heavy fermions or disorder?
Prathyush P. Poduval, Katharina Laubscher, Sankar Das Sarma
A recent work by Zhao et al. [1] reports the realization of a synthetic Kondo lattice in a gate-tunable Moiré TMD bilayer system. The observation of a Kondo lattice is supported by…
Anderson localization in doped semiconductors
Prathyush P. Poduval, Sankar Das Sarma
We theoretically consider the problem of doping induced insulator to metal transition in bulk semiconductors by obtaining the transition density as a function of compensation, assu…
Vestigial singlet pairing in a fluctuating magnetic triplet superconductor: Applications to graphene moiré systems
Prathyush P. Poduval, Mathias S. Scheurer
Motivated by the phenomenology of graphene moiré superlattices, we study a 2D model with strong tendencies towards both magnetism and triplet superconductivity. Individually, their…
Subgap two-particle spectral weight in disordered -wave superconductors: Insights from mode coupling approach
Prathyush P. Poduval, Abhisek Samanta, Prashant Gupta +2
We study the two-particle spectral functions and collective modes of weakly disordered superconductors using a disordered attractive Hubbard model on square lattice. We show that t…