7 citations · 16 across the 13 of their papers we have counts for
13 papers
Unsupervised Latent Space Alignment with Hyperspherical Geodesic Matching
Cameron Ryan, Vivek Sivaraman Narayanaswamy, Kowshik Thopalli +1
Independently trained neural networks tend to encode the same data with similar latent geometries. These latent geometries are not directly compatible, yet they can be nearly the s…
The Fragility of Chain-of-Thought Monitoring Across Typologically Diverse Languages
Eric Onyame, Runtao Zhou, Kowshik Thopalli +2
Chain-of-thought (CoT) monitoring has been proposed as a promising safety mechanism for detecting misaligned behavior in large language models. However, its reliability remains lar…
LatentDiff: Scaling Semantic Dataset Comparison to Millions of Images
James Flora, Kowshik Thopalli, Akshay R. Kulkarni +2
We present LatentDiff, a scalable framework for semantic dataset comparison that operates directly in the latent space of pretrained vision encoders. By combining sparse autoencode…
ProtAlign: Contrastive learning paradigm for Sequence and structure alignment
Aditya Ranganath, Hasin Us Sami, Kowshik Thopalli +2
Protein language models often take into consideration the alignment between a protein sequence and its textual description. However, they do not take structural information into co…
Interpretable and Steerable Concept Bottleneck Sparse Autoencoders
Akshay Kulkarni, Tsui-Wei Weng, Vivek Narayanaswamy +3
Sparse autoencoders (SAEs) promise a unified approach for mechanistic interpretability, concept discovery, and model steering in LLMs and LVLMs. However, realizing this potential r…
Visual Exploration of Feature Relationships in Sparse Autoencoders with Curated Concepts
Xinyuan Yan, Shusen Liu, Kowshik Thopalli +1
Sparse autoencoders (SAEs) have emerged as a powerful tool for uncovering interpretable features in large language models (LLMs) through the sparse directions they learn. However,…
Revisiting Deep Subspace Alignment for Unsupervised Domain Adaptation
Kowshik Thopalli, Jayaraman J Thiagarajan, Rushil Anirudh +1
Unsupervised domain adaptation (UDA) aims to transfer and adapt knowledge from a labeled source domain to an unlabeled target domain. Traditionally, subspace-based methods form an…
MaAST: Map Attention with Semantic Transformersfor Efficient Visual Navigation
Zachary Seymour, Kowshik Thopalli, Niluthpol Mithun +3
Visual navigation for autonomous agents is a core task in the fields of computer vision and robotics. Learning-based methods, such as deep reinforcement learning, have the potentia…
Calibrate and Prune: Improving Reliability of Lottery Tickets Through Prediction Calibration
Bindya Venkatesh, Jayaraman J. Thiagarajan, Kowshik Thopalli +1
The hypothesis that sub-network initializations (lottery) exist within the initializations of over-parameterized networks, which when trained in isolation produce highly generaliza…
Invenio: Discovering Hidden Relationships Between Tasks/Domains Using Structured Meta Learning
Sameeksha Katoch, Kowshik Thopalli, Jayaraman J. Thiagarajan +2
Exploiting known semantic relationships between fine-grained tasks is critical to the success of recent model agnostic approaches. These approaches often rely on meta-optimization…
SALT: Subspace Alignment as an Auxiliary Learning Task for Domain Adaptation
Kowshik Thopalli, Jayaraman J. Thiagarajan, Rushil Anirudh +1
Unsupervised domain adaptation aims to transfer and adapt knowledge learned from a labeled source domain to an unlabeled target domain. Key components of unsupervised domain adapta…
Multiple Subspace Alignment Improves Domain Adaptation
Kowshik Thopalli, Rushil Anirudh, Jayaraman J. Thiagarajan +1
We present a novel unsupervised domain adaptation (DA) method for cross-domain visual recognition. Though subspace methods have found success in DA, their performance is often limi…
Perturbation Robust Representations of Topological Persistence Diagrams
Anirudh Som, Kowshik Thopalli, Karthikeyan Natesan Ramamurthy +3
Topological methods for data analysis present opportunities for enforcing certain invariances of broad interest in computer vision, including view-point in activity analysis, artic…