collaborators

5 papers

cs.CL2026

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…

cs.CV2026

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…

cs.LG2026

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…

cs.LG2026

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…

cs.CL2025

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,…