papers

Publications (8)

cs.LG2023

Measuring Self-Supervised Representation Quality for Downstream Classification using Discriminative Features

Neha Kalibhat, Kanika Narang, Hamed Firooz +2

Self-supervised learning (SSL) has shown impressive results in downstream classification tasks. However, there is limited work in understanding their failure modes and interpreting…

cs.CV2025

Understanding the Effect of using Semantically Meaningful Tokens for Visual Representation Learning

Neha Kalibhat, Priyatham Kattakinda, Sumit Nawathe +5

Vision transformers have established a precedent of patchifying images into uniformly-sized chunks before processing. We hypothesize that this design choice may limit models in lea…

cs.CV2026

Visual prompt engineering for video models

Robert Geirhos, Yuxuan Li, Thaddäus Wiedemer +7

In the age of foundation models, a model is only as good as its prompt. For this reason, prompt engineering has become an essential technique for improving language model performan…

cs.CV2023

Adapting Self-Supervised Representations to Multi-Domain Setups

Neha Kalibhat, Sam Sharpe, Jeremy Goodsitt +2

Current state-of-the-art self-supervised approaches, are effective when trained on individual domains but show limited generalization on unseen domains. We observe that these model…

cs.LG2024

Augmentations vs Algorithms: What Works in Self-Supervised Learning

Warren Morningstar, Alex Bijamov, Chris Duvarney +8

We study the relative effects of data augmentations, pretraining algorithms, and model architectures in Self-Supervised Learning (SSL). While the recent literature in this space le…

cs.CV2023

Identifying Interpretable Subspaces in Image Representations

Neha Kalibhat, Shweta Bhardwaj, Bayan Bruss +3

We propose Automatic Feature Explanation using Contrasting Concepts (FALCON), an interpretability framework to explain features of image representations. For a target feature, FALC…

cs.LG2026

Interpreting and Controlling Model Behavior via Constitutions for Atomic Concept Edits

Neha Kalibhat, Zi Wang, Prasoon Bajpai +4

We introduce a black-box interpretability framework that learns a verifiable constitution: a natural language summary of how changes to a prompt affect a model's specific behavior,…

cs.CV2023

Disentangling the Effects of Data Augmentation and Format Transform in Self-Supervised Learning of Image Representations

Neha Kalibhat, Warren Morningstar, Alex Bijamov +3

Self-Supervised Learning (SSL) enables training performant models using limited labeled data. One of the pillars underlying vision SSL is the use of data augmentations/perturbation…