Amit Kumar Kundu — accepted AI-conference papers

2026

A Bayesian Nonparametric Framework For Learning Disentangled Representations

Vaishnavi S Patil, Siddhi Patil, Matthew Evanusa, Amit Kumar Kundu, Cornelia Fermuller, Joseph JaJa

ICLR 2026poster

Disentangled representation learning aims to identify and organize the underlying sources of variation in observed data. However, learning disentangled representations without any additional supervision necessitates inductive biases to solve the fundamental identifiability problem of uniquely recove…

Cited by 0 Source ↗Scholar ↗

2026

Boosting Open Set Recognition Performance through Modulated Representation Learning

Amit Kumar Kundu, Vaishnavi S Patil, Joseph JaJa

ICLR 2026poster

The open set recognition (OSR) problem aims to identify test samples from novel semantic classes that are not part of the training classes, a task that is crucial in many practical scenarios. However, the existing OSR methods use a constant scaling factor (the temperature) to the logits before apply…

Cited by 0 Source ↗Scholar ↗