Shubhendu Trivedi
4 papers in the PaperMetrix corpus
Papers by this author
-
Capacity of Group-invariant Linear Readouts from Equivariant Representations: How Many Objects can be Linearly Classified Under All Possible Views?
2021 · arXiv (Cornell University)
Equivariance has emerged as a desirable property of representations of objects subject to identity-preserving transformations that constitute a group, such as translations and rotations. However, the expressivity of a representation constrained by group equivariance is …
-
Taking a Step Back with KCal: Multi-Class Kernel-Based Calibration for Deep Neural Networks
2022 · arXiv (Cornell University)
Deep neural network (DNN) classifiers are often overconfident, producing miscalibrated class probabilities. In high-risk applications like healthcare, practitioners require $\textit{fully calibrated}$ probability predictions for decision-making. That is, conditioned on the prediction $\textit{vector}$, $\textit{every}$ class' probability …
-
Position Paper: Generalized grammar rules and structure-based generalization beyond classical equivariance for lexical tasks and transduction
2024 · arXiv (Cornell University)
Compositional generalization is one of the main properties which differentiates lexical learning in humans from state-of-art neural networks. We propose a general framework for building models that can generalize compositionally using the concept of Generalized …
-
Watermarking Degrades Alignment in Language Models: Analysis and Mitigation
2025 · arXiv (Cornell University)
Watermarking has become a practical tool for tracing language model outputs, but it modifies token probabilities at inference time, which were carefully tuned by alignment training. This creates a tension: how do watermark-induced shifts interact …