← Search

Kushal Jain

2 accepted papers

2025

First-Step Advantage: Importance of Starting Right in Multi-Step Math Reasoning

ACL 2025finding

Language models can solve complex reasoning tasks better by learning to generate rationales for their predictions. Often these models know how to solve a task but their auto-regressive decoding nature leads to incorrect results if started incorrectly. We observe that smaller models in particular, wh…

Cited by 0SourcePDFScholar
2022

Learning to Drop Out: An Adversarial Approach to Training Sequence VAEs

NeurIPS 2022accept

In principle, applying variational autoencoders (VAEs) to sequential data offers a method for controlled sequence generation, manipulation, and structured representation learning. However, training sequence VAEs is challenging: autoregressive decoders can often explain the data without utilizing the…

Cited by 2SourcePDFScholar