← Search

Anand Ramachandran

2 accepted papers

2026

Align to Structure: Aligning Large Language Models with Structural Information

AAAI 2026technical

Generating long, coherent text remains a challenge for large language models (LLMs), as they lack hierarchical planning and structured organization in discourse generation. We introduce Structural Alignment, a novel method that aligns LLMs with human-like discourse structures to enhance long-form te

Cited by 7SourcePDFScholar
2019

A recurrent Markov state-space generative model for sequences

AISTATS 2019poster

While the Hidden Markov Model (HMM) is a versatile generative model of sequences capable of performing many exact inferences efficiently, it is not suited for capturing complex long-term structure in the data. Advanced state-space models based on Deep Neural Networks (DNN) overcome this limitation…

Cited by 2SourcePDFScholar