Soujanya Poria

A look at the difficulties computers face in visual puzzle solving.

A new method enhances entity classification in complex documents using spatial data.

A study on improving audio outputs from text prompts using preference optimization.

New methods improve Language Model responses to meet user preferences effectively.

A new tool assesses the safety and reliability of language models.

New methods aim to reduce inaccuracies in language models within information retrieval systems.

New framework enhances AI planning by improving visual understanding and reasoning.

Advancements in robot training are making them more adaptable and capable.

A new framework prioritizes safety alongside performance in AI evaluation.

Discover how text can transform into audio with cutting-edge models.