Papers by Nalin Gupta
Generating Contextual Images for Long-Form Text (2024.lrec-main)
Copied to clipboard
| Challenge: | Recent advances in Text-to-Image models require short prompts that describe both the content and style of the target image. |
| Approach: | They propose to use Large Language Models (LLMs) and Text-to-Image Models to synthesize relevant visual imagery from generic long-form text. |
| Outcome: | The proposed models can generate high-quality images from short prompts that describe both the content and style of the target image. |
Multimodal Context Carryover (2022.emnlp-industry)
Copied to clipboard
Prashan Wanigasekara, Nalin Gupta, Fan Yang, Emre Barut, Zeynab Raeesy, Kechen Qin, Stephen Rawls, Xinyue Liu, Chengwei Su, Spurthi Sandiri
| Challenge: | Existing voice-only dialogue systems lack multimodality support, which can lead to costly system redesigns. |
| Approach: | They propose to augment existing voice-only dialogue systems with additional multimodal components to facilitate quick delivery of visual modality support with minimal changes. |
| Outcome: | The proposed framework improves visual modality support with minimal changes on an in-house multi-modal visual navigation data set. |