Papers by Kavya Srinet
CraftAssist Instruction Parsing: Semantic Parsing for a Voxel-World Assistant (2020.acl-main)
Copied to clipboard
| Challenge: | Existing datasets for semantic parsing are limited due to the wide variety of robot setups and proprietary nature of personal assistants. |
| Approach: | They propose a semantic parsing dataset for Minecraft's voxel-based crafting game . they propose to use 7K human utterances and their corresponding parses to execute them in game if proper world state is provided . |
| Outcome: | The proposed dataset can be used to analyze human-bot interactions in the game Minecraft. |
AnyMAL: An Efficient and Scalable Any-Modality Augmented Language Model (2024.emnlp-industry)
Copied to clipboard
Seungwhan Moon, Andrea Madotto, Zhaojiang Lin, Tushar Nagarajan, Matt Smith, Shashank Jain, Chun-Fu Yeh, Prakash Murugesan, Peyman Heidari, Yue Liu, Kavya Srinet, Babak Damavandi, Anuj Kumar
| Challenge: | Prior work on LLMs focused on models that combine text and one other modality, such as image encoders or proprietary models that are not open sourced. |
| Approach: | They propose a unified model that reasons over diverse input modality signals and generates textual responses. |
| Outcome: | The proposed model performs better on multimodal tasks than industry-leading models . |