Papers by Aishwarya Padmakumar
ALFRED-L: Investigating the Role of Language for Action Learning in Interactive Visual Environments (2022.emnlp-main)
Copied to clipboard
Arjun Akula, Spandana Gella, Aishwarya Padmakumar, Mahdi Namazifar, Mohit Bansal, Jesse Thomason, Dilek Hakkani-Tur
| Challenge: | Embodied Vision and Language Task Completion requires an embodied agent to interpret natural language instructions and egocentric visual observations to navigate through and interact with environments. |
| Approach: | They propose to use ALFRED to test whether models can adapt to tasks not seen during training that require the same types of language understanding as ALFred. |
| Outcome: | The proposed model can adapt to tasks that require the same types of language understanding as ALFRED-L. |
Learning a Policy for Opportunistic Active Learning (D18-1)
Copied to clipboard
| Challenge: | Prior work has shown that opportunistic active learning can be used to improve grounding of natural language descriptions in interactive object retrieval tasks. |
| Approach: | They propose to use active learning to constrain possible queries during interactions to improve grounding of natural language descriptions in an interactive object retrieval task. |
| Outcome: | The proposed policy trades off task completion with model improvement that would benefit future tasks while lowering the cost of annotation without sacrificing model performance. |
Multimodal Embodied Plan Prediction Augmented with Synthetic Embodied Dialogue (2023.emnlp-main)
Copied to clipboard
| Challenge: | Embodied task completion requires an agent to predict environment actions to complete tasks based on natural language instructions and egocentric visual observations. |
| Approach: | They propose a method to generate human-human dialogues and use them as training data for plan prediction. |
| Outcome: | The proposed model outperforms language-only models but falls short of oracle plans. |
AEGIS2.0: A Diverse AI Safety Dataset and Risks Taxonomy for Alignment of LLM Guardrails (2025.naacl-long)
Copied to clipboard
Shaona Ghosh, Prasoon Varshney, Makesh Narsimhan Sreedhar, Aishwarya Padmakumar, Traian Rebedea, Jibin Rajan Varghese, Christopher Parisien
| Challenge: | Existing safety-related content safety models are not well-suited for commercial use. |
| Approach: | They propose a taxonomy that can be used to categorize safety risks . it combines human annotations with a multi-LLM "jury" system to assess safety . they plan to open-source Aegis2.0 data and models to aid in safety guardrailing . |
| Outcome: | The proposed taxonomy can be used to assess the safety of human-LLM interactions . it can be trained on large, non-commercial datasets and is open-source . |
KILM: Knowledge Injection into Encoder-Decoder Language Models (2023.acl-long)
Copied to clipboard
| Challenge: | Large pre-trained language models retain implicit knowledge within their parameters, but are susceptible to memorizing the pretraining corpora rather than capturing the knowledge within them. |
| Approach: | They propose to inject entity-related knowledge into encoder-decoder PLMs via a generative knowledge infilling objective through continued pre-training. |
| Outcome: | The proposed approach outperforms state-of-the-art models on general NLU and NLG tasks while maintaining their original performance. |