Papers by Ayan Banerjee
NITI: Neural Plan Concretization for Incremental Execution, Bridging and Trigger Inference from Underspecified Human Policies (2026.findings-acl)
Copied to clipboard
| Challenge: | Using NITI, we examine the performance of a safety-critical automated insulin dosing task with minimal contextualization infence overhead. |
| Approach: | They propose a framework that treats large language models as execution-time concretizers of human intent that incrementally executes abstract policies via verifier-grounded interfaces. |
| Outcome: | The proposed framework outperforms one-shot and chain-of-thought baselines on two structurally distinct embodied domains: a world cubing championship 22 Rubik’s Cube scramble and a safety-critical automated insulin dosing task. |
CANDICE: Agentic Causal Disentanglement with Class Conditional Knowledge Integration for Long Tailed Domain Generalization (2026.findings-acl)
Copied to clipboard
| Challenge: | Domain generalization and long-tailed (LT) learning models face two challenges . domain invariance often suppresses class-discriminative signals essential for long-tail recognition. |
| Approach: | They propose a framework that disentangles domain-invariant and class-discriminative features . they evaluate 10 diverse medical imaging datasets spanning four modalities . |
| Outcome: | The proposed framework achieves an average performance improvement of 10.3% across multi-domain and in-domain long-tailed tasks while preserving minority class performance. |
Personalized open world plan generation for safety-critical human centered autonomous systems: A case study on Artificial Pancreas (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Design-time safety guarantees for human-centered autonomous systems often break down in open-world deployment due to uncertain human interaction. |
| Approach: | They propose an LLM-based architecture that automatically generates personalized safety plans . by itself, the LLM fares poorly at producing safe usage plans, but coupling it with a safety verifier enables the discovery of safe plans. |
| Outcome: | The proposed architecture generates personalized safety plans that are safe for open-world use . the proposed architecture fares poorly at producing safe usage plans . |