Amish Sethi — accepted AI-conference papers

2025

DOLPHIN: A Programmable Framework for Scalable Neurosymbolic Learning

Aaditya Naik, Jason Liu, Claire Wang, Amish Sethi, Saikat Dutta, Mayur Naik +1

ICML 2025poster

Neurosymbolic learning enables the integration of symbolic reasoning with deep learning but faces significant challenges in scaling to complex symbolic programs, large datasets, or both. We introduce DOLPHIN, a framework that tackles these challenges by supporting neurosymbolic programs in Python, e…

Cited by 1 Source ↗PDF ↗code ↗Scholar ↗

2025

ESCA: Contextualizing Embodied Agents via Scene-Graph Generation

Jiani Huang, Amish Sethi, Matthew Kuo, Mayank Keoliya, Neelay Velingker, JungHo Jung +3

NeurIPS 2025spotlight

Multi-modal large language models (MLLMs) are making rapid progress toward general-purpose embodied agents. However, existing MLLMs do not reliably capture fine-grained links between low-level visual features and high-level textual semantics, leading to weak grounding and inaccurate perception. To o…

Cited by 0 Source ↗code ↗Scholar ↗