Martin Foltin — accepted AI-conference papers

2026

InfrastructureSentinel: Policy Enforced Guardrails for Secure MCP-driven Infrastructure Agents

Tarun Kumar, Aalap Tripathy, Gayathri Saranathan, Martin Foltin, Suparna Bhattacharya, Scott Hinchley +4

AAAI 2026technical

The proliferation of Model Context Protocol (MCP) servers in enterprise infrastructure management has revolutionized AI-driven automation while introducing critical multi-layered security vulnerabilities that traditional cybersecurity frameworks cannot adequately address. This paper presents a compr

Cited by 0 Source ↗PDF ↗Scholar ↗

2026

Position: It is Time to Virtualize Foundation Models with a Self-evolving Operating System Layer

Suparna Bhattacharya, Tarun Kumar, Cong Xu, Satish Mopur, Jiahao Li, Ashish Mishra +4

ICML 2026poster

AI applications have shifted from single, mono-lithic foundation models (FM) to compound agentic systems. Yet today’s stacks remain fragmented: even as protocols (e.g., MCP, A2A) ease tool/agent connectivity, each framework embeds an implicit runtime for state, memory, budgets, and guardrails, makin…

Cited by 0 Source ↗Scholar ↗

2025

SubLIME: Subset Selection via Rank Correlation Prediction for Data-Efficient LLM Evaluation

Gayathri Saranathan, Cong Xu, Mahammad Parwez Alam, Tarun Kumar, Martin Foltin, Soon Yee Wong +1

ACL 2025long

The rapid expansion of Large Language Models (LLMs) and natural language processing datasets has made exhaustive benchmark evaluations computationally prohibitive. Inspired by high-stakes competitions like the International Mathematical Olympiad-where a few well-chosen problems suffice to differenti…

Cited by 0 Source ↗PDF ↗Scholar ↗