3 papers
cs.AI2026
Training Language Models to Cooperate with Inference-Time Controllers
Moumita Choudhury, Vanshaj Khattar, Jing Liu +4
Large language model (LLM) performance increasingly depends not only on the base model, but also on the inference-time controller used to organize reasoning. Existing post-training…
cs.LG2026
Amplification Effects in Test-Time Reinforcement Learning: Safety and Reasoning Vulnerabilities
Vanshaj Khattar, Md Rafi ur Rashid, Moumita Choudhury +4
Test-time training (TTT) has recently emerged as a promising method to improve the reasoning abilities of large language models (LLMs), in which the model directly learns from test…
cs.LG2025
Detecting Zero-Day Attacks in Digital Substations via In-Context Learning
Faizan Manzoor, Vanshaj Khattar, Akila Herath +5
The occurrences of cyber attacks on the power grids have been increasing every year, with novel attack techniques emerging every year. In this paper, we address the critical challe…