3 papers
cs.RO2026
Refuse the Harm, Complete the Task via Graph-of-Rules Planning for LLM-Enabled Robots
Ali Taheri, Alireza Taban, Qizhou Wang +1
Large Language Models (LLMs) are increasingly used in embodied AI for robotic manipulation and planning, but their deployment in physical systems exposes vulnerabilities such as ja…
cs.AI2025
BarrierBench: Evaluating Large Language Models for Safety Verification in Dynamical Systems
Ali Taheri, Alireza Taban, Sadegh Soudjani +1
Safety verification of dynamical systems via barrier certificates is essential for ensuring correctness in autonomous applications. Synthesizing these certificates involves discove…
cs.LG2025
Forgetting: A New Mechanism Towards Better Large Language Model Fine-tuning
Ali Taheri, Alireza Taban, Qizhou Wang +4
Supervised fine-tuning (SFT) plays a critical role for pretrained large language models (LLMs), notably enhancing their capacity to acquire domain-specific knowledge while preservi…