P. Li | 刘均 | 西安交通大学https://liujun-xjtu.github.io/zh/authors/p.-li/P. LiHugoBlox Kit (https://hugoblox.com)zh-HansThu, 01 Jan 2026 00:00:00 +0000AGT^AO: Robust and Stabilized LLM Unlearning via Adversarial Gating Training with Adaptive Orthogonalityhttps://liujun-xjtu.github.io/zh/publication/agtao-robust-and-stabilized-llm-unlearning-via-adversarial-gating-training-with-adaptive-orthogonali/Thu, 01 Jan 2026 00:00:00 +0000https://liujun-xjtu.github.io/zh/publication/agtao-robust-and-stabilized-llm-unlearning-via-adversarial-gating-training-with-adaptive-orthogonali/PhysPRM: A Generative Process Reward Model with Fine-grained Diagnosis for Physics Problem Solvinghttps://liujun-xjtu.github.io/zh/publication/physprm-a-generative-process-reward-model-with-fine-grained-diagnosis-for-physics-problem-solving/Thu, 01 Jan 2026 00:00:00 +0000https://liujun-xjtu.github.io/zh/publication/physprm-a-generative-process-reward-model-with-fine-grained-diagnosis-for-physics-problem-solving/