Author

Wei Lu

h-index 5 View on Semantic Scholar

We have 3 of 15 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#artificial intelligence Jun 2026

Safety Paradox: How Enhanced Safety Awareness Leaves LLMs Vulnerable to Posterior Attack

This work formalizes the Safety Paradox, analytically showing that monotonic improvements in safety alignment naturally amplify posterior vulnerability, and establishes a causal link via reinforcement learning interventions, exemplifying that artificially degrading a model's safety judgment immunizes it against the att...

Ho-Ang P. Long, H. V. Le, Shaoyang Xu et al. · arXiv.org · 0 citations

#artificial intelligence Jun 2026

Multilingual Fine-Tuning via Localized Gradient Conflict Resolution

Bucket-Level MOO is introduced, a scalable distributed framework that applies gradient-based MOO algorithms locally, within the parameter buckets of distributed training, that enables conflict-aware updates without ever materializing a full gradient vector for any objective, and improves multilingual performance over s...

Ho-Ang P. Long, Yiran Zhao, Wei Lu et al. · arXiv.org · 0 citations

Jul 2026

DT-Guard: Intent-Driven Reasoning-Active Training for Reasoning-Free LLM Safety Guardrail

DT-Guard is presented, a content safety guardrail model based on a Reasoning-Active Training, Reasoning-Free Inference paradigm, which demonstrates that reasoning supervision can be effectively internalized into low-latency safety discrimination.

Heng-Xiang Liu, Changtao Miao, Xinjie Yang et al. · arXiv.org · 0 citations