Junxiao Yang

Papers on Lattice

Total citations

Topics

h-index

Publication activitypapers/week, last 8 weeks

Research focus

Constitutional AI & AI Ethics (1)Eval Frameworks & Benchmarks (1)Red-Teaming & Adversarial Robustness (1)

Frequent co-authors

Haoran Liu (1)Jinzhe Tu (1)Jiale Cheng (1)Zhexin Zhang (1)

Papers (1)

Apr 13, 2026

Junxiao Yang +112w ago

LASA: Language-Agnostic Semantic Alignment at the Semantic Bottleneck for LLM Safety

LLM safety crumbles in low-resource languages because alignment is skin-deep; LASA fixes this by injecting safety at the semantic core, slashing attack success by 88%.

Junxiao Yang, Haoran Liu, Jinzhe Tu +9

Constitutional AI & AI Ethics Eval Frameworks & Benchmarks Red-Teaming & Adversarial Robustness

Search

Junxiao Yang

Publication activitypapers/week, last 8 weeks

Research focus

Frequent co-authors

Papers (1)