Lattice AI Research

Research focus

Interpretability & Mechanistic Interp (2)Red-Teaming & Adversarial Robustness (1)Architecture Design (Transformers, SSMs, MoE) (1)

Frequent co-authors

Shanshan Lin (2)Dongsheng Hong (2)Xiangwen Liao (2)Yanhui Chen (1)

Papers (2)

Mar 2, 2026

Yanhui Chen +52w ago

Explanation-Guided Adversarial Training for Robust and Interpretable Models

Get robust and interpretable models by combining adversarial training with explanation-guided learning, achieving a whopping +37% boost in adversarial accuracy on OOD data.

Yanhui Chen, Shanshan Lin, Dongsheng Hong +3

Interpretability & Mechanistic Interp Red-Teaming & Adversarial Robustness

Xujia Li +42w ago

BAED: a New Paradigm for Few-shot Graph Learning with Explanation in the Loop

Get better few-shot graph learning by explaining your predictions: BAED extracts informative subgraphs to improve accuracy and interpretability.

Xujia Li, Dongsheng Hong, Shanshan Lin +2

Architecture Design (Transformers, SSMs, MoE)Interpretability & Mechanistic Interp

Chuanyi Liu

Publication activitypapers/week, last 8 weeks

Research focus

Frequent co-authors

Papers (2)

Search

Chuanyi Liu

Publication activitypapers/week, last 8 weeks

Research focus

Frequent co-authors

Papers (2)