Wei Yang Bryan Lim

Papers on Lattice

Total citations

Topics

h-index

Publication activitypapers/week, last 8 weeks

Research focus

Red-Teaming & Adversarial Robustness (3)Tool Use & Agents (2)Constitutional AI & AI Ethics (1)Architecture Design (Transformers, SSMs, MoE) (1)

Frequent co-authors

Fuyao Zhang (2)Che Wang (2)Che Wang (2)Jiaming Zhang (2)

Papers (4)

Aug 5, 2026

Jiaming Zhang +29Aug 5, 2026·also Great Bay University, HIT, JHU, Melbourne +1

Adversarial Attacks for Good: A Survey of Proactive Protection across the Visual Content Lifecycle

Adversarial techniques traditionally seen as threats are now being repurposed by content owners to proactively safeguard their visual assets from misuse.

Jiaming Zhang, Jiaming Zhang, Boyang Chen +27

Constitutional AI & AI Ethics Red-Teaming & Adversarial Robustness

Jul 20, 2026

CoCurve: Cross-Module Co-Pruning Curvature for Training-Free Structured LLM Pruning

Jointly pruning dependent units in LLMs can lead to more effective model compression without the need for fine-tuning, challenging conventional independent pruning methods.

Zhiren Gong, Zihao Zeng, Tiantong Wang +2

Architecture Design (Transformers, SSMs, MoE)Inference & Quantization Natural Language Processing

Feb 24, 2026

ICON: Indirect Prompt Injection Defense for Agents based on Inference-Time Correction

LLM agents can now defend against indirect prompt injection attacks without sacrificing task performance, thanks to a new method that surgically manipulates attention based on latent space analysis.

Che Wang, Che Wang, Fuyao Zhang +6

Red-Teaming & Adversarial Robustness Tool Use & Agents

Feb 24, 2026·also Georgia Tech

AdapTools: Adaptive Tool-based Indirect Prompt Injection Attacks on Agentic LLMs

Agentic LLMs are far more vulnerable to indirect prompt injection attacks than previously thought: AdapTools achieves over 2x improvement in attack success while significantly degrading system utility, even against strong defenses.

Che Wang, Che Wang, Jiaming Zhang +6