Publications (21)
-systems for twisted quantum affine algebras
Keyu Wang
We establish the -systems for the twisted quantum affine algebras that were conjectured in arXiv:1606.05301. We develop the representation theory of Borel subalgeb…
Embedding Ontologies via Incorporating Extensional and Intensional Knowledge
Keyu Wang, Guilin Qi, Jiaoyan Chen +2
Ontologies contain rich knowledge within domain, which can be divided into two categories, namely extensional knowledge and intensional knowledge. Extensional knowledge provides in…
When Fewer Layers Break More Chains: Layer Pruning Harms Test-Time Scaling in LLMs
Keyu Wang, Tian Lyu, Guinan Su +4
Layer pruning has emerged as a widely adopted technique for improving the efficiency of large language models (LLMs). Although existing methods demonstrate strong performance reten…
One LR Doesn't Fit All: Heavy-Tail Guided Layerwise Learning Rates for LLMs
Di He, Songjun Tu, Keyu Wang +2
Learning rate configuration is a fundamental aspect of modern deep learning. The prevailing practice of applying a uniform learning rate across all layers overlooks the structural…
Fraud-R1 : A Multi-Round Benchmark for Assessing the Robustness of LLM Against Augmented Fraud and Phishing Inducements
Shu Yang, Shenzhe Zhu, Zeyu Wu +7
We introduce Fraud-R1, a benchmark designed to evaluate LLMs' ability to defend against internet fraud and phishing in dynamic, real-world scenarios. Fraud-R1 comprises 8,564 fraud…
Folding shuffle algebras and twisted -characters
Andrei Neguţ, Keyu Wang
Using our new notion of folding shuffle algebras, we prove a conjecture of Hernandez on the equality between certain -characters of quantum untwisted affine algebra modules and…