Assistant Professor, HKUST(GZ)
3 papers at NeurIPS 2025
We introduce HELM, a family of hyperbolic large language models operating fully in hyperbolic space.
Propose a novel approach that redefines pseudo-labeling and confidence estimation in the latent space.
A novel method to efficiently fine-tune Large Language Models in hyperbolic space, unlocking their latent tree-like structures and significantly boosting complex reasoning performance by adapting directly on the hyperbolic manifold.
