← Search

Haotian Huang

2 accepted papers

2025

Long-Short Alignment for Effective Long-Context Modeling in LLMs

ICML 2025poster

Large language models (LLMs) have exhibited impressive performance and surprising emergent properties. However, their effectiveness remains limited by the fixed context window of the transformer architecture, posing challenges for long-context modeling. Among these challenges, length generalization…

2024

Look Ahead or Look Around? A Theoretical Comparison Between Autoregressive and Masked Pretraining

ICML 2024poster

In recent years, the rise of generative self-supervised learning (SSL) paradigms has exhibited impressive performance across visual, language, and multi-modal domains. While the varied designs of generative SSL objectives lead to distinct properties in downstream tasks, a theoretical understanding o…