3 papers
cs.LG2026
Context Staircase: Signature-Aligned Dynamics of Token Embeddings under Small Initialization
Junjie Yao, Liangkai Hang, Zhi-Qin John Xu
Token embeddings are the basic representational units that connect discrete tokens with continuous computation in language models. Although modern language models learn embeddings…
cs.AI2026
Small Initialization Matters for Large Language Models
Liangkai Hang, Junjie Yao, Zhiyu Li +3
Large language models provide a tractable system for asking how intelligence itself emerges, rather than only how LLMs can be engineered. Although progress is usually attributed to…
cs.LG2025
Scalable Complexity Control Facilitates Reasoning Ability of LLMs
Liangkai Hang, Junjie Yao, Zhiwei Bai +17
The reasoning ability of large language models (LLMs) has been rapidly advancing in recent years, attracting interest in more fundamental approaches that can reliably enhance their…