3 papers
cs.CL2026
SimLens for Early Exit in Large Language Models: Eliciting Accurate Latent Predictions with One More Token
Ming Ma, Bowen Zheng, Zhongqiao Lin +1
Intermediate-layer predictions in large language models (LLMs) are informative but hard to decode accurately, especially at early layers. Existing lens-style methods typically rely…
cs.CL2025
Label Words as Local Task Vectors in In-Context Learning
Bowen Zheng, Ming Ma, Zhongqiao Lin +1
Large Language Models (LLMs) have demonstrated remarkable abilities, one of the most important being in-context learning (ICL). With ICL, LLMs can derive the underlying rule from a…
q-bio.NC2025
From Transformer to Biology: A Hierarchical Model for Attention in Complex Problem-Solving
Zhongqiao Lin, Yunwei Li, Tianming Yang
Attention is fundamental to cognition, yet it remains a challenge to understand attention in tasks approaching real-world complexity. Here, we approached this problem by modeling g…