Institution profile

University of Sussex

Academic institutioneurope · gb
Official website
Research library155linked papers
Opportunities0open roles
Selected work

Representative Papers

A Brain-like Synergistic Core in LLMs Drives Behaviour and Learning

Jan 11, 2026arXiv.org

This study investigates whether large language models (LLMs) exhibit human brain–like mechanisms of information integration and how such mechanisms influence learning and behavior. Drawing on information decomposition theory, the authors conduct cross-architectural analyses, ablation studies, and comparisons between reinforcement learning and supervised fine-tuning. They reveal, for the first time, a high-cooperativity information processing core in intermediate layers of LLMs, whose organizational pattern closely resembles that of the human brain and emerges spontaneously during training. Ablating this cooperative region significantly impairs model performance, while targeted fine-tuning of this region yields substantially greater improvements than fine-tuning redundant regions, confirming its critical role in intelligent behavior. These findings further inform a novel, efficient fine-tuning strategy centered on cooperative neural substrates.

1 citationsRead paper

Omni-Streaming Thinking

Sep 14, 2026

为解决多模态流式模型中过早跨模态承诺问题,提出Omni-Streaming Thinking方法,通过分离存储视听证据并设置验证间隔来更新状态,减少错误响应。

0 citationsRead paper
Recent publications

Latest Papers

Omni-Streaming Thinking

Sep 14, 2026

为解决多模态流式模型中过早跨模态承诺问题,提出Omni-Streaming Thinking方法,通过分离存储视听证据并设置验证间隔来更新状态,减少错误响应。

0 citationsRead paper

On Synthesis of Metric Interval Temporal Logics

Sep 01, 2026

本文提出了一种解决精确被动学习Metric Interval Temporal Logic(MITL)的方法,通过将时间学习问题转换为非时间问题,并合成精确的时间约束来嵌入到布尔原子命题中。

0 citationsRead paper