activity
20242026
collaborators

7 papers

cs.AI2026

A Control Architecture for Training-Free Memory Use

Yanzhen Lu, Muchen Jiang, Zhicheng Qian +1

Prompt-injected memory can improve reasoning without updating model weights, but it also creates a control problem: retrieved content helps only when it is applied in the right sta…

cs.AI2026

State Transfer Reveals Reuse in Controlled Routing

Yanzhen Lu, Zhicheng Qian, Muchen Jiang +1

Prompt-based interventions can change model behavior, but trained success alone does not identify where the behaviorally relevant state is represented. We study this question in co…

cs.AI2026

CSPO: Alleviating Reward Ambiguity for Structured Table-to-LaTeX Generation

Yunfan Yang, Cuiling Lan, Jitao Sang +1

Tables contain rich structured information, yet when stored as images their contents remain "locked" within pixels. Converting table images into LaTeX code enables faithful digitiz…

cs.AI2026

Stepwise Think-Critique: A Unified Framework for Robust and Interpretable LLM Reasoning

Jiaqi Xu, Cuiling Lan, Xuejin Chen +1

Human beings solve complex problems through critical thinking, where reasoning and evaluation are intertwined to converge toward correct solutions. However, most existing large lan…

cs.LG2026

Temperature as a Meta-Policy: Adaptive Temperature in LLM Reinforcement Learning

Haoran Dang, Cuiling Lan, Hai Wan +2

Temperature is a crucial hyperparameter in large language models (LLMs), controlling the trade-off between exploration and exploitation during text generation. High temperatures en…

q-bio.NC2025

Deciphering Functions of Neurons in Vision-Language Models

Jiaqi Xu, Cuiling Lan, Yan Lu

The burgeoning growth of open-sourced vision-language models (VLMs) has catalyzed a plethora of applications across diverse domains. Ensuring the transparency and interpretability…