5 papers
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…
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…
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…
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…
GSemSplat: Generalizable Semantic 3D Gaussian Splatting from Uncalibrated Image Pairs
Xingrui Wang, Cuiling Lan, Hanxin Zhu +2
Modeling and understanding the 3D world is crucial for various applications, from augmented reality to robotic navigation. Recent advancements based on 3D Gaussian Splatting have i…