3 papers
cs.LG2025
PARM: Multi-Objective Test-Time Alignment via Preference-Aware Autoregressive Reward Model
Baijiong Lin, Weisen Jiang, Yuancheng Xu +2
Multi-objective test-time alignment aims to adapt large language models (LLMs) to diverse multi-dimensional user preferences during inference while keeping LLMs frozen. Recently, G…
cs.CL2025
DeskVision: Large Scale Desktop Region Captioning for Advanced GUI Agents
Yibin Xu, Liang Yang, Hao Chen +3
The limitation of graphical user interface (GUI) data has been a significant barrier to the development of GUI agents today, especially for the desktop / computer use scenarios. To…
cs.CL2025
SEKI: Self-Evolution and Knowledge Inspiration based Neural Architecture Search via Large Language Models
Zicheng Cai, Yaohua Tang, Yutao Lai +3
We introduce SEKI, a novel large language model (LLM)-based neural architecture search (NAS) method. Inspired by the chain-of-thought (CoT) paradigm in modern LLMs, SEKI operates i…