4 papers
Breaking Model Lock-in: Cost-Efficient Zero-Shot LLM Routing via a Universal Latent Space
Cheng Yan, Wuyang Zhang, Zhiyuan Ning +5
The rapid proliferation of Large Language Models (LLMs) has led to a fragmented and inefficient ecosystem, a state of ``model lock-in'' where seamlessly integrating novel models re…
Step-GUI Technical Report
Haolong Yan, Jia Wang, Xin Huang +95
Recent advances in multimodal large language models unlock unprecedented opportunities for GUI automation. However, a fundamental challenge remains: how to efficiently acquire high…
LCDB 1.1: A Database Illustrating Learning Curves Are More Ill-Behaved Than Previously Thought
Cheng Yan, Felix Mohr, Tom Viering
Sample-wise learning curves plot performance versus training set size. They are useful for studying scaling laws and speeding up hyperparameter tuning and model selection. Learning…
Video-based Generalized Category Discovery via Memory-Guided Consistency-Aware Contrastive Learning
Zhang Jing, Pu Nan, Xie Yu Xiang +5
Generalized Category Discovery (GCD) is an emerging and challenging open-world problem that has garnered increasing attention in recent years. Most existing GCD methods focus on di…