Tag
This paper presents a retrospective analysis of the CODS 2025 AssetOpsBench Challenge, examining leaderboard saturation, hidden evaluation effects, and design patterns rewarded.
ModelLens is a unified framework that recommends AI models for unseen datasets by learning from public leaderboard data, eliminating the need for costly direct evaluations. It constructs a performance-aware latent space to rank candidates across diverse tasks, outperforming existing baselines on large-scale benchmarks.