10 papers
Unveiling Multi-regime Patterns in SciML: Distinct Failure Modes and Regime-specific Optimization
Yuxin Wang, Yuanzhe Hu, Xiaokun Zhong +7
Neural networks trained under different hyperparameter settings can fall into distinct training "regimes," with consistent behavior within regimes and qualitative differences acros…
Transfer Faster, Price Smarter: Minimax Dynamic Pricing under Cross-Market Preference Shift
Yi Zhang, Elynn Chen, Yujun Yan
We study contextual dynamic pricing when a target market can leverage K auxiliary markets -- offline logs or concurrent streams -- whose mean utilities differ by a structured prefe…
Judging with Many Minds: Do More Perspectives Mean Less Prejudice? On Bias Amplifications and Resistance in Multi-Agent Based LLM-as-Judge
Chiyu Ma, Enpei Zhang, Yilun Zhao +7
LLM-as-Judge has emerged as a scalable alternative to human evaluation, enabling large language models (LLMs) to provide reward signals in trainings. While recent work has explored…
GENUINE: Graph Enhanced Multi-level Uncertainty Estimation for Large Language Models
Tuo Wang, Adithya Kulkarni, Tyler Cody +3
Uncertainty estimation is essential for enhancing the reliability of Large Language Models (LLMs), particularly in high-stakes applications. Existing methods often overlook semanti…
Tackling Size Generalization of Graph Neural Networks on Biological Data from a Spectral Perspective
Gaotang Li, Danai Koutra, Yujun Yan
We address the key challenge of size-induced distribution shifts in graph neural networks (GNNs) and their impact on the generalization of GNNs to larger graphs. Existing literatur…
Non-exchangeable Conformal Prediction for Temporal Graph Neural Networks
Tuo Wang, Jian Kang, Yujun Yan +2
Conformal prediction for graph neural networks (GNNs) offers a promising framework for quantifying uncertainty, enhancing GNN reliability in high-stakes applications. However, exis…