collaborators

10 papers

cs.LG2026

From Objectives to What Models Learn: A Landau Theory of Invariant Learning

Pinli Wang, Yue He, Peng Cui

Invariant learning seeks representations that remain predictive across environments, yet the behavior of its objectives along the regularization path is often opaque. We address th…

cs.LG2026

Closed-Form Spectral Regularization for Multi-Task Model Merging

Yongxian Wei, Runxi Cheng, Xingxuan Zhang +4

Model merging combines several independently fine-tuned experts into a single multi-task model without any training data, reducing the storage, serving, and decentralized-developme…

cs.LG2026

LimiX-2M: Mitigating Low-Rank Collapse and Attention Bottlenecks in Tabular Foundation Models

Yuanrui Wang, Xingxuan Zhang, Han Yu +7

Tabular foundation models (TFMs) increasingly rival tree ensembles, but their performance is often compute-inefficient: with standard affine scalar tokenization, each feature injec…

cs.LG2025

Generating Risky Samples with Conformity Constraints via Diffusion Models

Han Yu, Hao Zou, Xingxuan Zhang +4

Although neural networks achieve promising performance in many tasks, they may still fail when encountering some examples and bring about risks to applications. To discover risky s…

cs.LG2025

Error Slice Discovery via Manifold Compactness

Han Yu, Hao Zou, Jiashuo Liu +4

Despite the great performance of deep learning models in many areas, they still make mistakes and underperform on certain subsets of data, i.e. error slices. Given a trained model,…

cs.LG2025

ODP-Bench: Benchmarking Out-of-Distribution Performance Prediction

Han Yu, Kehan Li, Dongbai Li +3

Recently, there has been gradually more attention paid to Out-of-Distribution (OOD) performance prediction, whose goal is to predict the performance of trained models on unlabeled…