3 papers
cs.AI2026
Bridging the Know-Act Gap via Task-Level Autoregressive Reasoning
Jihyun Janice Ahn, Ryo Kamoi, Berk Atil +34
LLMs often generate seemingly valid answers to flawed or ill-posed inputs. This is not due to missing knowledge: under discriminative prompting, the same models can mostly identify…
cs.LG2025
IMPA-HGAE:Intra-Meta-Path Augmented Heterogeneous Graph Autoencoder
Di Lin, Wanjing Ren, Xuanbin Li +1
Self-supervised learning (SSL) methods have been increasingly applied to diverse downstream tasks due to their superior generalization capabilities and low annotation costs. Howeve…
cs.LG2025
Learning Robust Heterogeneous Graph Representations via Contrastive-Reconstruction under Sparse Semantics
Di Lin, Wanjing Ren, Xuanbin Li +1
In graph self-supervised learning, masked autoencoders (MAE) and contrastive learning (CL) are two prominent paradigms. MAE focuses on reconstructing masked elements, while CL maxi…