3 papers
stat.ML2026
Optimization Dynamics Imprint Semantic Specificity in Contrastive Embedding Norms
Ziwei Su, Junyu Ren, Victor Veitch
Contrastive embedding models trained with scale-invariant losses are typically paired with distance metrics like cosine similarity, effectively ignoring embedding magnitudes. Howev…
cs.LG2025
Time-Aware Feature Selection: Adaptive Temporal Masking for Stable Sparse Autoencoder Training
T. Ed Li, Junyu Ren
Understanding the internal representations of large language models is crucial for ensuring their reliability and safety, with sparse autoencoders (SAEs) emerging as a promising in…
cs.SI2024
Pre-Training and Prompting for Few-Shot Node Classification on Text-Attributed Graphs
Huanjing Zhao, Beining Yang, Yukuo Cen +6
The text-attributed graph (TAG) is one kind of important real-world graph-structured data with each node associated with raw texts. For TAGs, traditional few-shot node classificati…