3 papers
cs.LG2026
Clin-JEPA: A Multi-Phase Co-Training Framework for Joint-Embedding Predictive Pretraining on EHR Patient Trajectories
Yixuan Yang, Mehak Arora, Ryan Zhang +10
We present Clin-JEPA, a multi-phase co-training framework for joint-embedding predictive (JEPA) pretraining on EHR patient trajectories. JEPA architectures have enabled latent-spac…
cs.LG2026
How Label Imbalance Shapes Geometry: A General Spectral Analysis of Multi-Label Neural Collapse
Xiaoxuan Ma, Yixuan Yang, Song Li +1
This work investigates the phenomenon of Neural Collapse (NC) in multi-label classification, extending its conceptual framework from multi-class learning to general correlated and…
cs.CV2026
GEAR: Geography-knowledge Enhanced Analog Recognition Framework in Extreme Environments
Zelin Liu, Bocheng Li, Yuling Zhou +5
The Mariana Trench and the Qinghai-Tibet Plateau exhibit significant similarities in geological origins and microbial metabolic functions. Given that deep-sea biological sampling f…