3 papers
cs.LG2026
When Softmax Fails at the Top: Extreme Value Corrections for InfoNCE
Melihcan Erol, Suat Evren, Oktay Ozel +3
InfoNCE is the standard contrastive learning objective, but its softmax form is not only a computational convenience: it also encodes a statistical assumption about how the top-sco…
eess.SP2025
Sensing for Free: Learn to Localize More Sources than Antennas without Pilots
Wentao Yu, Khaled B. Letaief, Lizhong Zheng
Integrated sensing and communication (ISAC) represents a key paradigm for future wireless networks. However, existing approaches require waveform modifications, dedicated pilots, o…
eess.SP2024
AI and Deep Learning for Terahertz Ultra-Massive MIMO: From Model-Driven Approaches to Foundation Models
Wentao Yu, Hengtao He, Shenghui Song +4
This study explored the transformative potential of artificial intelligence (AI) in addressing the challenges posed by terahertz ultra-massive multiple-input multiple-output (UM-MI…