Showing eess.SYShow all
3 papers · 1 filter
eess.SY2026
FARM: Fundamental Agentic Reward Model For Multi-task Wireless Network Optimization
Feiran You, Changxu Ni, Haozhe Ma +2
Future wireless networks require learning agents to adapt across heterogeneous channel conditions, traffic patterns, quality-of-service (QoS) requirements, objectives, and operatio…
eess.SY2026
TwinJEPA: Action-Preferred Predictive Representations for Goal-Conditioned Control
Feiran You, Hongyang Du
Joint-Embedding Predictive Architectures (JEPAs) are a promising paradigm for representation learning by predicting future latent states without reconstructing observations. Recent…
eess.SY2026
StarSD: One-for-Many Speculative Decoding
Junhao He, Feiran You, Hongyang Du
Speculative decoding accelerates autoregressive generation by separating token proposal from verification, but most existing approaches are designed for single-node execution and d…