2 papers
cs.CV2026
CM-MAE: A Physics-Guided Cross-Modal Self-Supervised Learning Framework for Vision-Wireless Applications
Yubo Zhang, Yiyao Liu
Synchronized camera and wireless measurements observe the same scene through different physical channels. The central difficulty is that a representation learned in one deployment…
cs.LG2026
I-SDPO: Instance-Level Adaptive Self-Distillation Policy Optimization
Yubo Zhang, Xinhong Ma, Zezhong Tan +1
Group Relative Policy Optimization (GRPO) learns from reward differences within a rollout group, but receives no useful relative signal when every sampled response is incorrect. Pr…