2 papers
cs.LG2026
Decoupling Exploration from Optimization in RLVR
Saif Punjwani, Micah Goldblum
Modern language models undergo reinforcement learning with verifiable rewards (RLVR) on top of already-trained checkpoints. A key promise of RLVR is the discovery of new reasoning…
physics.optics2025
Electrical and Thermal Performance Tuning of Spoof Plasmonic Interconnect
Rafichha Yasmin, Ishrat Jahan, Abdelrahman Omar +3
This work introduces an electromagnetic metastructure based interconnect design that could address the critical need for electrical bandwidth and heat dissipation in high-speed, ch…