11 citations · 16 across the 10 of their papers we have counts for
4 papers · 1 filter
ISO: An RLVR-Native Optimization Stack
Hanqing Zhu, Wenyan Cong, Zhizhou Sha +8
Reinforcement learning with verifiable rewards (RLVR) is rapidly advancing the reasoning capabilities of language models, yet the optimization layer that converts reward feedback i…
The Path Not Taken: RLVR Provably Learns Off the Principals
Hanqing Zhu, Zhenyu Zhang, Hanxian Huang +11
Reinforcement Learning with Verifiable Rewards (RLVR) reliably improves the reasoning performance of large language models, yet it appears to modify only a small fraction of parame…
APOLLO: SGD-like Memory, AdamW-level Performance
Hanqing Zhu, Zhenyu Zhang, Wenyan Cong +7
Large language models (LLMs) are notoriously memory-intensive during training, particularly with the popular AdamW optimizer. This memory burden necessitates using more or higher-e…
PACE: Pacing Operator Learning to Accurate Optical Field Simulation for Complicated Photonic Devices
Hanqing Zhu, Wenyan Cong, Guojin Chen +4
Electromagnetic field simulation is central to designing, optimizing, and validating photonic devices and circuits. However, costly computation associated with numerical simulation…