2 papers
cs.LG2025
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…
cs.LG2025
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…