11 citations · 16 across the 10 of their papers we have counts for
3 papers · 1 filter
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…
Can Test-Time Scaling Improve World Foundation Model?
Wenyan Cong, Hanqing Zhu, Peihao Wang +7
World foundation models, which simulate the physical world by predicting future states from current observations and inputs, have become central to many applications in physical in…
Hardware-Efficient Photonic Tensor Core: Accelerating Deep Neural Networks with Structured Compression
Shupeng Ning, Hanqing Zhu, Chenghao Feng +3
The rapid growth in computing demands, particularly driven by artificial intelligence applications, has begun to exceed the capabilities of traditional electronic hardware. Optical…