10 papers
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…
Geometry-Preserving Orthonormal Initialization for Low-Rank Adaptation in RLVR
Ruijia Zhang, Jiacheng Zhu, Hanqing Zhu +1
Low-rank adaptation (LoRA) and its variants enable parameter-efficient fine-tuning of large language models under the supervised fine-tuning (SFT) paradigm. However, their efficacy…
General-Purpose Photonic Computing Primitive for Contemporary Artificial Intelligence
Shupeng Ning, Chenghao Feng, Zhenxiang Xu +4
Photonic computing offers a promising route to accelerating artificial intelligence (AI) by providing high analog bandwidth, low latency, and low energy consumption. However, exist…
Harnessing Photonics for Machine Intelligence
Hanqing Zhu, Shupeng Ning, Hongjian Zhou +4
The exponential growth of machine-intelligence workloads is colliding with the power, memory, and interconnect limits of the post-Moore era, motivating compute substrates that scal…
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…
ENLighten: Lighten the Transformer, Enable Efficient Optical Acceleration
Hanqing Zhu, Zhican Zhou, Shupeng Ning +4
Photonic computing has emerged as a promising substrate for accelerating the dense linear-algebra operations at the heart of AI, yet adoption for large Transformer models remains i…