Publications (41)
Persistent Computational State: A Session-Centric Runtime for Generative World Models
Zhen Lin
Generative world models are increasingly driven as simulators: a planner forks a state, rolls out futures, backtracks, and returns to a visited viewpoint. Recent benchmarks establi…
Clebsch-Gordan Nets: a Fully Fourier Space Spherical Convolutional Neural Network
Risi Kondor, Zhen Lin, Shubhendu Trivedi
Recent work by Cohen \emph{et al.} has achieved state-of-the-art results for learning spherical images in a rotation invariant way by using ideas from group representation theory a…
DeepScientist: Advancing Frontier-Pushing Scientific Findings Progressively
Yixuan Weng, Minjun Zhu, Qiujie Xie +4
While previous AI Scientist systems can generate novel findings, they often lack the focus to produce scientifically valuable contributions that address pressing human-defined chal…
Extracting at future Higgs factory with energy correlators
Zhen Lin, Manqi Ruan, Meng Xiao +1
The prospected sensitivity in determination using an event shape observable, ratio of energy correlators at future electron-positron colliders is presented. The stu…
On the Ky Fan -norm of the -matrix of graphs
Zhen Lin, Lianying Miao, Guanglong Yu +1
Let and be the adjacency matrix and the degree diagonal matrix of a graph , respectively. Then is called Laplacian matrix of the graph . Let $G…
HGCA: Hybrid GPU-CPU Attention for Long Context LLM Inference
Weishu Deng, Yujie Yang, Peiran Du +6
Scaling inference for large language models (LLMs) is increasingly constrained by limited GPU memory, especially due to growing key-value (KV) caches required for long-context gene…