10 papers
Flag Varieties: A Geometric Framework for Deep Network Alignment
Jingchuan Xiao, Xinyi Sui, Cihan Ruan
Alignment, the tendency of adjacent weight matrices in deep networks to develop compatible subspace orientations, underlies gradient flow, Neural Collapse, and representation simil…
Geometric and Spectral Alignment for Deep Neural Network II
Ziran Liu, Wei Wang, Jinhao Wang +5
This paper develops the angular and static-channel component of Geometric and Spectral Alignment for residual Jacobian chains. Starting from Cartan-coordinate rigidity and fitted e…
Geometric and Spectral Alignment for Deep Neural Network I
Ziran Liu, Wei Wang, Jinhao Wang +5
Deep residual architectures are modeled as products of near-identity Jacobians. This paper proves deterministic quotient-geometric estimates for singular spectra of Frobenius-norma…
What Did They Mean? How LLMs Resolve Ambiguous Social Situations across Perspectives and Roles
Qiming Yuan, Linyi Han, Nam Ling +1
People increasingly turn to large language models (LLMs) to interpret ambiguous social situations: a delayed text reply, an unusually cold supervisor, a teacher's mixed signals, or…
From Pixels to Nucleotides: End-to-End Token-Based Video Compression for DNA Storage
Cihan Ruan, Lebin Zhou, Bingqing Zhao +8
DNA-based storage has emerged as a promising approach to the global data crisis, offering molecular-scale density and millennial-scale stability at low maintenance cost. Over the p…
Thinking Like Van Gogh: Structure-Aware Style Transfer via Flow-Guided 3D Gaussian Splatting
Lebin Zhou, Jingchuan Xiao, Zhendong Wang +4
In 1888, Vincent van Gogh wrote, "I am seeking exaggeration in the essential." This principle, amplifying structural form while suppressing photographic detail, lies at the core of…