collaborators

14 papers

cs.LG2026

COEC: Calibrated Orthogonal-Equivalence Compensation for Structured Pruning of Large Language Models

Peiqi Yu, Nam Ling, Wei Wang +1

Structured pruning reduces the size and inference cost of large language models (LLMs) by removing weight columns, but the resulting output error can degrade accuracy. Existing tra…

cs.LG2026

CORAM: Coherent Orthogonal Rotation for Model Merging

Xinyi Sui, Ziran Liu, Nam Ling +2

Merging finetuned models combines specialized capabilities without joint training or access to the original data. Most methods operate by linear arithmetic in Euclidean weight spac…

eess.IV2026

Adaptive Fused Prior Transfer for Controllable Generative Image Compression

Yifei Pei, Ying Liu, Nam Ling

Learned image compression has achieved competitive rate-distortion performance, but very-low-bitrate reconstruction remains difficult because the transmitted representation often c…

cs.LG2026

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…

cs.LG2026

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…

cs.HC2026

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…