collaborators

8 papers

cs.LG2026

Understanding Deep Representation Learning via Layerwise Feature Compression and Discrimination

Peng Wang, Xiao Li, Can Yaras +4

Over the past decade, deep learning has proven to be a highly effective tool for learning meaningful features from raw data. However, it remains an open question how deep networks…

cs.CL2026

Erase-then-Delta Attention: Decoupling Erase and Write Addresses in Delta-Rule Linear Attention

Xiao Li, Chengruidong Zhang, Hao Luo +15

Delta-rule linear attention improves recurrent memory updates by correcting what is already stored at the current write address before writing new content. However, the active corr…

cs.LG2026

Data-Constrained Language Model Pretraining: Improved Regularization and Scaling Laws

Zhiwei Xu, Shihao Wu, Hanseul Cho +2

Classical scaling laws for language model pretraining balance model size against training dataset size under a fixed compute budget, assuming abundant data and a single pass over t…

cs.LG2026

Lightweight Transformer for EEG Classification via Balanced Signed Graph Algorithm Unrolling

Junyi Yao, Parham Eftekhar, Gene Cheung +3

Samples of brain signals collected by EEG sensors have inherent anti-correlations that are well modeled by negative edges in a finite graph. To differentiate epilepsy patients from…

cs.LG2025

RaanA: A Fast, Flexible, and Data-Efficient Post-Training Quantization Algorithm

Yongyi Yang, Jianyang Gao, Wei Hu

Post-training Quantization (PTQ) has become a widely used technique for improving inference efficiency of large language models (LLMs). However, existing PTQ methods generally suff…

cs.LG2025

Swing-by Dynamics in Concept Learning and Compositional Generalization

Yongyi Yang, Core Francisco Park, Ekdeep Singh Lubana +3

Prior work has shown that text-conditioned diffusion models can learn to identify and manipulate primitive concepts underlying a compositional data-generating process, enabling gen…