9 papers
CR: Cross-sample Consistency Regularization Mitigates Feature Splitting and Absorption in Sparse Autoencoders
Haoran Jin, Xiting Wang, Shijie Ren +2
Sparse Autoencoders (SAEs) are widely used to interpret large language models by decomposing activations into sparse, human-understandable features, but scaling to large dictionari…
Projective Graph Residualization: Variation-Allocation Frontiers for Control-Function IV
Rui Wu, Zongyuan Chen, Hong Xie +2
Control-function instrumental-variable estimators pass an estimated first-stage residual to an outcome model. The residual must retain the latent control direction while leaving en…
Scaling Federated Linear Contextual Bandits via Sketching
Hantao Yang, Hong Xie, Xutong Liu +1
In federated contextual linear bandits, high data dimensionality incurs prohibitive computation and communication costs: local agents perform -time determinant computation…
GTM: A General Time-series Model for Enhanced Representation Learning of Time-Series Data
Cheng He, Xu Huang, Gangwei Jiang +7
Despite recent progress in time-series foundation models, challenges persist in improving representation learning and adapting to diverse downstream tasks. We introduce a General T…
AgentCAT: An LLM Agent for Extracting and Analyzing Catalytic Reaction Data from Chemical Engineering Literature
Wei Yang, Zihao Liu, Tao Tan +6
This paper presents a large language model (LLM) agent named AgentCAT, which extracts and analyzes catalytic reaction data from chemical engineering papers, %and supports natural l…
A Unified Frequency Domain Decomposition Framework for Interpretable and Robust Time Series Forecasting
Cheng He, Xijie Liang, Zengrong Zheng +6
Current approaches for time series forecasting, whether in the time or frequency domain, predominantly use deep learning models based on linear layers or transformers. They often e…