Sheng Guo

Stop Unnecessary Reflection: Training LRMs for Efficient Reasoning with Adaptive Reflection and Length Coordinated Penalty

Enhancing Document Understanding with Group Position Embedding: A Novel Approach to Incorporate Layout Information

OmniKV: Dynamic Context Selection for Efficient Long-Context LLMs

NAText: Faster Scene Text Recognition with Non Autoregressive Transformer

MaskTab: Masked Tabular Data Modeling for Learning with Missing Features

TIMESFORMER:A MULTI-REPRESENTATION FRAMEWORK COMBINING CONVOLUTION AND TRANSFORMER FOR MULTIVARIATE TIME SERIES CLASSIFICATION TASKS