4 papers
Efficient Dataset Distillation for Pre-Trained Self-Supervised Models via Statistical Flow Matching
Qianxin Xia, Jiawei Du, Xin Zhang +3
Dataset distillation seeks to synthesize a highly compact dataset that achieves performance comparable to the original dataset on downstream tasks. For the classification task that…
Computational Design and Fabrication of Modular Robots with Untethered Control
Manas Bhargava, Takefumi Hiraki, Malina Strugaru +5
Natural organisms utilize distributed actuation through their musculoskeletal systems to adapt their gait for traversing diverse terrains or to morph their bodies for varied tasks.…
Mixed Hodge Structures of cluster varieties of dimension 3
Yuhang Zhang, Zili Zhang
We calculate the mixed Hodge numbers of smooth 3-dimensional cluster varieties and show that they are of mixed Tate type. We also study the mixed Hodge structures of the cohomology…
MAP-Neo: Highly Capable and Transparent Bilingual Large Language Model Series
Ge Zhang, Scott Qu, Jiaheng Liu +42
Large Language Models (LLMs) have made great strides in recent years to achieve unprecedented performance across different tasks. However, due to commercial interest, the most comp…