48 citations · 88 across the 27 of their papers we have counts for
5 papers · 1 filter
Aligner: One Global Token is Worth Millions of Parameters When Aligning Large Language Models
Zhou Ziheng, Yingnian Wu, Song-Chun Zhu +1
We introduce Aligner, a novel Parameter-Efficient Fine-Tuning (PEFT) method for aligning multi-billion-parameter-sized Large Language Models (LLMs). Aligner employs a unique design…
Unstructured Moving Least Squares Material Point Methods: A Stable Kernel Approach With Continuous Gradient Reconstruction on General Unstructured Tessellations
Yadi Cao, Yidong Zhao, Minchen Li +4
The Material Point Method (MPM) is a hybrid Eulerian Lagrangian simulation technique for solid mechanics with significant deformation. Structured background grids are commonly empl…
CSAM: A 2.5D Cross-Slice Attention Module for Anisotropic Volumetric Medical Image Segmentation
Alex Ling Yu Hung, Haoxin Zheng, Kai Zhao +6
A large portion of volumetric medical data, especially magnetic resonance imaging (MRI) data, is anisotropic, as the through-plane resolution is typically much lower than the in-pl…
Semi-Supervised Relational Contrastive Learning
Attiano Purpura-Pontoniere, Demetri Terzopoulos, Adam Wang +1
Disease diagnosis from medical images via supervised learning is usually dependent on tedious, error-prone, and costly image labeling by medical experts. Alternatively, semi-superv…
ARNOLD: A Benchmark for Language-Grounded Task Learning With Continuous States in Realistic 3D Scenes
Ran Gong, Jiangyong Huang, Yizhou Zhao +9
Understanding the continuous states of objects is essential for task learning and planning in the real world. However, most existing task learning benchmarks assume discrete (e.g.,…