32 citations · 80 across the 14 of their papers we have counts for
14 papers
SOAP, Muon, and Beyond: Pushing LLM Pretraining Scales
Mikail Khona, Aditya Vavre, Boxiang Wang +11
Higher-order optimizers such as Muon and SOAP offer faster convergence than AdamW, but their computational cost and numerical stability challenges have limited adoption at scale. I…
Cosmos 3: Omnimodal World Models for Physical AI
NVIDIA, :, Aditi +293
We introduce Cosmos 3, a family of omnimodal world models designed to jointly process and generate language, image, video, audio, and action sequences within a unified mixture-of-t…
TorchKM: A GPU-Oriented Library for Kernel Learning and Model Selection
Yikai Zhang, Gaoxiang Jia, Jie Ding +1
TorchKM is an open-source library for kernel machines, including support vector machines, kernel logistic regression, and kernel quantile regression, with GPU acceleration. The lib…
Spec-Driven AI for Science: The ARIA Framework for Automated and Reproducible Data Analysis
Chuke Chen, Biao Luo, Nan Li +4
The rapid expansion of scientific data has widened the gap between analytical capability and research intent. Existing AI-based analysis tools, ranging from AutoML frameworks to ag…
fastkqr: A Fast Algorithm for Kernel Quantile Regression
Qian Tang, Yuwen Gu, Boxiang Wang
Quantile regression is a powerful tool for robust and heterogeneous learning that has seen applications in a diverse range of applied areas. However, its broader application is oft…
Using Large Language Models for Humanitarian Frontline Negotiation: Opportunities and Considerations
Zilin Ma, Susannah, Su +14
Humanitarian negotiations in conflict zones, called \emph{frontline negotiation}, are often highly adversarial, complex, and high-risk. Several best-practices have emerged over the…
The ART of Transfer Learning: An Adaptive and Robust Pipeline
Boxiang Wang, Yunan Wu, Chenglong Ye
Transfer learning is an essential tool for improving the performance of primary tasks by leveraging information from auxiliary data resources. In this work, we propose Adaptive Rob…
Colossal-AI: A Unified Deep Learning System For Large-Scale Parallel Training
Shenggui Li, Hongxin Liu, Zhengda Bian +5
The success of Transformer models has pushed the deep learning model scale to billions of parameters. Due to the limited memory resource of a single GPU, However, the best practice…
Maximizing Parallelism in Distributed Training for Huge Neural Networks
Zhengda Bian, Qifan Xu, Boxiang Wang +1
The recent Natural Language Processing techniques have been refreshing the state-of-the-art performance at an incredible speed. Training huge language models is therefore an impera…
Partially Interpretable Estimators (PIE): Black-Box-Refined Interpretable Machine Learning
Tong Wang, Jingyi Yang, Yunyi Li +1
We propose Partially Interpretable Estimators (PIE) which attribute a prediction to individual features via an interpretable model, while a (possibly) small part of the PIE predict…
Tesseract: Parallelize the Tensor Parallelism Efficiently
Boxiang Wang, Qifan Xu, Zhengda Bian +1
Together with the improvements in state-of-the-art accuracies of various tasks, deep learning models are getting significantly larger. However, it is extremely difficult to impleme…
Sparse Tensor Additive Regression
Botao Hao, Boxiang Wang, Pengyuan Wang +3
Tensors are becoming prevalent in modern applications such as medical imaging and digital marketing. In this paper, we propose a sparse tensor additive regression (STAR) that model…
Another Look at DWD: Thrifty Algorithm and Bayes Risk Consistency in RKHS
Boxiang Wang, Hui Zou
Distance weighted discrimination (DWD) is a margin-based classifier with an interesting geometric motivation. DWD was originally proposed as a superior alternative to the support v…
Sparse Distance Weighted Discrimination
Boxiang Wang, Hui Zou
Distance weighted discrimination (DWD) was originally proposed to handle the data piling issue in the support vector machine. In this paper, we consider the sparse penalized DWD fo…