Zobrazeno 1 - 10
of 22 482
pro vyhledávání: '"Huang, Xin"'
Autor:
Zhou, Hao, Wang, Zhijun, Huang, Shujian, Huang, Xin, Han, Xue, Feng, Junlan, Deng, Chao, Luo, Weihua, Chen, Jiajun
Large Language Models (LLMs) are often English-centric due to the disproportionate distribution of languages in their pre-training data. Enhancing non-English language capabilities through post-pretraining often results in catastrophic forgetting of
Externí odkaz:
http://arxiv.org/abs/2408.11396
Autor:
Aziz, Haris, Huang, Xin, Kimura, Kei, Saha, Indrajit, Suzuki, Zhaohong Sun Mashbat, Yokoo, Makoto
We consider the problem of fair allocation with subsidy when agents have weighted entitlements. After highlighting several important differences from the unweighted cases, we present several results concerning weighted envy-freeability including gene
Externí odkaz:
http://arxiv.org/abs/2408.08711
Multimodal Large Language Models (MLLMs) excel in solving text-based mathematical problems, but they struggle with mathematical diagrams since they are primarily trained on natural scene images. For humans, visual aids generally enhance problem-solvi
Externí odkaz:
http://arxiv.org/abs/2408.08640
Checkpoint/Restart (C/R) has been widely deployed in numerous HPC systems, Clouds, and industrial data centers, which are typically operated by system engineers. Nevertheless, there is no existing approach that helps system engineers without domain e
Externí odkaz:
http://arxiv.org/abs/2408.06082
Unified graph representation learning aims to produce node embeddings, which can be applied to multiple downstream applications. However, existing studies based on graph neural networks and language models either suffer from the limitations of numero
Externí odkaz:
http://arxiv.org/abs/2408.05456
Sequential recommendation leverages interaction sequences to predict forthcoming user behaviors, crucial for crafting personalized recommendations. However, the true preferences of a user are inherently complex and high-dimensional, while the observe
Externí odkaz:
http://arxiv.org/abs/2407.17802
Data summarization aims at utilizing a small-scale summary to represent massive datasets as a whole, which is useful for visualization and information sipped generation. However, most existing studies of hierarchical summarization only work on \emph{
Externí odkaz:
http://arxiv.org/abs/2407.14098
Autor:
Liu, Jihao, Huang, Xin, Zheng, Jinliang, Liu, Boxiao, Wang, Jia, Yoshie, Osamu, Liu, Yu, Li, Hongsheng
This paper introduces MM-Instruct, a large-scale dataset of diverse and high-quality visual instruction data designed to enhance the instruction-following capabilities of large multimodal models (LMMs). While existing visual instruction datasets ofte
Externí odkaz:
http://arxiv.org/abs/2406.19736
Autor:
Hu, Peng, Liu, Sizhe, Gao, Changjiang, Huang, Xin, Han, Xue, Feng, Junlan, Deng, Chao, Huang, Shujian
Large Language Models have demonstrated impressive reasoning capabilities across multiple languages. However, the relationship between capabilities in different languages is less explored. In this work, we decompose the process of reasoning tasks int
Externí odkaz:
http://arxiv.org/abs/2406.16655
Random feature neural network approximations of the potential in Hamiltonian systems yield approximations of molecular dynamics correlation observables that have the expected error $\mathcal{O}\big((K^{-1}+J^{-1/2})^{\frac{1}{2}}\big)$, for networks
Externí odkaz:
http://arxiv.org/abs/2406.14791