Zobrazeno 1 - 10
of 103
pro vyhledávání: '"Chilimbi, Trishul"'
Autor:
Swetha, Sirnam, Yang, Jinyu, Neiman, Tal, Rizve, Mamshad Nayeem, Tran, Son, Yao, Benjamin, Chilimbi, Trishul, Shah, Mubarak
Recent advancements in Multimodal Large Language Models (MLLMs) have revolutionized the field of vision-language understanding by integrating visual perception capabilities into Large Language Models (LLMs). The prevailing trend in this field involve
Externí odkaz:
http://arxiv.org/abs/2407.13851
Autor:
Gupta, Rohit, Rizve, Mamshad Nayeem, Unnikrishnan, Jayakrishnan, Tawari, Ashish, Tran, Son, Shah, Mubarak, Yao, Benjamin, Chilimbi, Trishul
Pre-trained vision-language models (VLMs) have enabled significant progress in open vocabulary computer vision tasks such as image classification, object detection and image segmentation. Some recent works have focused on extending VLMs to open vocab
Externí odkaz:
http://arxiv.org/abs/2407.09073
Autor:
Rizve, Mamshad Nayeem, Fei, Fan, Unnikrishnan, Jayakrishnan, Tran, Son, Yao, Benjamin Z., Zeng, Belinda, Shah, Mubarak, Chilimbi, Trishul
In this paper, we propose VidLA, an approach for video-language alignment at scale. There are two major limitations of previous video-language alignment approaches. First, they do not capture both short-range and long-range temporal dependencies and
Externí odkaz:
http://arxiv.org/abs/2403.14870
Autor:
He, Yifei, Zhou, Shiji, Zhang, Guojun, Yun, Hyokun, Xu, Yi, Zeng, Belinda, Chilimbi, Trishul, Zhao, Han
Multi-task learning (MTL) considers learning a joint model for multiple tasks by optimizing a convex combination of all task losses. To solve the optimization problem, existing methods use an adaptive weight updating scheme, where task weights are dy
Externí odkaz:
http://arxiv.org/abs/2402.02009
Graph-Aware Language Model Pre-Training on a Large Graph Corpus Can Help Multiple Graph Applications
Autor:
Xie, Han, Zheng, Da, Ma, Jun, Zhang, Houyu, Ioannidis, Vassilis N., Song, Xiang, Ping, Qing, Wang, Sheng, Yang, Carl, Xu, Yi, Zeng, Belinda, Chilimbi, Trishul
Model pre-training on large text corpora has been demonstrated effective for various downstream applications in the NLP domain. In the graph mining domain, a similar analogy can be drawn for pre-training graph models on large graphs in the hope of be
Externí odkaz:
http://arxiv.org/abs/2306.02592
Autor:
Jiang, Qian, Chen, Changyou, Zhao, Han, Chen, Liqun, Ping, Qing, Tran, Son Dinh, Xu, Yi, Zeng, Belinda, Chilimbi, Trishul
Contrastive loss has been increasingly used in learning representations from multiple modalities. In the limit, the nature of the contrastive loss encourages modalities to exactly match each other in the latent space. Yet it remains an open question
Externí odkaz:
http://arxiv.org/abs/2303.05952
Autor:
He, Chaoyang, Zheng, Shuai, Zhang, Aston, Karypis, George, Chilimbi, Trishul, Soltanolkotabi, Mahdi, Avestimehr, Salman
The mixture of Expert (MoE) parallelism is a recent advancement that scales up the model size with constant computational cost. MoE selects different sets of parameters (i.e., experts) for each incoming token, resulting in a sparsely-activated model.
Externí odkaz:
http://arxiv.org/abs/2212.05191
Publikováno v:
Proceedings of the 29th International Conference on Computational Linguistics (COLING). 2022
In contrast to traditional exhaustive search, selective search first clusters documents into several groups before all the documents are searched exhaustively by a query, to limit the search executed within one group or only a few groups. Selective s
Externí odkaz:
http://arxiv.org/abs/2209.04378
Autor:
Ioannidis, Vassilis N., Song, Xiang, Zheng, Da, Zhang, Houyu, Ma, Jun, Xu, Yi, Zeng, Belinda, Chilimbi, Trishul, Karypis, George
Can we combine heterogenous graph structure with text to learn high-quality semantic and behavioural representations? Graph neural networks (GNN)s encode numerical node attributes and graph structure to achieve impressive performance in a variety of
Externí odkaz:
http://arxiv.org/abs/2206.10781
Autor:
Sun, Xiaodi, Rajagopalan, Sunny, Nigam, Priyanka, Lu, Weiyi, Xu, Yi, Zeng, Belinda, Chilimbi, Trishul
Recent research has shown that large language models pretrained using unsupervised approaches can achieve significant performance improvement on many downstream tasks. Typically when adapting these language models to downstream tasks, like a classifi
Externí odkaz:
http://arxiv.org/abs/2206.02982