Zobrazeno 1 - 10
of 4 535
pro vyhledávání: '"SHAH, NEIL"'
Autor:
Han, Haoyu, Wang, Yu, Shomer, Harry, Guo, Kai, Ding, Jiayuan, Lei, Yongjia, Halappanavar, Mahantesh, Rossi, Ryan A., Mukherjee, Subhabrata, Tang, Xianfeng, He, Qi, Hua, Zhigang, Long, Bo, Zhao, Tong, Shah, Neil, Javari, Amin, Xia, Yinglong, Tang, Jiliang
Retrieval-augmented generation (RAG) is a powerful technique that enhances downstream task execution by retrieving additional information, such as knowledge, skills, and tools from external sources. Graph, by its intrinsic "nodes connected by edges"
Externí odkaz:
http://arxiv.org/abs/2501.00309
Current Non-Audible Murmur (NAM)-to-speech techniques rely on voice cloning to simulate ground-truth speech from paired whispers. However, the simulated speech often lacks intelligibility and fails to generalize well across different speakers. To add
Externí odkaz:
http://arxiv.org/abs/2412.18839
Previous real-time MRI (rtMRI)-based speech synthesis models depend heavily on noisy ground-truth speech. Applying loss directly over ground truth mel-spectrograms entangles speech content with MRI noise, resulting in poor intelligibility. We introdu
Externí odkaz:
http://arxiv.org/abs/2412.18836
Autor:
Wu, Xinyi, Loveland, Donald, Chen, Runjin, Liu, Yozen, Chen, Xin, Neves, Leonardo, Jadbabaie, Ali, Ju, Clark Mingxuan, Shah, Neil, Zhao, Tong
Deep recommender systems rely heavily on large embedding tables to handle high-cardinality categorical features such as user/item identifiers, and face significant memory constraints at scale. To tackle this challenge, hashing techniques are often em
Externí odkaz:
http://arxiv.org/abs/2412.17245
Autor:
Chen, Runjin, Ju, Mingxuan, Bui, Ngoc, Antypas, Dimosthenis, Cai, Stanley, Wu, Xiaopeng, Neves, Leonardo, Wang, Zhangyang, Shah, Neil, Zhao, Tong
Generative recommendation systems, driven by large language models (LLMs), present an innovative approach to predicting user preferences by modeling items as token sequences and generating recommendations in a generative manner. A critical challenge
Externí odkaz:
http://arxiv.org/abs/2412.17171
Autor:
Liu, Jingzhe, Mao, Haitao, Chen, Zhikai, Fan, Wenqi, Ju, Mingxuan, Zhao, Tong, Shah, Neil, Tang, Jiliang
Graph Neural Networks (GNNs) have emerged as a powerful tool to capture intricate network patterns, achieving success across different domains. However, existing GNNs require careful domain-specific architecture designs and training from scratch on e
Externí odkaz:
http://arxiv.org/abs/2412.00315
Modern recommendation systems often create information cocoons, limiting users' exposure to diverse content. To enhance user experience, a crucial challenge is developing systems that can balance content exploration and exploitation, allowing users t
Externí odkaz:
http://arxiv.org/abs/2411.13865
Autor:
Shah, Neil
Decentralized Autonomous Organizations (DAOs), based on block-chain systems such as Ethereum, are emerging governance protocols that enable decentralized community management without a central authority. For instance, UniswapDAO allows members to vot
Externí odkaz:
http://arxiv.org/abs/2410.21593
Collaborative Filtering (CF) methods dominate real-world recommender systems given their ability to learn high-quality, sparse ID-embedding tables that effectively capture user preferences. These tables scale linearly with the number of users and ite
Externí odkaz:
http://arxiv.org/abs/2410.23300
Graph neural networks (GNNs) have demonstrated remarkable success in graph representation learning, and various sampling approaches have been proposed to scale GNNs to applications with large-scale graphs. A class of promising GNN training algorithms
Externí odkaz:
http://arxiv.org/abs/2410.05416