Zobrazeno 1 - 10
of 239
pro vyhledávání: '"Deng, Zihao"'
In the emerging hybrid traffic flow environment, which includes both human-driven vehicles (HDVs) and autonomous vehicles (AVs), ensuring safe and robust decision-making and control is crucial for the effective operation of autonomous vehicle platoon
Externí odkaz:
http://arxiv.org/abs/2408.09468
Multi-robot collaborative navigation is an essential ability where teamwork and synchronization are keys. In complex and uncertain environments, adaptive formation is vital, as rigid formations prove to be inadequate. The ability of robots to dynamic
Externí odkaz:
http://arxiv.org/abs/2404.01618
Autor:
Deng, Zihao, Ghaemmaghami, Benjamin, Singh, Ashish Kumar, Cho, Benjamin, Orshansky, Leo, Erez, Mattan, Orshansky, Michael
Modern DNN-based recommendation systems rely on training-derived embeddings of sparse features. Input sparsity makes obtaining high-quality embeddings for rarely-occurring categories harder as their representations are updated infrequently. We demons
Externí odkaz:
http://arxiv.org/abs/2309.15881
Autor:
Deng, Zihao, Ma, Yinghao, Liu, Yudong, Guo, Rongchen, Zhang, Ge, Chen, Wenhu, Huang, Wenhao, Benetos, Emmanouil
Publikováno v:
2024 Annual Conference of the North American Chapter of the Association for Computational Linguistics
Large Language Models (LLMs) have shown immense potential in multimodal applications, yet the convergence of textual and musical domains remains not well-explored. To address this gap, we present MusiLingo, a novel system for music caption generation
Externí odkaz:
http://arxiv.org/abs/2309.08730
Quantization is commonly used to compress and accelerate deep neural networks. Quantization assigning the same bit-width to all layers leads to large accuracy degradation at low precision and is wasteful at high precision settings. Mixed-precision qu
Externí odkaz:
http://arxiv.org/abs/2307.05657
Autor:
Liang, Paul Pu, Deng, Zihao, Ma, Martin, Zou, James, Morency, Louis-Philippe, Salakhutdinov, Ruslan
In a wide range of multimodal tasks, contrastive learning has become a particularly appealing approach since it can successfully learn representations from abundant unlabeled data with only pairing information (e.g., image-caption or video-audio pair
Externí odkaz:
http://arxiv.org/abs/2306.05268
Autor:
Liang, Paul Pu, Cheng, Yun, Fan, Xiang, Ling, Chun Kai, Nie, Suzanne, Chen, Richard, Deng, Zihao, Allen, Nicholas, Auerbach, Randy, Mahmood, Faisal, Salakhutdinov, Ruslan, Morency, Louis-Philippe
The recent explosion of interest in multimodal applications has resulted in a wide selection of datasets and methods for representing and integrating information from different modalities. Despite these empirical advances, there remain fundamental re
Externí odkaz:
http://arxiv.org/abs/2302.12247
Autor:
Zhuo, Ming1,2, Deng, Zihao2, Yuan, Lin3, Mai, Zifeng3, Zhong, Maolin2, Ye, Jun-Ming1,2 yjm7798@sina.com
Publikováno v:
Scientific Reports. 8/17/2024, Vol. 14 Issue 1, p1-10. 10p.
Autor:
Liang, Paul Pu, Lyu, Yiwei, Chhablani, Gunjan, Jain, Nihal, Deng, Zihao, Wang, Xingbo, Morency, Louis-Philippe, Salakhutdinov, Ruslan
The promise of multimodal models for real-world applications has inspired research in visualizing and understanding their internal mechanics with the end goal of empowering stakeholders to visualize model behavior, perform model debugging, and promot
Externí odkaz:
http://arxiv.org/abs/2207.00056
The ability for a human to understand an Artificial Intelligence (AI) model's decision-making process is critical in enabling stakeholders to visualize model behavior, perform model debugging, promote trust in AI models, and assist in collaborative h
Externí odkaz:
http://arxiv.org/abs/2203.02013