Results 71 to 80 of about 127,235 (91)

Uni-GBSA: an open-source and web-based automatic workflow to perform MM/GB(PB)SA calculations for virtual screening

Briefings Bioinform., 2023
Binding free energy calculation of a ligand to a protein receptor is a fundamental objective in drug discovery. Molecular mechanics/Generalized-Born (Poisson-Boltzmann) surface area (MM/GB(PB)SA) is one of the most popular methods for binding free energy
Maohua Yang, Zonghua Bo, Tao Xu, Bo Xu, Dongdong Wang, Hang Zheng   +5 more
semanticscholar   +1 more source

Uni-O4: Unifying Online and Offline Deep Reinforcement Learning with Multi-Step On-Policy Optimization

International Conference on Learning Representations, 2023
Combining offline and online reinforcement learning (RL) is crucial for efficient and safe learning. However, previous approaches treat offline and online learning as separate procedures, resulting in redundant designs and limited performance.
Kun Lei, Zhengmao He, Chenhao Lu, Kaizhe Hu, Yang Gao, Huazhe Xu   +5 more
semanticscholar   +1 more source

Uni-Sign: Toward Unified Sign Language Understanding at Scale

International Conference on Learning Representations
Sign language pre-training has gained increasing attention for its ability to enhance performance across various sign language understanding (SLU) tasks.
Zecheng Li, Wen-gang Zhou, Weichao Zhao, Kepeng Wu, Hezhen Hu, Houqiang Li   +5 more
semanticscholar   +1 more source

2-mW-Output Power Uni-Traveling-Carrier Photodiodes in 300-GHz-Band

Asia-Pacific Microwave Conference, 2023
In this paper, we present a uni-traveling-carrier photodiode (UTC-PD) fabricated on a SiC substrate in order to increase saturated output power by improving the thermal management.
Takahiro Ohara, Tadao Ishibashi, Y. Kawamoto, Mizuki Tojo, Keisuke Maekawa, T. Nagatsuma   +5 more
semanticscholar   +1 more source

Uni-Retrieval: A Multi-Style Retrieval Framework for STEM's Education

Annual Meeting of the Association for Computational Linguistics
In AI-facilitated teaching, leveraging various query styles to interpret abstract text descriptions is crucial for ensuring high-quality teaching.
Yanhao Jia, Xinyi Wu, Hao Li, Qinglin Zhang, Yuxiao Hu, Shuai Zhao, Wenqi Fan   +6 more
semanticscholar   +1 more source

Uni-cot: Towards Unified Chain-of-Thought Reasoning Across Text and Vision

arXiv.org
Chain-of-Thought (CoT) reasoning has been widely adopted to enhance Large Language Models (LLMs) by decomposing complex tasks into simpler, sequential subtasks.
Luozheng Qin, Jia Gong, Yuqing Sun, Tianjiao Li, Mengping Yang, Xiaomeng Yang, Chao Qu, Zhiyu Tan, Hao Li   +8 more
semanticscholar   +1 more source

Uni-NaVid: A Video-based Vision-Language-Action Model for Unifying Embodied Navigation Tasks

arXiv.org
A practical navigation agent must be capable of handling a wide range of interaction demands, such as following instructions, searching objects, answering questions, tracking people, and more. Existing models for embodied navigation fall short of serving
Jiazhao Zhang, Kunyu Wang, Shaoan Wang, Minghan Li, Haoran Liu, Songlin Wei, Zhongyuan Wang, Zhizheng Zhang, He Wang   +8 more
semanticscholar   +1 more source

Ming-Lite-Uni: Advancements in Unified Architecture for Natural Multimodal Interaction

arXiv.org
We introduce Ming-Lite-Uni, an open-source multimodal framework featuring a newly designed unified visual generator and a native multimodal autoregressive model tailored for unifying vision and language. Specifically, this project provides an open-source
AI Inclusion, Biao Gong, Cheng Zou, Dandan Zheng, Hu Yu, Jingdong Chen, Jianxin Sun, Junbo Zhao, Jun Zhou, Kaixiang Ji, Lixiang Ru, Libin Wang, Qingpei Guo, Rui Liu, Weilong Chai, Xinyu Xiao, Ziyuan Huang   +16 more
semanticscholar   +1 more source

Uni-Mol2: Exploring Molecular Pretraining Model at Scale

Neural Information Processing Systems
In recent years, pretraining models have made significant advancements in the fields of natural language processing (NLP), computer vision (CV), and life sciences.
Xiaohong Ji, Zhen Wang, Zhifeng Gao, Hang Zheng, Linfeng Zhang, Guolin Ke, E. Weinan   +6 more
semanticscholar   +1 more source

Uni-MMMU: A Massive Multi-discipline Multimodal Unified Benchmark

arXiv.org
Unified multimodal models aim to jointly enable visual understanding and generation, yet current benchmarks rarely examine their true integration. Existing evaluations either treat the two abilities in isolation or overlook tasks that inherently couple ...
Kai Zou, Ziqi Huang, Yuhao Dong, Shulin Tian, Dian Zheng, Hongbo Liu, Jingwen He, Bin Liu, Yu Qiao, Ziwei Liu   +9 more
semanticscholar   +1 more source