Results 81 to 90 of about 127,235 (91)

Uni-Layout: Integrating Human Feedback in Unified Layout Generation and Evaluation

ACM Multimedia
Layout generation plays a crucial role in enhancing both user experience and design efficiency. However, current approaches suffer from task-specific generation capabilities and perceptually misaligned evaluation metrics, leading to limited applicability
Shuo Lu, Yanyin Chen, Wei Feng, Jiahao Fan, Fengheng Li, Zheng Zhang, Jingjing Lv, Jun-Jun Shen, Ching Law, Jianqiang Q. Liang   +9 more
semanticscholar   +1 more source

Photonics-assisted THz wireless communication enabled by wide-bandwidth packaged back-illuminated modified uni-traveling-carrier photodiode

Opto-Electronic Science
This paper presents a wide-bandwidth back-illuminated modified uni-traveling-carrier photodiode (MUTC-PD) packaged with standard WR-5 rectangular waveguide for high-speed wireless communications.
Yuxin Tian, Boyu Dong, Yaxuan Li, B. Xiong, Junwen Zhang, Changzheng Sun, Z. Hao, Jian Wang, Lai Wang, Yanjun Han, Hongtao Li, Lin Gan, Nan Chi, Yi Luo   +13 more
semanticscholar   +1 more source

Uni-Instruct: One-step Diffusion Model through Unified Diffusion Divergence Instruction

arXiv.org
In this paper, we unify more than 10 existing one-step diffusion distillation approaches, such as Diff-Instruct, DMD, SIM, SiD, $f$-distill, etc, inside a theory-driven framework which we name the \textbf{\emph{Uni-Instruct}}.
Yifei Wang, Weimin Bai, Colin Zhang, Debing Zhang, Weijian Luo, He Sun   +5 more
semanticscholar   +1 more source

Uni-VERSA: Versatile Speech Assessment with a Unified Network

Interspeech
Subjective listening tests remain the golden standard for speech quality assessment, but are costly, variable, and difficult to scale. In contrast, existing objective metrics, such as PESQ, F0 correlation, and DNSMOS, typically capture only specific ...
Jiatong Shi, Hye-jin Shim, Shinji Watanabe   +2 more
semanticscholar   +1 more source

Connect, Collapse, Corrupt: Learning Cross-Modal Tasks with Uni-Modal Data

International Conference on Learning Representations
Building cross-modal applications is challenging due to limited paired multi-modal data. Recent works have shown that leveraging a pre-trained multi-modal contrastive representation space enables cross-modal tasks to be learned from uni-modal data.
Yuhui Zhang, Elaine Sui, S. Yeung-Levy
semanticscholar   +1 more source

Uni-RLHF: Universal Platform and Benchmark Suite for Reinforcement Learning with Diverse Human Feedback

International Conference on Learning Representations
Reinforcement Learning with Human Feedback (RLHF) has received significant attention for performing tasks without the need for costly manual reward design by aligning human preferences.
Yifu Yuan, Jianye Hao, Yi Ma, Zibin Dong, Hebin Liang, Jinyi Liu, Zhixin Feng, Kai-Wen Zhao, Yan Zheng   +8 more
semanticscholar   +1 more source

Uni-Med: A Unified Medical Generalist Foundation Model For Multi-Task Learning Via Connector-MoE

Neural Information Processing Systems
Multi-modal large language models (MLLMs) have shown impressive capabilities as a general-purpose interface for various visual and linguistic tasks. However, building a unified MLLM for multi-task learning in the medical field remains a thorny challenge.
Xun Zhu, Ying Hu, Fanbin Mo, Miao Li, Ji Wu   +4 more
semanticscholar   +1 more source

Uni-Mol Docking V2: Towards Realistic and Accurate Binding Pose Prediction

arXiv.org
In recent years, machine learning (ML) methods have emerged as promising alternatives for molecular docking, offering the potential for high accuracy without incurring prohibitive computational costs.
Eric Alcaide, Zhifeng Gao, Guolin Ke, Yaqi Li, Linfeng Zhang, Hang Zheng, G. Zhou   +6 more
semanticscholar   +1 more source

Uni-to-Multi Modal Knowledge Distillation for Bidirectional LiDAR-Camera Semantic Segmentation

IEEE Transactions on Pattern Analysis and Machine Intelligence
Combining LiDAR points and images for robust semantic segmentation has shown great potential. However, the heterogeneity between the two modalities (e.g.
Tianfang Sun, Zhizhong Zhang, Xin Tan, Yong Peng, Yanyun Qu, Yuan Xie   +5 more
semanticscholar   +1 more source

Uni-Dubbing: Zero-Shot Speech Synthesis from Visual Articulation

Annual Meeting of the Association for Computational Linguistics
In the field of speech synthesis, there is a growing emphasis on employing multimodal speech to enhance robustness. A key challenge in this area is the scarcity of datasets that pair audio with corresponding video.
Songju Lei, Xize Cheng, Mengjiao Lyu, Jianqiao Hu, Jintao Tan, Runlin Liu, Lingyu Xiong, Tao Jin, Xiandong Li, Zhou Zhao   +9 more
semanticscholar   +1 more source