Zobrazeno 1 - 10
of 24 303
pro vyhledávání: '"An, Chenguang"'
Autor:
Xiao, Chenguang, Wang, Shuo
Data Heterogeneity is a major challenge of Federated Learning performance. Recently, momentum based optimization techniques have beed proved to be effective in mitigating the heterogeneity issue. Along with the model updates, the momentum updates are
Externí odkaz:
http://arxiv.org/abs/2411.19798
Autor:
Yu, Yue, Chen, Zhengxing, Zhang, Aston, Tan, Liang, Zhu, Chenguang, Pang, Richard Yuanzhe, Qian, Yundi, Wang, Xuewei, Gururangan, Suchin, Zhang, Chao, Kambadur, Melanie, Mahajan, Dhruv, Hou, Rui
Reward modeling is crucial for aligning large language models (LLMs) with human preferences, especially in reinforcement learning from human feedback (RLHF). However, current reward models mainly produce scalar scores and struggle to incorporate crit
Externí odkaz:
http://arxiv.org/abs/2411.16646
Autor:
Wang, Yutong, Teng, Jiajie, Cao, Jiajiong, Li, Yuming, Ma, Chenguang, Xu, Hongteng, Luo, Dixin
As a very common type of video, face videos often appear in movies, talk shows, live broadcasts, and other scenes. Real-world online videos are often plagued by degradations such as blurring and quantization noise, due to the high compression ratio c
Externí odkaz:
http://arxiv.org/abs/2411.16468
Autor:
Song, Yuhang, Gianni, Mario, Yang, Chenguang, Lin, Kunyang, Chiu, Te-Chuan, Nguyen, Anh, Lee, Chun-Yi
This paper addresses the challenge of fine-grained alignment in Vision-and-Language Navigation (VLN) tasks, where robots navigate realistic 3D environments based on natural language instructions. Current approaches use contrastive learning to align l
Externí odkaz:
http://arxiv.org/abs/2411.14811
This paper presents a novel approach for nonlinear assimilation called score-based sequential Langevin sampling (SSLS) within a recursive Bayesian framework. SSLS decomposes the assimilation process into a sequence of prediction and update steps, uti
Externí odkaz:
http://arxiv.org/abs/2411.13443
Modern AI- and Data-intensive software systems rely heavily on data science and machine learning libraries that provide essential algorithmic implementations and computational frameworks. These libraries expose complex APIs whose correct usage has to
Externí odkaz:
http://arxiv.org/abs/2411.11410
Autor:
Tu, Jianhong, Ni, Zhuohao, Crispino, Nicholas, Yu, Zihao, Bendersky, Michael, Gunel, Beliz, Jia, Ruoxi, Liu, Xin, Lyu, Lingjuan, Song, Dawn, Wang, Chenguang
We present a novel instruction tuning recipe to improve the zero-shot task generalization of multimodal large language models. In contrast to existing instruction tuning mechanisms that heavily rely on visual instructions, our approach focuses on lan
Externí odkaz:
http://arxiv.org/abs/2411.10557
Recent work on human animation usually involves audio, pose, or movement maps conditions, thereby achieves vivid animation quality. However, these methods often face practical challenges due to extra control conditions, cumbersome condition injection
Externí odkaz:
http://arxiv.org/abs/2411.10061
The Travelling Salesman Problem (TSP) remains a fundamental challenge in combinatorial optimization, inspiring diverse algorithmic strategies. This paper revisits the "heatmap + Monte Carlo Tree Search (MCTS)" paradigm that has recently gained tracti
Externí odkaz:
http://arxiv.org/abs/2411.09238
Quantum information entropy is regarded as a measure of coherence between the observed system and the environment or between many-body. It is commonly described as the uncertainty and purity of a mixed state of a quantum system. Different from tradit
Externí odkaz:
http://arxiv.org/abs/2411.09150