Zobrazeno 1 - 10
of 748
pro vyhledávání: '"Yang Yaodong"'
Autor:
Wang, Qianxu, Deng, Congyue, Lum, Tyler Ga Wei, Chen, Yuanpei, Yang, Yaodong, Bohg, Jeannette, Zhu, Yixin, Guibas, Leonidas
One-shot transfer of dexterous grasps to novel scenes with object and context variations has been a challenging problem. While distilled feature fields from large vision models have enabled semantic correspondences across 3D scenes, their features ar
Externí odkaz:
http://arxiv.org/abs/2410.23039
Autor:
Wang, Mingzhi, Ma, Chengdong, Chen, Qizhi, Meng, Linjian, Han, Yang, Xiao, Jiancong, Zhang, Zhaowei, Huo, Jing, Su, Weijie J., Yang, Yaodong
Self-play methods have demonstrated remarkable success in enhancing model capabilities across various domains. In the context of Reinforcement Learning from Human Feedback (RLHF), self-play not only boosts Large Language Model (LLM) performance but a
Externí odkaz:
http://arxiv.org/abs/2410.16714
In multi-agent reinforcement learning, a commonly considered paradigm is centralized training with decentralized execution. However, in this framework, decentralized execution restricts the development of coordinated policies due to the local observa
Externí odkaz:
http://arxiv.org/abs/2410.15841
Autor:
Liu, Naming, Wang, Mingzhi, Wang, Xihuai, Zhang, Weinan, Yang, Yaodong, Zhang, Youzhi, An, Bo, Wen, Ying
The ex ante equilibrium for two-team zero-sum games, where agents within each team collaborate to compete against the opposing team, is known to be the best a team can do for coordination. Many existing works on ex ante equilibrium solutions are aimi
Externí odkaz:
http://arxiv.org/abs/2410.01575
Aligning the behavior of Large language models (LLMs) with human intentions and values remains a critical challenge. Reinforcement learning from human feedback (RLHF) aligns LLMs by training a reward model (RM) on human preferences and fine-tuning th
Externí odkaz:
http://arxiv.org/abs/2409.00162
Autor:
Zhang, Ruize, Xu, Zelai, Ma, Chengdong, Yu, Chao, Tu, Wei-Wei, Huang, Shiyu, Ye, Deheng, Ding, Wenbo, Yang, Yaodong, Wang, Yu
Self-play, characterized by agents' interactions with copies or past versions of itself, has recently gained prominence in reinforcement learning. This paper first clarifies the preliminaries of self-play, including the multi-agent reinforcement lear
Externí odkaz:
http://arxiv.org/abs/2408.01072
Frontier AI systems, including large language models (LLMs), hold increasing influence over the epistemology of human users. Such influence can reinforce prevailing societal values, potentially contributing to the lock-in of misguided moral beliefs a
Externí odkaz:
http://arxiv.org/abs/2406.20087
Autor:
Ji, Jiaming, Hong, Donghai, Zhang, Borong, Chen, Boyuan, Dai, Josef, Zheng, Boren, Qiu, Tianyi, Li, Boxun, Yang, Yaodong
In this work, we introduce the PKU-SafeRLHF dataset, designed to promote research on safety alignment in large language models (LLMs). As a sibling project to SafeRLHF and BeaverTails, we separate annotations of helpfulness and harmlessness for quest
Externí odkaz:
http://arxiv.org/abs/2406.15513
To mitigate the risk of harmful outputs from large vision models (LVMs), we introduce the SafeSora dataset to promote research on aligning text-to-video generation with human values. This dataset encompasses human preferences in text-to-video generat
Externí odkaz:
http://arxiv.org/abs/2406.14477
Autor:
Qi, Siyuan, Yang, Bangcheng, Jiang, Kailin, Wang, Xiaobo, Li, Jiaqi, Zhong, Yifan, Yang, Yaodong, Zheng, Zilong
In scenarios where language models must incorporate new information efficiently without extensive retraining, traditional fine-tuning methods are prone to overfitting, degraded generalization, and unnatural language generation. To address these limit
Externí odkaz:
http://arxiv.org/abs/2406.11194