Zobrazeno 1 - 10
of 4 999
pro vyhledávání: '"Zhang, Yiming"'
Autor:
Chi, Jianfeng, Karn, Ujjwal, Zhan, Hongyuan, Smith, Eric, Rando, Javier, Zhang, Yiming, Plawiak, Kate, Coudert, Zacharie Delpierre, Upasani, Kartikeya, Pasupuleti, Mahesh
We introduce Llama Guard 3 Vision, a multimodal LLM-based safeguard for human-AI conversations that involves image understanding: it can be used to safeguard content for both multimodal LLM inputs (prompt classification) and outputs (response classif
Externí odkaz:
http://arxiv.org/abs/2411.10414
Autor:
Huang, Chao, Xiao, Huichen, Chen, Chen, Chen, Chunyan, Zhao, Yi, Du, Shiyu, Zhang, Yiming, Sha, He, Gu, Ruixin
As the application of large language models in various fields continues to expand, materials science also ushers in opportunities for AI-driven innovation. The traditional way of relying on manual search for materials science-related information is n
Externí odkaz:
http://arxiv.org/abs/2411.08728
Autor:
Zhao, Yilun, Long, Yitao, Jiang, Yuru, Wang, Chengye, Chen, Weiyuan, Liu, Hongjun, Zhang, Yiming, Tang, Xiangru, Zhao, Chen, Cohan, Arman
We introduce FinDVer, a comprehensive benchmark specifically designed to evaluate the explainable claim verification capabilities of LLMs in the context of understanding and analyzing long, hybrid-content financial documents. FinDVer contains 2,400 e
Externí odkaz:
http://arxiv.org/abs/2411.05764
Autor:
Chuang, Alexander Y., Bui, Huan Q., Christianen, Arthur, Zhang, Yiming, Ni, Yiqi, Ahmed-Braun, Denise, Robens, Carsten, Zwierlein, Martin W.
The quantum mechanics of three interacting particles gives rise to interesting universal phenomena, such as the staircase of Efimov trimers predicted in the context of nuclear physics and observed in ultracold gases. Here, we observe a novel type of
Externí odkaz:
http://arxiv.org/abs/2411.04820
Autor:
Zhang, Yiming, Rando, Javier, Evtimov, Ivan, Chi, Jianfeng, Smith, Eric Michael, Carlini, Nicholas, Tramèr, Florian, Ippolito, Daphne
Large language models are pre-trained on uncurated text datasets consisting of trillions of tokens scraped from the Web. Prior work has shown that: (1) web-scraped pre-training datasets can be practically poisoned by malicious actors; and (2) adversa
Externí odkaz:
http://arxiv.org/abs/2410.13722
Autor:
Zhang, Yiming, He, Baoyi, Zhang, Shengyu, Fu, Yuhao, Zhou, Qi, Sang, Zhijie, Hong, Zijin, Yang, Kejing, Wang, Wenjun, Yuan, Jianbo, Ning, Guanghan, Li, Linyi, Ji, Chunlin, Wu, Fei, Yang, Hongxia
Recent advancements in building domain-specific large language models (LLMs) have shown remarkable success, especially in tasks requiring reasoning abilities like logical inference over complex relationships and multi-step problem solving. However, c
Externí odkaz:
http://arxiv.org/abs/2410.13699
Chess has long been a testbed for AI's quest to match human intelligence, and in recent years, chess AI systems have surpassed the strongest humans at the game. However, these systems are not human-aligned; they are unable to match the skill levels o
Externí odkaz:
http://arxiv.org/abs/2410.03893
Despite much progress in large 3D datasets there are currently few interactive 3D object datasets, and their scale is limited due to the manual effort required in their construction. We introduce the static to openable (S2O) task which creates intera
Externí odkaz:
http://arxiv.org/abs/2409.18896
Autor:
Zhang, Yiming, Chi, Jianfeng, Nguyen, Hailey, Upasani, Kartikeya, Bikel, Daniel M., Weston, Jason, Smith, Eric Michael
Text generation has a fundamental limitation almost by definition: there is no taking back tokens that have been generated, even when they are clearly problematic. In the context of language model safety, when a partial unsafe generation is produced,
Externí odkaz:
http://arxiv.org/abs/2409.14586
Autor:
Zhang, Chuqi, Zeng, Jun, Zhang, Yiming, Ahmad, Adil, Zhang, Fengwei, Jin, Hai, Liang, Zhenkai
Protecting system observability records (logs) from compromised OSs has gained significant traction in recent times, with several note-worthy approaches proposed. Unfortunately, none of the proposed approaches achieve high performance with tiny log p
Externí odkaz:
http://arxiv.org/abs/2409.04484