Zobrazeno 1 - 10
of 56
pro vyhledávání: '"Shen, William"'
Autor:
Qiu, Xinchi, Shen, William F., Chen, Yihong, Cancedda, Nicola, Stenetorp, Pontus, Lane, Nicholas D.
Recently, machine unlearning, which seeks to erase specific data stored in the pre-trained or fine-tuned models, has emerged as a crucial protective measure for LLMs. However, unlearning approaches for LLMs that have been considered thus far have foc
Externí odkaz:
http://arxiv.org/abs/2406.16810
Autor:
Marino, Bill, Chaudhary, Yaqub, Pi, Yulu, Yew, Rui-Jie, Aleksandrov, Preslav, Rahman, Carwyn, Shen, William F., Robinson, Isaac, Lane, Nicholas D.
As the AI supply chain grows more complex, AI systems and models are increasingly likely to incorporate multiple internally- or externally-sourced components such as datasets and (pre-trained) models. In such cases, determining whether or not the agg
Externí odkaz:
http://arxiv.org/abs/2406.14758
Autor:
Iacob, Alex, Sani, Lorenzo, Marino, Bill, Aleksandrov, Preslav, Shen, William F., Lane, Nicholas Donald
The reliance of language model training on massive amounts of computation and vast datasets scraped from potentially low-quality, copyrighted, or sensitive data has come into question practically, legally, and ethically. Federated learning provides a
Externí odkaz:
http://arxiv.org/abs/2405.14446
Autor:
Sani, Lorenzo, Iacob, Alex, Cao, Zeyu, Marino, Bill, Gao, Yan, Paulik, Tomas, Zhao, Wanru, Shen, William F., Aleksandrov, Preslav, Qiu, Xinchi, Lane, Nicholas D.
Generative pre-trained large language models (LLMs) have demonstrated impressive performance over a wide range of tasks, thanks to the unprecedented amount of data they have been trained on. As established scaling laws indicate, LLMs' future performa
Externí odkaz:
http://arxiv.org/abs/2405.10853
Autor:
Shen, William
Self-supervised and language-supervised image models contain rich knowledge of the world that is important for generalization. Many robotic tasks, however, require a detailed understanding of 3D geometry, which is often lacking in 2D image features.
Autor:
Miller, Kristina, Zeitler, Christopher K., Shen, William, Hobbs, Kerianne, Mitra, Sayan, Schierman, John, Viswanathan, Mahesh
A runtime assurance system (RTA) for a given plant enables the exercise of an untrusted or experimental controller while assuring safety with a backup (or safety) controller. The relevant computational design problem is to create a logic that assures
Externí odkaz:
http://arxiv.org/abs/2310.04288
Self-supervised and language-supervised image models contain rich knowledge of the world that is important for generalization. Many robotic tasks, however, require a detailed understanding of 3D geometry, which is often lacking in 2D image features.
Externí odkaz:
http://arxiv.org/abs/2308.07931
Runtime assurance (RTA) addresses the problem of keeping an autonomous system safe while using an untrusted (or experimental) controller. This can be done via logic that explicitly switches between the untrusted controller and a safety controller, or
Externí odkaz:
http://arxiv.org/abs/2306.04585
Autor:
Qiu, Xinchi, Pan, Heng, Zhao, Wanru, Gao, Yan, Gusmao, Pedro P. B., Shen, William F., Ma, Chenyang, Lane, Nicholas D.
Most work in privacy-preserving federated learning (FL) has focused on horizontally partitioned datasets where clients hold the same features and train complete client-level models independently. However, individual data points are often scattered ac
Externí odkaz:
http://arxiv.org/abs/2305.16794
We present the first approach capable of learning domain-independent planning heuristics entirely from scratch. The heuristics we learn map the hypergraph representation of the delete-relaxation of the planning problem at hand, to a cost estimate tha
Externí odkaz:
http://arxiv.org/abs/1911.13101