Zobrazeno 1 - 10
of 190 117
pro vyhledávání: '"A, Chow"'
Autor:
Chow, Yinlam, Tennenholtz, Guy, Gur, Izzeddin, Zhuang, Vincent, Dai, Bo, Thiagarajan, Sridhar, Boutilier, Craig, Agarwal, Rishabh, Kumar, Aviral, Faust, Aleksandra
Recent studies have indicated that effectively utilizing inference-time compute is crucial for attaining better performance from large language models (LLMs). In this work, we propose a novel inference-aware fine-tuning paradigm, in which the model i
Externí odkaz:
http://arxiv.org/abs/2412.15287
The growing concern over data privacy, the benefits of utilizing data from diverse sources for model training, and the proliferation of networked devices with enhanced computational capabilities have all contributed to the rise of federated learning
Externí odkaz:
http://arxiv.org/abs/2412.12640
We investigate the metric theory of Diophantine approximation on missing-digit fractals. In particular, we establish analogues of Khinchin's theorem and Gallagher's theorem, as well as inhomogeneous generalisations.
Comment: 36 pages
Comment: 36 pages
Externí odkaz:
http://arxiv.org/abs/2412.12070
This work concerns the zeroth-order global minimization of continuous nonconvex functions with a unique global minimizer and possibly multiple local minimizers. We formulate a theoretical framework for inexact proximal point (IPP) methods for global
Externí odkaz:
http://arxiv.org/abs/2412.11485
Autor:
Nabati, Ofir, Tennenholtz, Guy, Hsu, ChihWei, Ryu, Moonkyung, Ramachandran, Deepak, Chow, Yinlam, Li, Xiang, Boutilier, Craig
We address the problem of personalized, interactive text-to-image (T2I) generation, designing a reinforcement learning (RL) agent which iteratively improves a set of generated images for a user through a sequence of prompt expansions. Using human rat
Externí odkaz:
http://arxiv.org/abs/2412.10419
As Graph Neural Networks (GNNs) become increasingly popular for learning from large-scale graph data across various domains, their susceptibility to adversarial attacks when using graph reduction techniques for scalability remains underexplored. In t
Externí odkaz:
http://arxiv.org/abs/2412.05883
Large language models (LLMs) are increasingly used in applications where LLM inputs may span many different tasks. Recent work has found that the choice of LLM is consequential, and different LLMs may be good for different input samples. Prior approa
Externí odkaz:
http://arxiv.org/abs/2412.04692
Autor:
Su, Haoran, Chow, Joseph Y. J.
Emergency response times are critical in densely populated urban environments like New York City (NYC), where traffic congestion significantly impedes emergency vehicle (EMV) mobility. This study introduces an intersection-aware emergency medical ser
Externí odkaz:
http://arxiv.org/abs/2412.04369
Autor:
Bai, Jinbin, Chow, Wei, Yang, Ling, Li, Xiangtai, Li, Juncheng, Zhang, Hanwang, Yan, Shuicheng
We present HumanEdit, a high-quality, human-rewarded dataset specifically designed for instruction-guided image editing, enabling precise and diverse image manipulations through open-form language instructions. Previous large-scale editing datasets o
Externí odkaz:
http://arxiv.org/abs/2412.04280
Autor:
Zhang, Junyuan, Zhang, Qintong, Wang, Bin, Ouyang, Linke, Wen, Zichen, Li, Ying, Chow, Ka-Ho, He, Conghui, Zhang, Wentao
Retrieval-augmented Generation (RAG) enhances Large Language Models (LLMs) by integrating external knowledge to reduce hallucinations and incorporate up-to-date information without retraining. As an essential part of RAG, external knowledge bases are
Externí odkaz:
http://arxiv.org/abs/2412.02592