Zobrazeno 1 - 10
of 133
pro vyhledávání: '"Wei, Yuxiang"'
Recent studies have been increasingly demonstrating that high-quality data is crucial for effective pretraining of language models. However, the precise definition of "high-quality" remains underexplored. Focusing on the code domain, we introduce Arc
Externí odkaz:
http://arxiv.org/abs/2409.02326
Recent advances in deep learning structured state space models, especially the Mamba architecture, have demonstrated remarkable performance improvements while maintaining linear complexity. In this study, we introduce functional spatiotemporal Mamba
Externí odkaz:
http://arxiv.org/abs/2408.13074
As a key component in boosting online user growth, uplift modeling aims to measure individual user responses (e.g., whether to play the game) to various treatments, such as gaming bonuses, thereby enhancing business outcomes. However, previous resear
Externí odkaz:
http://arxiv.org/abs/2408.12803
We introduce Differential Performance Evaluation (DPE), a framework designed to reliably evaluate Large Language Models (LLMs) for efficient code generation. Traditional coding benchmarks often fail to provide reliable insights into code efficiency,
Externí odkaz:
http://arxiv.org/abs/2408.06450
Alzheimer's disease (AD) progresses from asymptomatic changes to clinical symptoms, emphasizing the importance of early detection for proper treatment. Functional magnetic resonance imaging (fMRI), particularly dynamic functional network connectivity
Externí odkaz:
http://arxiv.org/abs/2408.00378
By leveraging the text-to-image diffusion priors, score distillation can synthesize 3D contents without paired text-3D training data. Instead of spending hours of online optimization per text prompt, recent studies have been focused on learning a tex
Externí odkaz:
http://arxiv.org/abs/2407.02040
Autor:
Liu, Jiawei, Tian, Jia Le, Daita, Vijay, Wei, Yuxiang, Ding, Yifeng, Wang, Yuhan Katherine, Yang, Jun, Zhang, Lingming
Recent advances have been improving the context windows of Large Language Models (LLMs). To quantify the real long-context capabilities of LLMs, evaluators such as the popular Needle in a Haystack have been developed to test LLMs over a large chunk o
Externí odkaz:
http://arxiv.org/abs/2406.06025
Text-to-image (T2I) diffusion models have shown significant success in personalized text-to-image generation, which aims to generate novel images with human identities indicated by the reference images. Despite promising identity fidelity has been ac
Externí odkaz:
http://arxiv.org/abs/2405.05806
We introduce XFT, a simple yet powerful training scheme, by simply merging upcycled Mixture-of-Experts (MoE) to unleash the performance limit of instruction-tuned code Large Language Models (LLMs). While vanilla sparse upcycling fails to improve inst
Externí odkaz:
http://arxiv.org/abs/2404.15247
Autor:
Liu, Xiaoyu, Wei, Yuxiang, Liu, Ming, Lin, Xianhui, Ren, Peiran, Xie, Xuansong, Zuo, Wangmeng
Human visual imagination usually begins with analogies or rough sketches. For example, given an image with a girl playing guitar before a building, one may analogously imagine how it seems like if Iron Man playing guitar before Pyramid in Egypt. None
Externí odkaz:
http://arxiv.org/abs/2404.06451