Zobrazeno 1 - 10
of 1 832 958
pro vyhledávání: '"refine"'
Autor:
Guo, Hongming, Fu, Ruibo, Geng, Yizhong, Liu, Shuai, Shi, Shuchen, Wang, Tao, Qiang, Chunyu, Li, Chenxing, Li, Ya, Wen, Zhengqi, Liu, Yukun, Liu, Xuefei
Text-to-audio (TTA) model is capable of generating diverse audio from textual prompts. However, most mainstream TTA models, which predominantly rely on Mel-spectrograms, still face challenges in producing audio with rich content. The intricate detail
Externí odkaz:
http://arxiv.org/abs/2412.08577
Autor:
Yu, Dian, Zhang, Yuheng, Xu, Jiahao, Liang, Tian, Song, Linfeng, Tu, Zhaopeng, Mi, Haitao, Yu, Dong
Large language models (LLMs) can refine their responses based on feedback, enabling self-improvement through iterative training or test-time refinement. However, existing methods predominantly focus on refinement within the same reasoning format, whi
Externí odkaz:
http://arxiv.org/abs/2412.16871
Retrieve-augmented generation (RAG) frameworks have emerged as a promising solution to multi-hop question answering(QA) tasks since it enables large language models (LLMs) to incorporate external knowledge and mitigate their inherent knowledge defici
Externí odkaz:
http://arxiv.org/abs/2412.15101
Autor:
Schneider, Johannes
Autoregressive language models like GPT aim at predicting next tokens, while autoencoding models such as BERT are trained on tasks such as predicting masked tokens. We train a decoder only architecture for predicting the second last token for a seque
Externí odkaz:
http://arxiv.org/abs/2411.15661
Mathematical reasoning has proven to be a critical yet challenging task for large language models (LLMs), as they often struggle with complex multi-step problems. To address these limitations, we introduce the Monte Carlo Nash Equilibrium Self-Refine
Externí odkaz:
http://arxiv.org/abs/2411.15645
Autor:
Song, Yizhi, He, Liu, Zhang, Zhifei, Kim, Soo Ye, Zhang, He, Xiong, Wei, Lin, Zhe, Price, Brian, Cohen, Scott, Zhang, Jianming, Aliaga, Daniel
Personalized image generation has emerged from the recent advancements in generative models. However, these generated personalized images often suffer from localized artifacts such as incorrect logos, reducing fidelity and fine-grained identity detai
Externí odkaz:
http://arxiv.org/abs/2412.00306
Open-set Domain Adaptation (OSDA) aims to adapt a model from a labeled source domain to an unlabeled target domain, where novel classes - also referred to as target-private unknown classes - are present. Source-free Open-set Domain Adaptation (SF-OSD
Externí odkaz:
http://arxiv.org/abs/2411.12558
Spatiotemporal data imputation plays a crucial role in various fields such as traffic flow monitoring, air quality assessment, and climate prediction. However, spatiotemporal data collected by sensors often suffer from temporal incompleteness, and th
Externí odkaz:
http://arxiv.org/abs/2412.12642
Autor:
Lynse Allen
In a world where the only known constant is change, adapting and evolving to meet the needs of your employer can be overwhelming, frustrating, and depressing. Whether you need to find work-life health, solve unexpected roadblocks quicker, take on add
Recent studies show that LLMs, particularly open-source models, struggle to follow complex instructions with multiple constraints. Despite the importance, methods to improve LLMs' adherence to such constraints remain unexplored, and current research
Externí odkaz:
http://arxiv.org/abs/2410.12207