Zobrazeno 1 - 10
of 5 890
pro vyhledávání: '"ZHENG, LIN"'
Autor:
Gong, Shansan, Agarwal, Shivam, Zhang, Yizhe, Ye, Jiacheng, Zheng, Lin, Li, Mukai, An, Chenxin, Zhao, Peilin, Bi, Wei, Han, Jiawei, Peng, Hao, Kong, Lingpeng
Diffusion Language Models (DLMs) have emerged as a promising new paradigm for text generative modeling, potentially addressing limitations of autoregressive (AR) models. However, current DLMs have been studied at a smaller scale compared to their AR
Externí odkaz:
http://arxiv.org/abs/2410.17891
Autor:
Ye, Jiacheng, Gao, Jiahui, Gong, Shansan, Zheng, Lin, Jiang, Xin, Li, Zhenguo, Kong, Lingpeng
Autoregressive language models, despite their impressive capabilities, struggle with complex reasoning and long-term planning tasks. We introduce discrete diffusion models as a novel solution to these challenges. Through the lens of subgoal imbalance
Externí odkaz:
http://arxiv.org/abs/2410.14157
Formal theorem proving, a field at the intersection of mathematics and computer science, has seen renewed interest with advancements in large language models (LLMs). This paper introduces SubgoalXL, a novel approach that synergizes subgoal-based proo
Externí odkaz:
http://arxiv.org/abs/2408.11172
Autor:
Ye, Jiacheng, Gong, Shansan, Chen, Liheng, Zheng, Lin, Gao, Jiahui, Shi, Han, Wu, Chuan, Jiang, Xin, Li, Zhenguo, Bi, Wei, Kong, Lingpeng
Recently, diffusion models have garnered significant interest in the field of text processing due to their many potential advantages compared to conventional autoregressive models. In this work, we propose Diffusion-of-Thought (DoT), a novel approach
Externí odkaz:
http://arxiv.org/abs/2402.07754
Efficient attentions have greatly improved the computational efficiency of Transformers. However, most existing linear attention mechanisms suffer from an \emph{efficiency degradation} problem, leading to inefficiencies in causal language modeling an
Externí odkaz:
http://arxiv.org/abs/2312.11135
This work introduces self-infilling code generation, a general framework that incorporates infilling operations into auto-regressive decoding. Our approach capitalizes on the observation that recent infilling-capable code language models can self-inf
Externí odkaz:
http://arxiv.org/abs/2311.17972
Autor:
Chenhui Zhou, Lu Li, Zhaoqi Dong, Fan Lv, Hongyu Guo, Kai Wang, Menggang Li, Zhengyi Qian, Na Ye, Zheng Lin, Mingchuan Luo, Shaojun Guo
Publikováno v:
Nature Communications, Vol 15, Iss 1, Pp 1-9 (2024)
Abstract Ruthenium (Ru) is widely recognized as a low-cost alternative to iridium as anode electrocatalyst in proton-exchange membrane water electrolyzers (PEMWE). However, the reported Ru-based catalysts usually only operate within tens of hours in
Externí odkaz:
https://doaj.org/article/9240d69ff1044dc786122d3e3fdf2ddb
Autoregressive~(AR) generation almost dominates sequence generation for its efficacy. Recently, non-autoregressive~(NAR) generation gains increasing popularity for its efficiency and growing efficacy. However, its efficiency is still bottlenecked by
Externí odkaz:
http://arxiv.org/abs/2310.09512
Autor:
Zheng, Hui, Chen, Zhong-Tao, Wang, Hai-Teng, Zhou, Jian-Yang, Zheng, Lin, Lin, Pei-Yang, Liu, Yun-Zhe
Understanding semantic content from brain activity during sleep represents a major goal in neuroscience. While studies in rodents have shown spontaneous neural reactivation of memories during sleep, capturing the semantic content of human sleep poses
Externí odkaz:
http://arxiv.org/abs/2309.16457
This paper investigates the impact of data volume and the use of similar languages on transfer learning in a machine translation task. We find out that having more data generally leads to better performance, as it allows the model to learn more patte
Externí odkaz:
http://arxiv.org/abs/2306.00660