Zobrazeno 1 - 10
of 33
pro vyhledávání: '"Zheng, Chuanyang"'
Autor:
Xiong, Jing, Shen, Jianghan, Ye, Fanghua, Tao, Chaofan, Wan, Zhongwei, Lu, Jianqiao, Wu, Xun, Zheng, Chuanyang, Guo, Zhijiang, Kong, Lingpeng, Wong, Ngai
Deploying large language models (LLMs) is challenging due to their high memory and computational demands, especially during long-context inference. While key-value (KV) caching accelerates inference by reusing previously computed keys and values, it
Externí odkaz:
http://arxiv.org/abs/2410.03090
Autor:
Li, Zixuan, Xiong, Jing, Ye, Fanghua, Zheng, Chuanyang, Wu, Xun, Lu, Jianqiao, Wan, Zhongwei, Liang, Xiaodan, Li, Chengming, Sun, Zhenan, Kong, Lingpeng, Wong, Ngai
We present UncertaintyRAG, a novel approach for long-context Retrieval-Augmented Generation (RAG) that utilizes Signal-to-Noise Ratio (SNR)-based span uncertainty to estimate similarity between text chunks. This span uncertainty enhances model calibr
Externí odkaz:
http://arxiv.org/abs/2410.02719
The emergence of Large Language Models (LLMs) has improved the prospects for robotic tasks. However, existing benchmarks are still limited to single tasks with limited generalization capabilities. In this work, we introduce a comprehensive benchmark
Externí odkaz:
http://arxiv.org/abs/2406.03757
Autor:
Zheng, Chuanyang, Gao, Yihang, Shi, Han, Huang, Minbin, Li, Jingyao, Xiong, Jing, Ren, Xiaozhe, Ng, Michael, Jiang, Xin, Li, Zhenguo, Li, Yu
Positional encoding plays a crucial role in transformers, significantly impacting model performance and length generalization. Prior research has introduced absolute positional encoding (APE) and relative positional encoding (RPE) to distinguish toke
Externí odkaz:
http://arxiv.org/abs/2405.14722
Autor:
Gao, Yihang, Zheng, Chuanyang, Xie, Enze, Shi, Han, Hu, Tianyang, Li, Yu, Ng, Michael K., Li, Zhenguo, Liu, Zhaoqiang
Besides natural language processing, transformers exhibit extraordinary performance in solving broader applications, including scientific computing and computer vision. Previous works try to explain this from the expressive power and capability persp
Externí odkaz:
http://arxiv.org/abs/2402.13572
Autor:
Sun, Jiankai, Zheng, Chuanyang, Xie, Enze, Liu, Zhengying, Chu, Ruihang, Qiu, Jianing, Xu, Jiaqi, Ding, Mingyu, Li, Hongyang, Geng, Mengzhe, Wu, Yue, Wang, Wenhai, Chen, Junsong, Yin, Zhangyue, Ren, Xiaozhe, Fu, Jie, He, Junxian, Yuan, Wu, Liu, Qi, Liu, Xihui, Li, Yu, Dong, Hao, Cheng, Yu, Zhang, Ming, Heng, Pheng Ann, Dai, Jifeng, Luo, Ping, Wang, Jingdong, Wen, Ji-Rong, Qiu, Xipeng, Guo, Yike, Xiong, Hui, Liu, Qun, Li, Zhenguo
Reasoning, a crucial ability for complex problem-solving, plays a pivotal role in various real-world settings such as negotiation, medical diagnosis, and criminal investigation. It serves as a fundamental methodology in the field of Artificial Genera
Externí odkaz:
http://arxiv.org/abs/2312.11562
We seek to accelerate research in developing rich, multimodal scene models trained from egocentric data, based on differentiable volumetric ray-tracing inspired by Neural Radiance Fields (NeRFs). The construction of a NeRF-like model from an egocentr
Externí odkaz:
http://arxiv.org/abs/2311.06455
Autor:
Xiong, Jing, Shen, Jianhao, Yuan, Ye, Wang, Haiming, Yin, Yichun, Liu, Zhengying, Li, Lin, Guo, Zhijiang, Cao, Qingxing, Huang, Yinya, Zheng, Chuanyang, Liang, Xiaodan, Zhang, Ming, Liu, Qun
Automated theorem proving (ATP) has become an appealing domain for exploring the reasoning ability of the recent successful generative language models. However, current ATP benchmarks mainly focus on symbolic inference, but rarely involve the underst
Externí odkaz:
http://arxiv.org/abs/2310.10180
Autor:
Xiong, Jing, Li, Zixuan, Zheng, Chuanyang, Guo, Zhijiang, Yin, Yichun, Xie, Enze, Yang, Zhicheng, Cao, Qingxing, Wang, Haiming, Han, Xiongwei, Tang, Jing, Li, Chengming, Liang, Xiaodan
Recent advances in natural language processing, primarily propelled by Large Language Models (LLMs), have showcased their remarkable capabilities grounded in in-context learning. A promising avenue for guiding LLMs in intricate reasoning tasks involv
Externí odkaz:
http://arxiv.org/abs/2310.02954
Autor:
Wang, Haiming, Xin, Huajian, Zheng, Chuanyang, Li, Lin, Liu, Zhengying, Cao, Qingxing, Huang, Yinya, Xiong, Jing, Shi, Han, Xie, Enze, Yin, Jian, Li, Zhenguo, Liao, Heng, Liang, Xiaodan
Despite the success of large language models (LLMs), the task of theorem proving still remains one of the hardest reasoning tasks that is far from being fully solved. Prior methods using language models have demonstrated promising results, but they s
Externí odkaz:
http://arxiv.org/abs/2310.00656