Zobrazeno 1 - 10
of 3 681
pro vyhledávání: '"DING Liang"'
Publikováno v:
E3S Web of Conferences, Vol 522, p 01044 (2024)
With the quickly development of the Internet of Things technology, Bluetooth (BLE) protocol has been increasingly adopted in consumer communication applications, industry communication utilization, and even positioning requirement, due to its advanta
Externí odkaz:
https://doaj.org/article/f3333a28db9c42b1b29d940cf98f10ad
Despite their impressive capabilities, large language models (LLMs) often lack interpretability and can generate toxic content. While using LLMs as foundation models and applying semantic steering methods are widely practiced, we believe that efficie
Externí odkaz:
http://arxiv.org/abs/2410.17714
Large Language Models (LLMs) have shown promising performance in text-to-SQL, which involves translating natural language questions into SQL queries. However, current text-to-SQL LLMs are computationally expensive and challenging to deploy in real-wo
Externí odkaz:
http://arxiv.org/abs/2410.11371
Fine-tuning is powerful for adapting large language models to downstream tasks, but it often results in huge memory usages. A promising approach to mitigate this is using Zeroth-Order (ZO) optimization, which estimates gradients to replace First-Orde
Externí odkaz:
http://arxiv.org/abs/2410.09823
Large language models (LLMs) exhibit remarkable performance across diverse tasks, indicating their potential for expansion into large speech-text models (LSMs) by integrating speech capabilities. Although unified speech-text pre-training and multimod
Externí odkaz:
http://arxiv.org/abs/2410.03798
Autor:
Hong, Bin, Wu, Jinze, Liu, Jiayu, Ding, Liang, Sha, Jing, Zhang, Kai, Wang, Shijin, Huang, Zhenya
In recent years, the breakthrough of Large Language Models (LLMs) offers new ideas for achieving universal methods on graph data. The common practice of converting graphs into natural language for LLMs, which refers to graph flattening, exhibits good
Externí odkaz:
http://arxiv.org/abs/2409.14880
Large Language Models (LLMs) have shown significant potential as judges for Machine Translation (MT) quality assessment, providing both scores and fine-grained feedback. Although approaches such as GEMBA-MQM has shown SOTA performance on reference-fr
Externí odkaz:
http://arxiv.org/abs/2409.14335
Knowledge distillation (KD) is a technique that compresses large teacher models by training smaller student models to mimic them. The success of KD in auto-regressive language models mainly relies on Reverse KL for mode-seeking and student-generated
Externí odkaz:
http://arxiv.org/abs/2409.12512
Large language models (LLMs) have shown remarkable capabilities in code generation. However, the effects of hallucinations (e.g., output noise) make it particularly challenging for LLMs to generate high-quality code in one pass. In this work, we prop
Externí odkaz:
http://arxiv.org/abs/2409.05923
Multimodal large language models (MLLMs) have experienced significant advancements recently, but still struggle to recognize and interpret intricate details in high-resolution (HR) images effectively. While state-of-the-art (SOTA) MLLMs claim to proc
Externí odkaz:
http://arxiv.org/abs/2408.15556