Zobrazeno 1 - 10
of 740
pro vyhledávání: '"Zhou Tianyi"'
Publikováno v:
Redai dili, Vol 44, Iss 3, Pp 505-519 (2024)
Using the Pearl River Delta urban agglomeration as the research area, this study comprehensively uses an interlocking network model and social network analysis to construct a network based on the headquarters branch data of digital economy listed ent
Externí odkaz:
https://doaj.org/article/1e927e62dd6e4e22871ed567f749e4bb
Adversarial audio attacks pose a significant threat to the growing use of large language models (LLMs) in voice-based human-machine interactions. While existing research has primarily focused on model-specific adversarial methods, real-world applicat
Externí odkaz:
http://arxiv.org/abs/2411.14842
This paper aims to reconstruct hundreds of people's 3D poses, shapes, and locations from a single image with unknown camera parameters. Due to the small and highly varying 2D human scales, depth ambiguity, and perspective distortion, no existing meth
Externí odkaz:
http://arxiv.org/abs/2411.06232
Large Language Models (LLMs) have become essential in advancing natural language processing (NLP) tasks, but their sequential token generation limits inference speed. Multi-Draft Speculative Decoding (MDSD) offers a promising solution by using a smal
Externí odkaz:
http://arxiv.org/abs/2411.05289
Autor:
Nguyen, Dang, Lai, Viet Dac, Yoon, Seunghyun, Rossi, Ryan A., Zhao, Handong, Zhang, Ruiyi, Mathur, Puneet, Lipka, Nedim, Wang, Yu, Bui, Trung, Dernoncourt, Franck, Zhou, Tianyi
Existing LLM agent systems typically select actions from a fixed and predefined set at every step. While this approach is effective in closed, narrowly-scoped environments, we argue that it presents two major challenges when deploying LLM agents in r
Externí odkaz:
http://arxiv.org/abs/2411.01747
What makes a difference in the post-training of LLMs? We investigate the training patterns of different layers in large language models (LLMs), through the lens of gradient, when training with different responses and initial models. We are specifical
Externí odkaz:
http://arxiv.org/abs/2410.23743
Sharpness-Aware Minimization (SAM) has been demonstrated to improve the generalization performance of overparameterized models by seeking flat minima on the loss landscape through optimizing model parameters that incur the largest loss within a neigh
Externí odkaz:
http://arxiv.org/abs/2410.22656
Incremental learning (IL) aims to acquire new knowledge from current tasks while retaining knowledge learned from previous tasks. Replay-based IL methods store a set of exemplars from previous tasks in a buffer and replay them when learning new tasks
Externí odkaz:
http://arxiv.org/abs/2410.15372
Evaluating large language models (LLMs) is costly: it requires the generation and examination of LLM outputs on a large-scale benchmark of various tasks. This paper investigates how to efficiently reduce the tasks used to benchmark LLMs without affec
Externí odkaz:
http://arxiv.org/abs/2410.13804
Low-quality or scarce data has posed significant challenges for training deep neural networks in practice. While classical data augmentation cannot contribute very different new data, diffusion models opens up a new door to build self-evolving AI by
Externí odkaz:
http://arxiv.org/abs/2410.13674