Zobrazeno 1 - 10
of 1 756
pro vyhledávání: '"Li, Zhifeng"'
Accurate mathematical reasoning with Large Language Models (LLMs) is crucial in revolutionizing domains that heavily rely on such reasoning. However, LLMs often encounter difficulties in certain aspects of mathematical reasoning, leading to flawed re
Externí odkaz:
http://arxiv.org/abs/2410.10735
Model quantization is widely used to compress and accelerate deep neural networks. However, recent studies have revealed the feasibility of weaponizing model quantization via implanting quantization-conditioned backdoors (QCBs). These special backdoo
Externí odkaz:
http://arxiv.org/abs/2405.12725
Despite the exceptional performance of multi-modal large language models (MLLMs), their deployment requires substantial computational resources. Once malicious users induce high energy consumption and latency time (energy-latency cost), it will exhau
Externí odkaz:
http://arxiv.org/abs/2404.16557
Autor:
Ma, Yue, He, Yingqing, Wang, Hongfa, Wang, Andong, Qi, Chenyang, Cai, Chengfei, Li, Xiu, Li, Zhifeng, Shum, Heung-Yeung, Liu, Wei, Chen, Qifeng
Despite recent advances in image-to-video generation, better controllability and local animation are less explored. Most existing image-to-video methods are not locally aware and tend to move the entire scene. However, human artists may need to contr
Externí odkaz:
http://arxiv.org/abs/2403.08268
Large vision-language models (VLMs) such as GPT-4 have achieved exceptional performance across various multi-modal tasks. However, the deployment of VLMs necessitates substantial energy consumption and computational resources. Once attackers maliciou
Externí odkaz:
http://arxiv.org/abs/2401.11170
Contrastive Vision-Language Pre-training, known as CLIP, has shown promising effectiveness in addressing downstream image recognition tasks. However, recent works revealed that the CLIP model can be implanted with a downstream-oriented backdoor. On d
Externí odkaz:
http://arxiv.org/abs/2311.16194
In recent years, audio-driven 3D facial animation has gained significant attention, particularly in applications such as virtual reality, gaming, and video conferencing. However, accurately modeling the intricate and subtle dynamics of facial express
Externí odkaz:
http://arxiv.org/abs/2311.04766
Autor:
Zhu, Bin, Lin, Bin, Ning, Munan, Yan, Yang, Cui, Jiaxi, Wang, HongFa, Pang, Yatian, Jiang, Wenhao, Zhang, Junwu, Li, Zongwei, Zhang, Wancai, Li, Zhifeng, Liu, Wei, Yuan, Li
The video-language (VL) pretraining has achieved remarkable improvement in multiple downstream tasks. However, the current VL pretraining framework is hard to extend to multiple modalities (N modalities, N>=3) beyond vision and language. We thus prop
Externí odkaz:
http://arxiv.org/abs/2310.01852
Oxide dispersion strengthened FeCrAl alloys dispersed high-density nano-oxides in the matrix show outstanding corrosion resistance and mechanical properties. However, ODS FeCrAl alloys achieve the high strength generally at the expense of ductility i
Externí odkaz:
http://arxiv.org/abs/2309.03703
Autor:
Zhang, Shuyang, Zeng, Zhikun, Yuan, Houfei, Xu, Zihang, Ai, Xinyu, He, Lewei, Li, Zhifeng, Wang, Yujie
We experimentally investigate the clogging process of granular materials in a two-dimensional hopper, and present a self-consistent physical mechanism of clogging based on preformed dynamic chain structures in the flow. We found that these chain stru
Externí odkaz:
http://arxiv.org/abs/2308.06584