Zobrazeno 1 - 10
of 17 691
pro vyhledávání: '"huang, Tao"'
KV cache pruning has emerged as a promising technique for reducing memory and computation costs in long-context auto-regressive generation. Existing methods for vision-language models (VLMs) typically rely on self-attention scores from large language
Externí odkaz:
http://arxiv.org/abs/2412.04652
The increasing reliance on deep computer vision models that process sensitive data has raised significant privacy concerns, particularly regarding the exposure of intermediate results in hidden layers. While traditional privacy risk assessment techni
Externí odkaz:
http://arxiv.org/abs/2412.00696
In contrast to quadruped robots that can navigate diverse terrains using a "blind" policy, humanoid robots require accurate perception for stable locomotion due to their high degrees of freedom and inherently unstable morphology. However, incorporati
Externí odkaz:
http://arxiv.org/abs/2411.14386
In the domain of deep learning, the challenge of protecting sensitive data while maintaining model utility is significant. Traditional Differential Privacy (DP) techniques such as Differentially Private Stochastic Gradient Descent (DP-SGD) typically
Externí odkaz:
http://arxiv.org/abs/2411.03059
We investigate the construction of gradient-guided conditional diffusion models for reconstructing private images, focusing on the adversarial interplay between differential privacy noise and the denoising capabilities of diffusion models. While curr
Externí odkaz:
http://arxiv.org/abs/2411.03053
Robots Pre-train Robots: Manipulation-Centric Robotic Representation from Large-Scale Robot Datasets
The pre-training of visual representations has enhanced the efficiency of robot learning. Due to the lack of large-scale in-domain robotic datasets, prior works utilize in-the-wild human videos to pre-train robotic visual representation. Despite thei
Externí odkaz:
http://arxiv.org/abs/2410.22325
Autor:
Zhang, Yuan, Fan, Chun-Kai, Ma, Junpeng, Zheng, Wenzhao, Huang, Tao, Cheng, Kuan, Gudovskiy, Denis, Okuno, Tomoyuki, Nakata, Yohei, Keutzer, Kurt, Zhang, Shanghang
In vision-language models (VLMs), visual tokens usually consume a significant amount of computational overhead, despite their sparser information density compared to text tokens. To address this, most existing methods learn a network to prune redunda
Externí odkaz:
http://arxiv.org/abs/2410.04417
Improving the automatic and timely recognition of construction and demolition waste (C&DW) composition is crucial for enhancing business returns, economic outcomes, and sustainability. Technologies like computer vision, artificial intelligence (AI),
Externí odkaz:
http://arxiv.org/abs/2409.13112
The time-critical industrial applications pose intense demands for enabling long-distance deterministic networks. However, previous priority-based and weight-based scheduling methods focus on probabilistically reducing average delay, which ignores st
Externí odkaz:
http://arxiv.org/abs/2409.09592
Autor:
Huang, Yudong, Huang, Tao, Zhang, Xinyuan, Wang, Shuo, Du, Hongyang, Niyato, Dusit, Yu, Fei Richard
Booming time-critical services, such as automated manufacturing and remote operations, stipulate increasing demands for facilitating large-scale Industrial Internet of Things (IoT). Recently, a cycle specified queuing and forwarding (CSQF) scheme has
Externí odkaz:
http://arxiv.org/abs/2409.09585