Zobrazeno 1 - 10
of 127
pro vyhledávání: '"Hong, Lanqing"'
As large language models (LLMs) constantly evolve, ensuring their safety remains a critical research problem. Previous red-teaming approaches for LLM safety have primarily focused on single prompt attacks or goal hijacking. To the best of our knowled
Externí odkaz:
http://arxiv.org/abs/2406.17626
While controllable generative models for images and videos have achieved remarkable success, high-quality models for 3D scenes, particularly in unbounded scenarios like autonomous driving, remain underdeveloped due to high data acquisition costs. In
Externí odkaz:
http://arxiv.org/abs/2405.14475
Autor:
Liu, Zhili, Gou, Yunhao, Chen, Kai, Hong, Lanqing, Gao, Jiahui, Mi, Fei, Zhang, Yu, Li, Zhenguo, Jiang, Xin, Liu, Qun, Kwok, James T.
As the capabilities of large language models (LLMs) have expanded dramatically, aligning these models with human values presents a significant challenge. Traditional alignment strategies rely heavily on human intervention, such as Supervised Fine-Tun
Externí odkaz:
http://arxiv.org/abs/2405.00557
Autor:
Chen, Kai, Li, Yanze, Zhang, Wenhua, Liu, Yanxin, Li, Pengxiang, Gao, Ruiyuan, Hong, Lanqing, Tian, Meng, Zhao, Xinhai, Li, Zhenguo, Yeung, Dit-Yan, Lu, Huchuan, Jia, Xu
Large Vision-Language Models (LVLMs) have received widespread attention in advancing the interpretable self-driving. Existing evaluations of LVLMs primarily focus on the multi-faceted capabilities in natural circumstances, lacking automated and quant
Externí odkaz:
http://arxiv.org/abs/2404.10595
Neural Radiance Fields (NeRF) have shown impressive capabilities for photorealistic novel view synthesis when trained on dense inputs. However, when trained on sparse inputs, NeRF typically encounters issues of incorrect density or color predictions,
Externí odkaz:
http://arxiv.org/abs/2403.16885
Autor:
Wang, Yibo, Gao, Ruiyuan, Chen, Kai, Zhou, Kaiqiang, Cai, Yingjie, Hong, Lanqing, Li, Zhenguo, Jiang, Lihui, Yeung, Dit-Yan, Xu, Qiang, Zhang, Kai
Current perceptive models heavily depend on resource-intensive datasets, prompting the need for innovative solutions. Leveraging recent advances in diffusion models, synthetic data, by constructing image inputs from various annotations, proves benefi
Externí odkaz:
http://arxiv.org/abs/2403.13304
Autor:
Gou, Yunhao, Chen, Kai, Liu, Zhili, Hong, Lanqing, Xu, Hang, Li, Zhenguo, Yeung, Dit-Yan, Kwok, James T., Zhang, Yu
Multimodal large language models (MLLMs) have shown impressive reasoning abilities, which, however, are also more vulnerable to jailbreak attacks than their LLM predecessors. Although still capable of detecting unsafe responses, we observe that safet
Externí odkaz:
http://arxiv.org/abs/2403.09572
In this paper, we focus on a realistic yet challenging task, Single Domain Generalization Object Detection (S-DGOD), where only one source domain's data can be used for training object detectors, but have to generalize multiple distinct target domain
Externí odkaz:
http://arxiv.org/abs/2402.04672
Masked Autoencoder~(MAE) is a prevailing self-supervised learning method that achieves promising results in model pre-training. However, when the various downstream tasks have data distributions different from the pre-training data, the semantically
Externí odkaz:
http://arxiv.org/abs/2402.05382
Although significant progress has been made in the field of 2D-based interactive editing, fine-grained 3D-based interactive editing remains relatively unexplored. This limitation can be attributed to two main challenges: the lack of an efficient 3D r
Externí odkaz:
http://arxiv.org/abs/2312.15856