Zobrazeno 1 - 10
of 106
pro vyhledávání: '"Gu, Jindong"'
Autor:
Chen, Haokun, Li, Hang, Zhang, Yao, Zhang, Gengyuan, Bi, Jinhe, Torr, Philip, Gu, Jindong, Krompass, Denis, Tresp, Volker
One-Shot Federated Learning (OSFL), a special decentralized machine learning paradigm, has recently gained significant attention. OSFL requires only a single round of client data or model upload, which reduces communication costs and mitigates privac
Externí odkaz:
http://arxiv.org/abs/2410.04810
Autor:
Zhang, Haowei, Liu, Jianzhe, Han, Zhen, Chen, Shuo, He, Bailan, Tresp, Volker, Xu, Zhiqiang, Gu, Jindong
Question decomposition has emerged as an effective strategy for prompting Large Language Models (LLMs) to answer complex questions. However, while existing methods primarily focus on unimodal language models, the question decomposition capability of
Externí odkaz:
http://arxiv.org/abs/2409.19339
Autor:
Liu, Tong, Lai, Zhixin, Zhang, Gengyuan, Torr, Philip, Demberg, Vera, Tresp, Volker, Gu, Jindong
Diffusion models have recently achieved remarkable advancements in terms of image quality and fidelity to textual prompts. Concurrently, the safety of such generative models has become an area of growing concern. This work introduces a novel type of
Externí odkaz:
http://arxiv.org/abs/2409.19149
Autor:
Cheng, Hao, Xiao, Erjia, Yu, Chengyuan, Yao, Zhao, Cao, Jiahang, Zhang, Qiang, Wang, Jiaxu, Sun, Mengshu, Xu, Kaidi, Gu, Jindong, Xu, Renjing
Recently, driven by advancements in Multimodal Large Language Models (MLLMs), Vision Language Action Models (VLAMs) are being proposed to achieve better performance in open-vocabulary scenarios for robotic manipulation tasks. Since manipulation tasks
Externí odkaz:
http://arxiv.org/abs/2409.13174
Recently, Text-to-Image(T2I) models have achieved remarkable success in image generation and editing, yet these models still have many potential issues, particularly in generating inappropriate or Not-Safe-For-Work(NSFW) content. Strengthening attack
Externí odkaz:
http://arxiv.org/abs/2408.13896
Autor:
Chen, Canyu, Huang, Baixiang, Li, Zekun, Chen, Zhaorun, Lai, Shiyang, Xu, Xiongxiao, Gu, Jia-Chen, Gu, Jindong, Yao, Huaxiu, Xiao, Chaowei, Yan, Xifeng, Wang, William Yang, Torr, Philip, Song, Dawn, Shu, Kai
Knowledge editing has been increasingly adopted to correct the false or outdated knowledge in Large Language Models (LLMs). Meanwhile, one critical but under-explored question is: can knowledge editing be used to inject harm into LLMs? In this paper,
Externí odkaz:
http://arxiv.org/abs/2407.20224
Dataset Distillation is used to create a concise, yet informative, synthetic dataset that can replace the original dataset for training purposes. Some leading methods in this domain prioritize long-range matching, involving the unrolling of training
Externí odkaz:
http://arxiv.org/abs/2407.14245
Autor:
Li, Jinming, Zhu, Yichen, Xu, Zhiyuan, Gu, Jindong, Zhu, Minjie, Liu, Xin, Liu, Ning, Peng, Yaxin, Feng, Feifei, Tang, Jian
It is fundamentally challenging for robots to serve as useful assistants in human environments because this requires addressing a spectrum of sub-problems across robotics, including perception, language understanding, reasoning, and planning. The rec
Externí odkaz:
http://arxiv.org/abs/2406.19693
Autor:
Zhang, Gengyuan, Fok, Mang Ling Ada, Xia, Yan, Tang, Yansong, Cremers, Daniel, Torr, Philip, Tresp, Volker, Gu, Jindong
Video understanding is a pivotal task in the digital era, yet the dynamic and multievent nature of videos makes them labor-intensive and computationally demanding to process. Thus, localizing a specific event given a semantic query has gained importa
Externí odkaz:
http://arxiv.org/abs/2406.10079
Using feature attributions for post-hoc explanations is a common practice to understand and verify the predictions of opaque machine learning models. Despite the numerous techniques available, individual methods often produce inconsistent and unstabl
Externí odkaz:
http://arxiv.org/abs/2406.05090