no code implementations • 21 Apr 2024 • Zhihang Li, Zhao Song, Weixin Wang, Junze Yin, Zheng Yu
Leverage score is a fundamental problem in machine learning and theoretical computer science.
no code implementations • 20 Mar 2024 • Yanyuan Qiao, Zheng Yu, Longteng Guo, Sihan Chen, Zijia Zhao, Mingzhen Sun, Qi Wu, Jing Liu
The extensive experiments on diverse multimodal benchmarks with competitive performance show the effectiveness of our proposed VL-Mamba and demonstrate the great potential of applying state space models for multimodal learning tasks.
Ranked #63 on Visual Question Answering on MM-Vet
1 code implementation • 19 Sep 2023 • Jiahao Yu, Xingwei Lin, Zheng Yu, Xinyu Xing
Remarkably, GPTFuzz achieves over 90% attack success rates against ChatGPT and Llama-2 models, even with suboptimal initial seed templates.
no code implementations • 15 Sep 2023 • Yikuan Li, Chengsheng Mao, Kaixuan Huang, Hanyin Wang, Zheng Yu, Mengdi Wang, Yuan Luo
Scarcity of health care resources could result in the unavoidable consequence of rationing.
1 code implementation • ICCV 2023 • Yanyuan Qiao, Zheng Yu, Qi Wu
The performance of the Vision-and-Language Navigation~(VLN) tasks has witnessed rapid progress recently thanks to the use of large pre-trained vision-and-language models.
1 code implementation • ICCV 2023 • Yanyuan Qiao, Yuankai Qi, Zheng Yu, Jing Liu, Qi Wu
Nevertheless, this poses more challenges than other VLN tasks since it requires agents to infer a navigation plan only based on a short instruction.
no code implementations • IEEE Transactions on Pattern Analysis and Machine Intelligence 2023 • Yanyuan Qiao, Yuankai Qi, Yicong Hong, Zheng Yu, Peng Wang, and Qi Wu ̊
To address these problems, we present a history-enhanced and order-aware pre-training with the complementing fine-tuning paradigm (HOP+) for VLN.
1 code implementation • 20 Feb 2023 • Zheng Yu, Yikuan Li, Joseph Kim, Kaixuan Huang, Yuan Luo, Mengdi Wang
In this work, we use reinforcement learning (RL) to find a dynamic policy that selects lab test panels sequentially based on previous observations, ensuring accurate testing at a low cost.
no code implementations • 15 Oct 2022 • Zhao Song, Yitan Wang, Zheng Yu, Lichen Zhang
In this paper, we propose a novel sketching scheme for the first order method in large-scale distributed learning setting, such that the communication costs between distributed agents are saved while the convergence of the algorithms is still guaranteed.
1 code implementation • CVPR 2022 • Yanyuan Qiao, Yuankai Qi, Yicong Hong, Zheng Yu, Peng Wang, Qi Wu
Pre-training has been adopted in a few of recent works for Vision-and-Language Navigation (VLN).
Ranked #4 on Visual Navigation on R2R
no code implementations • 4 Dec 2021 • Shunhua Jiang, Yunze Man, Zhao Song, Zheng Yu, Danyang Zhuo
Given a kernel matrix of $n$ graphs, using sketching in solving kernel regression can reduce the running time to $o(n^3)$.
no code implementations • 29 Sep 2021 • Zhao Song, Zheng Yu, Lichen Zhang
Though most federated learning frameworks only require clients and the server to send gradient information over the network, they still face the challenges of communication efficiency and data privacy.
no code implementations • 21 Aug 2021 • Zhao Song, David P. Woodruff, Zheng Yu, Lichen Zhang
Recent techniques in oblivious sketching reduce the dependence in the running time on the degree $q$ of the polynomial kernel from exponential to polynomial, which is useful for the Gaussian kernel, for which $q$ can be chosen to be polylogarithmic.
no code implementations • NeurIPS 2021 • Junyu Zhang, Chengzhuo Ni, Zheng Yu, Csaba Szepesvari, Mengdi Wang
By assuming the overparameterizaiton of policy and exploiting the hidden convexity of the problem, we further show that TSIVR-PG converges to global $\epsilon$-optimal policy with $\tilde{\mathcal{O}}(\epsilon^{-2})$ samples.
no code implementations • 1 Jan 2021 • Zhao Song, Zheng Yu
In this work, we propose a sketching-based central path method for solving linear programmings, whose running time matches the state of art results [Cohen, Lee, Song STOC 19; Lee, Song, Zhang COLT 19].
no code implementations • NeurIPS 2020 • Jason D. Lee, Ruoqi Shen, Zhao Song, Mengdi Wang, Zheng Yu
Leverage score sampling is a powerful technique that originates from theoretical computer science, which can be used to speed up a large number of fundamental questions, e. g. linear regression, linear programming, semi-definite programming, cutting plane method, graph sparsification, maximum matching and max-flow.
no code implementations • 24 Feb 2020 • Yaqiong Li, Xuhui Fan, Ling Chen, Bin Li, Zheng Yu, Scott A. Sisson
In this work, we leverage its interpretable modelling architecture and propose a deep dynamic probabilistic framework -- the Recurrent Dirichlet Belief Network~(Recurrent-DBN) -- to study interpretable hidden structures from dynamic relational data.
no code implementations • 17 Jan 2020 • Zheng Yu, Xuhui Fan, Marcin Pietrasik, Marek Reformat
Besides, the proposed model infers the network structure and models community evolution, manifested by appearances and disappearances of communities, using the discrete fragmentation coagulation process (DFCP).
no code implementations • 13 Feb 2018 • Ruihan Wu, Zheng Yu, Wei Chen
In this paper, we study scalable algorithms for influence maximization with general marketing strategies (IM-GMS), in which a marketing strategy mix is modeled as a vector $\mathbf{x}=(x_1, \ldots, x_d)$ and could activate a node $v$ in the social network with probability $h_v(\mathbf{x})$.
Social and Information Networks Data Structures and Algorithms