no code implementations • 14 Mar 2024 • Aonan Zhang, Chong Wang, Yi Wang, Xuanyu Zhang, Yunfei Cheng
In this paper, we introduce an improved approach of speculative decoding aimed at enhancing the efficiency of serving large language models.
no code implementations • 14 Mar 2024 • Brandon McKinzie, Zhe Gan, Jean-Philippe Fauconnier, Sam Dodge, BoWen Zhang, Philipp Dufter, Dhruti Shah, Xianzhi Du, Futang Peng, Floris Weers, Anton Belyi, Haotian Zhang, Karanjeet Singh, Doug Kang, Ankur Jain, Hongyu Hè, Max Schwarzer, Tom Gunter, Xiang Kong, Aonan Zhang, Jianyu Wang, Chong Wang, Nan Du, Tao Lei, Sam Wiseman, Guoli Yin, Mark Lee, ZiRui Wang, Ruoming Pang, Peter Grasch, Alexander Toshev, Yinfei Yang
Through careful and comprehensive ablations of the image encoder, the vision language connector, and various pre-training data choices, we identified several crucial design lessons.
Ranked #21 on Visual Question Answering on MM-Vet
no code implementations • 22 Feb 2024 • Zhuofeng Wu, He Bai, Aonan Zhang, Jiatao Gu, VG Vinod Vydiswaran, Navdeep Jaitly, Yizhe Zhang
Recent methods have demonstrated that Large Language Models (LLMs) can solve reasoning tasks better when they are encouraged to solve subtasks of the main task first.
no code implementations • 25 May 2023 • Xiaohui Chen, Jiankai Sun, Taiqing Wang, Ruocheng Guo, Li-Ping Liu, Aonan Zhang
Most subsampling methods are model-based and often require a pre-trained pilot model to measure data importance via e. g. sample hardness.
no code implementations • 19 Nov 2022 • Xiaohui Chen, Yukun Li, Aonan Zhang, Li-Ping Liu
Learning to generate graphs is challenging as a graph is a set of pairwise connected, unordered nodes encoding complex combinatorial structures.
no code implementations • 20 Sep 2022 • Ke Bai, Aonan Zhang, Zhizhong Li, Ricardo Heano, Chong Wang, Lawrence Carin
In recommendation systems, items are likely to be exposed to various users and we would like to learn about the familiarity of a new user with an existing item.
no code implementations • NeurIPS 2021 • Haiying Wang, Aonan Zhang, Chong Wang
We first prove that, with imbalanced data, the available information about unknown parameters is only tied to the relatively small number of positive instances, which justifies the usage of negative sampling.
no code implementations • 10 Jun 2021 • Jiankai Sun, Xin Yang, Yuanshun Yao, Aonan Zhang, Weihao Gao, Junyuan Xie, Chong Wang
In this paper, we propose a vFL framework based on Private Set Union (PSU) that allows each party to keep sensitive membership information to itself.
1 code implementation • 9 May 2019 • Aonan Zhang, John Paisley
The likelihood model of high dimensional data $X_n$ can often be expressed as $p(X_n|Z_n,\theta)$, where $\theta\mathrel{\mathop:}=(\theta_k)_{k\in[K]}$ is a collection of hidden features shared across objects, indexed by $n$, and $Z_n$ is a non-negative factor loading vector with $K$ entries where $Z_{nk}$ indicates the strength of $\theta_k$ used to express $X_n$.
1 code implementation • 10 Oct 2018 • Aonan Zhang, Quan Wang, Zhenyao Zhu, John Paisley, Chong Wang
In this paper, we propose a fully supervised speaker diarization approach, named unbounded interleaved-state recurrent neural networks (UIS-RNN).
Ranked #1 on Speaker Diarization on Hub5'00 CallHome
no code implementations • ICML 2018 • Aonan Zhang, John Paisley
Time-series data often exhibit irregular behavior, making them hard to analyze and explain with a simple dynamic model.
no code implementations • 25 May 2015 • San Gultekin, Aonan Zhang, John Paisley
We empirically evaluate a stochastic annealing strategy for Bayesian posterior optimization with variational inference.