no code implementations • 4 Mar 2025 • Paul Suganthan, Fedor Moiseev, Le Yan, Junru Wu, Jianmo Ni, Jay Han, Imed Zitouni, Enrique Alfonseca, Xuanhui Wang, Zhe Dong
Decoder-based transformers, while revolutionizing language modeling and scaling to immense sizes, have not completely overtaken encoder-heavy architectures in natural language processing.
no code implementations • 20 Sep 2024 • Tianqi Liu, Wei Xiong, Jie Ren, Lichang Chen, Junru Wu, Rishabh Joshi, Yang Gao, Jiaming Shen, Zhen Qin, Tianhe Yu, Daniel Sohn, Anastasiia Makarova, Jeremiah Liu, YuAn Liu, Bilal Piot, Abe Ittycheriah, Aviral Kumar, Mohammad Saleh
Our RRM improves the performance of a pairwise reward model trained on Gemma-2-9b-it, on RewardBench, increasing accuracy from 80. 61% to 84. 15%.
no code implementations • 6 Aug 2024 • Zhen Qin, Junru Wu, Jiaming Shen, Tianqi Liu, Xuanhui Wang
We introduce LAMPO, a novel paradigm that leverages Large Language Models (LLMs) for solving few-shot multi-class ordinal classification tasks.
1 code implementation • 27 Feb 2024 • Wuyang Chen, Junru Wu, Zhangyang Wang, Boris Hanin
However, most designs or optimization methods are agnostic to the choice of network structures, and thus largely ignore the impact of neural architectures on hyperparameters.
1 code implementation • 2 Feb 2024 • Tianqi Liu, Zhen Qin, Junru Wu, Jiaming Shen, Misha Khalman, Rishabh Joshi, Yao Zhao, Mohammad Saleh, Simon Baumgartner, Jialu Liu, Peter J. Liu, Xuanhui Wang
In this work, we formulate the LM alignment as a \textit{listwise} ranking problem and describe the LiPO framework, where the policy can potentially learn more effectively from a ranked list of plausible responses given the prompt.
no code implementations • 21 Oct 2023 • Honglei Zhuang, Zhen Qin, Kai Hui, Junru Wu, Le Yan, Xuanhui Wang, Michael Bendersky
We propose to incorporate fine-grained relevance labels into the prompt for LLM rankers, enabling them to better differentiate among documents with different levels of relevance to the query and thus derive a more accurate ranking.
no code implementations • 30 Jun 2023 • Zhen Qin, Rolf Jagerman, Kai Hui, Honglei Zhuang, Junru Wu, Le Yan, Jiaming Shen, Tianqi Liu, Jialu Liu, Donald Metzler, Xuanhui Wang, Michael Bendersky
Ranking documents using Large Language Models (LLMs) by directly feeding the query and candidate documents into the prompt is an interesting and practical problem.
no code implementations • 3 Nov 2022 • Junru Wu, Yi Liang, Feng Han, Hassan Akbari, Zhangyang Wang, Cong Yu
For example, even in the commonly adopted instructional videos, a speaker can sometimes refer to something that is not visually present in the current frame; and the semantic misalignment would only be more unpredictable for the raw videos from the internet.
1 code implementation • 27 Apr 2022 • Qiucheng Wu, Yifan Jiang, Junru Wu, Kai Wang, Gong Zhang, Humphrey Shi, Zhangyang Wang, Shiyu Chang
To study the motion features in the latent space of StyleGAN, in this paper, we hypothesize and demonstrate that a series of meaningful, natural, and versatile small, local movements (referred to as "micromotion", such as expression, head movement, and aging effect) can be represented in low-rank spaces extracted from the latent space of a conventionally pre-trained StyleGAN-v2 model for face generation, with the guidance of proper "anchors" in the form of either short text or video clips.
no code implementations • 9 Dec 2021 • Yifan Jiang, Xinyu Gong, Junru Wu, Humphrey Shi, Zhicheng Yan, Zhangyang Wang
Efficient video architecture is the key to deploying video recognition systems on devices with limited computing resources.
1 code implementation • 26 Aug 2021 • Wuyang Chen, Xinyu Gong, Junru Wu, Yunchao Wei, Humphrey Shi, Zhicheng Yan, Yi Yang, Zhangyang Wang
This work targets designing a principled and unified training-free framework for Neural Architecture Search (NAS), with high performance, low cost, and in-depth interpretation.
1 code implementation • NeurIPS 2021 • Junru Wu, Xiyang Dai, Dongdong Chen, Yinpeng Chen, Mengchen Liu, Ye Yu, Zhangyang Wang, Zicheng Liu, Mei Chen, Lu Yuan
We propose a paradigm shift from fitting the whole architecture space using one strong predictor, to progressively fitting a search path towards the high-performance sub-space through a set of weaker predictors.
no code implementations • 1 Jan 2021 • Junru Wu, Xiyang Dai, Dongdong Chen, Yinpeng Chen, Mengchen Liu, Ye Yu, Zhangyang Wang, Zicheng Liu, Mei Chen, Lu Yuan
Rather than expecting a single strong predictor to model the whole space, we seek a progressive line of weak predictors that can connect a path to the best architecture, thus greatly simplifying the learning task of each predictor.
no code implementations • 28 Nov 2020 • Junru Wu, Xiang Yu, Buyu Liu, Zhangyang Wang, Manmohan Chandraker
Face anti-spoofing (FAS) seeks to discriminate genuine faces from fake ones arising from any type of spoofing attack.
no code implementations • 7 Dec 2019 • Junru Wu, Xiang Yu, Ding Liu, Manmohan Chandraker, Zhangyang Wang
To train and evaluate on more diverse blur severity levels, we propose a Challenging DVD dataset generated from the raw DVD video set by pooling frames with different temporal windows.
6 code implementations • ICCV 2019 • Orest Kupyn, Tetiana Martyniuk, Junru Wu, Zhangyang Wang
We present a new end-to-end generative adversarial network (GAN) for single image motion deblurring, named DeblurGAN-v2, which considerably boosts state-of-the-art deblurring efficiency, quality, and flexibility.
Ranked #2 on
Deblurring
on BASED
2 code implementations • 22 May 2019 • Sicheng Wang, Bihan Wen, Junru Wu, DaCheng Tao, Zhangyang Wang
Several recent works discussed application-driven image restoration neural networks, which are capable of not only removing noise in images but also preserving their semantic-aware details, making them suitable for various high-level computer vision tasks as the pre-processing step.
no code implementations • 28 Jan 2019 • Rosaura G. VidalMata, Sreya Banerjee, Brandon RichardWebster, Michael Albright, Pedro Davalos, Scott McCloskey, Ben Miller, Asong Tambo, Sushobhan Ghosh, Sudarshan Nagesh, Ye Yuan, Yueyu Hu, Junru Wu, Wenhan Yang, Xiaoshuai Zhang, Jiaying Liu, Zhangyang Wang, Hwann-Tzong Chen, Tzu-Wei Huang, Wen-Chi Chin, Yi-Chun Li, Mahmoud Lababidi, Charles Otto, Walter J. Scheirer
From the observed results, it is evident that we are in the early days of building a bridge between computational photography and visual recognition, leaving many opportunities for innovation in this area.
1 code implementation • ICML 2018 • Junru Wu, Yue Wang, Zhen-Yu Wu, Zhangyang Wang, Ashok Veeraraghavan, Yingyan Lin
The current trend of pushing CNNs deeper with convolutions has created a pressing demand to achieve higher compression gains on CNNs where convolutions dominate the computation and parameter amount (e. g., GoogLeNet, ResNet and Wide ResNet).
1 code implementation • 24 Jun 2018 • Junru Wu, Yue Wang, Zhen-Yu Wu, Zhangyang Wang, Ashok Veeraraghavan, Yingyan Lin
The current trend of pushing CNNs deeper with convolutions has created a pressing demand to achieve higher compression gains on CNNs where convolutions dominate the computation and parameter amount (e. g., GoogLeNet, ResNet and Wide ResNet).
no code implementations • CVPR 2018 • Yanyu Xu, Yanbing Dong, Junru Wu, Zhengzhong Sun, Zhiru Shi, Jingyi Yu, Shenghua Gao
This paper explores gaze prediction in dynamic $360^circ$ immersive videos, emph{i. e.}, based on the history scan path and VR contents, we predict where a viewer will look at an upcoming time.
1 code implementation • 9 Oct 2017 • Yanyu Xu, Shenghua Gao, Junru Wu, Nianyi Li, Jingyi Yu
Specifically, we propose to decompose a personalized saliency map (referred to as PSM) into a universal saliency map (referred to as USM) predictable by existing saliency detection models and a new discrepancy map across users that characterizes personalized saliency.