1 code implementation • 27 Feb 2024 • MingJie Sun, Xinlei Chen, J. Zico Kolter, Zhuang Liu
We observe an empirical phenomenon in Large Language Models (LLMs) -- very few activations exhibit significantly larger values than others (e. g., 100, 000 times larger).
2 code implementations • 8 Nov 2023 • Rocktim Jyoti Das, MingJie Sun, Liqun Ma, Zhiqiang Shen
GBLM-Pruner leverages the first-order term of the Taylor expansion, operating in a training-free manner by harnessing properly normalized gradients from a few calibration samples to determine the pruning metric, and substantially outperforms competitive counterparts like SparseGPT and Wanda in multiple benchmarks.
no code implementations • 7 Oct 2023 • Eungyeup Kim, MingJie Sun, aditi raghunathan, Zico Kolter
In this work, we make a notable and surprising observation that TTAed models strongly show the agreement-on-the-line phenomenon (Baek et al., 2022) across a wide range of distribution shifts.
1 code implementation • 23 Aug 2023 • Siyue Yao, MingJie Sun, Bingliang Li, Fengyu Yang, Junle Wang, Ruimao Zhang
In this paper, we introduce a novel multi-dancer synthesis task called partner dancer generation, which involves synthesizing virtual human dancers capable of performing dance with users.
3 code implementations • 20 Jun 2023 • MingJie Sun, Zhuang Liu, Anna Bair, J. Zico Kolter
Motivated by the recent observation of emergent large magnitude features in LLMs, our approach prunes weights with the smallest magnitudes multiplied by the corresponding input activations, on a per-output basis.
1 code implementation • CVPR 2023 • MingJie Sun, J. Zico Kolter
Insipired by recent advances in adversarial robustness, our method SmoothInv starts from a single clean image, and then performs projected gradient descent towards the target class on a robust smoothed version of the original backdoored classifier.
no code implementations • 17 Dec 2022 • Hui Li, MingJie Sun, Jimin Xiao, Eng Gee Lim, Yao Zhao
To validate our framework on a weakly-supervised setting, we annotated three RES benchmark datasets (RefCOCO, RefCOCO+ and RefCOCOg) with click annotations. Our method is simple but surprisingly effective, outperforming all previous state-of-the-art RES methods on fully- and weakly-supervised settings by a large margin.
1 code implementation • 20 Jul 2022 • Sachin Goyal, MingJie Sun, aditi raghunathan, Zico Kolter
In this paper, we start by presenting a surprising phenomenon: if we attempt to meta-learn the best possible TTA loss over a wide class of functions, then we recover a function that is remarkably similar to (a temperature-scaled version of) the softmax-entropy employed by TENT.
1 code implementation • 21 Jun 2022 • Nicholas Carlini, Florian Tramer, Krishnamurthy Dj Dvijotham, Leslie Rice, MingJie Sun, J. Zico Kolter
In this paper we show how to achieve state-of-the-art certified adversarial robustness to 2-norm bounded perturbations by relying exclusively on off-the-shelf pretrained models.
1 code implementation • 8 Jun 2021 • MingJie Sun, Jimin Xiao, Eng Gee Lim, Si Liu, John Y. Goulermas
In this paper, we are tackling the weakly-supervised referring expression grounding task, for the localization of a referent object in an image according to a query sentence, where the mapping between image regions and queries are not available during the training stage.
1 code implementation • CVPR 2021 • MingJie Sun, Jimin Xiao, Eng Gee Lim
In this paper, we are tackling the proposal-free referring expression grounding task, aiming at localizing the target object according to a query sentence, without relying on off-the-shelf object proposals.
no code implementations • ICCV 2021 • MingJie Sun, Zichao Li, Chaowei Xiao, Haonan Qiu, Bhavya Kailkhura, Mingyan Liu, Bo Li
Specifically, EdgeNetRob and EdgeGANRob first explicitly extract shape structure features from a given image via an edge detection algorithm.
no code implementations • 17 Nov 2020 • MingJie Sun, Jianguo Li, ChangShui Zhang
Recent evidence shows that convolutional neural networks (CNNs) are biased towards textures so that CNNs are non-robust to adversarial perturbations over textures, while traditional robust visual features like SIFT (scale-invariant feature transforms) are designed to be robust across a substantial range of affine distortion, addition of noise, etc with the mimic of human perception nature.
1 code implementation • 18 Oct 2020 • MingJie Sun, Siddhant Agarwal, J. Zico Kolter
Under this threat model, we propose a test-time, human-in-the-loop attack method to generate multiple effective alternative triggers without access to the initial backdoor and the training data.
1 code implementation • CVPR 2020 • Mingjie Sun, Jimin Xiao, Eng Gee Lim, Bingfeng Zhang, Yao Zhao
Specifically, the reinforcement learning agent learns to decide whether to update the target template according to the quality of the predicted result.
1 code implementation • 27 Sep 2019 • Mingjie Sun, Jimin Xiao, Eng Gee Lim, Yanchu Xie, Jiashi Feng
In this paper, we aim to tackle the task of semi-supervised video object segmentation across a sequence of frames where only the ground-truth segmentation of the first frame is provided.
no code implementations • 25 Sep 2019 • Jianguo Li, MingJie Sun, ChangShui Zhang
Recent evidence shows that convolutional neural networks (CNNs) are biased towards textures so that CNNs are non-robust to adversarial perturbations over textures, while traditional robust visual features like SIFT (scale-invariant feature transforms) are designed to be robust across a substantial range of affine distortion, addition of noise, etc with the mimic of human perception nature.
1 code implementation • 21 Jul 2019 • Xinlei Pan, Chaowei Xiao, Warren He, Shuang Yang, Jian Peng, MingJie Sun, JinFeng Yi, Zijiang Yang, Mingyan Liu, Bo Li, Dawn Song
To the best of our knowledge, we are the first to apply adversarial attacks on DRL systems to physical robots.
no code implementations • 30 Oct 2018 • Mingjie Sun, Jian Tang, Huichen Li, Bo Li, Chaowei Xiao, Yao Chen, Dawn Song
In this paper, we take the task of link prediction as an example, which is one of the most fundamental problems for graph analysis, and introduce a data positioning attack to node embedding methods.