no code implementations • WMT (EMNLP) 2020 • Longyue Wang, Zhaopeng Tu, Xing Wang, Li Ding, Liang Ding, Shuming Shi
This paper describes the Tencent AI Lab’s submission of the WMT 2020 shared task on chat translation in English-German.
1 code implementation • 23 Jan 2024 • Andrew Ni, Li Ding, Lee Spector
Lexicase selection has been shown to provide advantages over other selection algorithms in several areas of evolutionary computation and machine learning.
1 code implementation • ICLR 2022 • Li Ding, Lee Spector
Lexicase selection is an uncompromising method developed in evolutionary computation, which selects models on the basis of sequences of individual training case errors instead of using aggregated metrics such as loss and accuracy.
no code implementations • 4 Nov 2023 • Ryan Boldi, Li Ding, Lee Spector
Furthermore, we find that this technique results in competitive performance on the diversity-focused metrics of QD-Score and Coverage, without explicitly optimizing for these things.
1 code implementation • 29 Oct 2023 • Li Ding, Masrour Zoghi, Guy Tennenholtz, Maryam Karimzadehgan
We introduce EV3, a novel meta-optimization framework designed to efficiently train scalable machine learning models through an intuitive explore-assess-adapt protocol.
1 code implementation • 18 Oct 2023 • Li Ding, Jenny Zhang, Jeff Clune, Lee Spector, Joel Lehman
Meanwhile, Quality Diversity (QD) algorithms excel at identifying diverse and high-quality solutions but often rely on manually crafted diversity metrics.
no code implementations • 26 Jun 2023 • Li Ding, Jack Terwilliger, Aishni Parab, Meng Wang, Lex Fridman, Bruce Mehler, Bryan Reimer
Non-intrusive, real-time analysis of the dynamics of the eye region allows us to monitor humans' visual attention allocation and estimate their mental state during the performance of real-world tasks, which can potentially benefit a wide range of human-computer interaction (HCI) applications.
no code implementations • 12 Jun 2023 • Lee Spector, Li Ding, Ryan Boldi
We describe a design principle for adaptive systems under which adaptation is driven by particular challenges that the environment poses, as opposed to average or otherwise aggregated measures of performance over many challenges.
1 code implementation • 19 May 2023 • Li Ding, Edward Pantridge, Lee Spector
Lexicase selection is a widely used parent selection algorithm in genetic programming, known for its success in various task domains such as program synthesis, symbolic regression, and machine learning.
no code implementations • 24 Apr 2023 • Haitian Jiang, Dongliang Xiong, Xiaowen Jiang, Li Ding, Liang Chen, Kai Huang
In this paper, we propose a fast and structure-aware halftoning method via a data-driven approach.
no code implementations • CVPR 2023 • Chao Chen, Xinhao Liu, Yiming Li, Li Ding, Chen Feng
LiDAR mapping is important yet challenging in self-driving and mobile robotics.
no code implementations • 23 Aug 2022 • Li Ding, Ryan Boldi, Thomas Helmuth, Lee Spector
Lexicase selection is a semantic-aware parent selection method, which assesses individual test cases in a randomly-shuffled data stream.
no code implementations • 23 Aug 2022 • Li Ding, Lee Spector
Recent works show that parameterized quantum circuits (PQCs) can be used to solve challenging reinforcement learning (RL) tasks with provable learning advantages.
no code implementations • 19 Aug 2022 • Chao Chen, Xinhao Liu, Xuchu Xu, Yiming Li, Li Ding, Ruoyu Wang, Chen Feng
Inspired by noisy label learning, we propose a novel self-supervised framework named \textit{TF-VPR} that uses temporal neighborhoods and learnable feature neighborhoods to discover unknown spatial neighborhoods.
no code implementations • 23 Jul 2022 • Haitian Jiang, Dongliang Xiong, Xiaowen Jiang, Aiguo Yin, Li Ding, Kai Huang
Deep neural networks have recently succeeded in digital halftoning using vanilla convolutional layers with high parallelism.
no code implementations • 4 Apr 2022 • Li Ding, Lee Spector
We propose the Adaptive Neural Selection (ANS) framework, which evolves to weigh neurons in a layer to form network variants that are suitable to handle different input cases.
no code implementations • 31 Jul 2021 • Li Ding, Yongwei Wang, Xin Ding, Kaiwen Yuan, Ping Wang, Hua Huang, Z. Jane Wang
Deep learning based image classification models are shown vulnerable to adversarial attacks by injecting deliberately crafted noises to clean images.
no code implementations • 10 Apr 2021 • Ruoyu Wang, Xuchu Xu, Li Ding, Yang Huang, Chen Feng
PoseNet can map a photo to the position where it is taken, which is appealing in robotics.
1 code implementation • 29 Oct 2020 • Yongwei Wang, Xin Ding, Li Ding, Rabab Ward, Z. Jane Wang
Specially, when adversaries consider imperceptibility as a constraint, the proposed anti-forensic method can improve the average attack success rate by around 30\% on fake face images over two baseline attacks.
no code implementations • 25 Jul 2019 • Li Ding, Lex Fridman
We provide qualitative evaluation of this representation for the object detection task and quantitative evaluation of its use in a baseline algorithm for the instance segmentation task.
no code implementations • 5 Jul 2019 • Li Ding, Mohammad H. Bawany, Ajay E. Kuriyan, Rajeev S. Ramchandran, Charles C. Wykoff, Gaurav Sharma
We propose a novel pipeline to detect retinal vessels in FA images using deep neural networks that reduces the effort required for generating labeled ground truth data by combining two key components: cross-modality transfer and human-in-the-loop learning.
no code implementations • 21 Mar 2019 • Li Ding, Jack Terwilliger, Rini Sherony, Bryan Reimer, Lex Fridman
What is not known is how much extra information the temporal dynamics of the visual scene carries that is complimentary to the information available in the individual frames of the video.
1 code implementation • CVPR 2019 • Li Ding, Chen Feng
We propose DeepMapping, a novel registration framework using deep neural networks (DNNs) as auxiliary functions to align multiple point clouds from scratch to a globally consistent frame.
1 code implementation • CVPR 2018 • Li Ding, Chenliang Xu
In this work, we address the task of weakly-supervised human action segmentation in long, untrimmed videos.
no code implementations • ICLR 2018 • Li Ding, Chenliang Xu
Action segmentation as a milestone towards building automatic systems to understand untrimmed videos has received considerable attention in the recent years.
no code implementations • 19 Nov 2017 • Lex Fridman, Daniel E. Brown, Michael Glazer, William Angell, Spencer Dodd, Benedikt Jenik, Jack Terwilliger, Aleksandr Patsekin, Julia Kindelsberger, Li Ding, Sean Seaman, Alea Mehler, Andrew Sipperley, Anthony Pettinato, Bobbie Seppelt, Linda Angell, Bruce Mehler, Bryan Reimer
For the foreseeble future, human beings will likely remain an integral part of the driving task, monitoring the AI system as it performs anywhere from just over 0% to just under 100% of the driving.
1 code implementation • 12 Oct 2017 • Lex Fridman, Li Ding, Benedikt Jenik, Bryan Reimer
We consider the paradigm of a black box AI system that makes life-critical decisions.
no code implementations • 22 May 2017 • Li Ding, Chenliang Xu
Action segmentation as a milestone towards building automatic systems to understand untrimmed videos has received considerable attention in the recent years.
Ranked #4 on Action Segmentation on JIGSAWS