Search Results for author: Wenlong Chen

Found 12 papers, 2 papers with code

Your Image is Secretly the Last Frame of a Pseudo Video

no code implementations26 Oct 2024 Wenlong Chen, Wenlin Chen, Lapo Rastrelli, Yingzhen Li

In this paper, we hypothesize that the success of diffusion models can be partly attributed to the additional self-supervision information for their intermediate latent states provided by corrupted images, which along with the original image form a pseudo video.

Data Augmentation Image Generation

Prototype-based Optimal Transport for Out-of-Distribution Detection

no code implementations10 Oct 2024 Ao Ke, Wenlong Chen, Chuanwen Feng, Yukun Cao, Xike Xie, S. Kevin Zhou, Lei Feng

In this paper, inspired by the inherent distribution shift between ID and OOD data, we propose a novel method that leverages optimal transport to measure the distribution discrepancy between test inputs and ID prototypes.

Out-of-Distribution Detection

MAO: A Framework for Process Model Generation with Multi-Agent Orchestration

no code implementations4 Aug 2024 Leilei Lin, Yumeng Jin, Yingming Zhou, Wenlong Chen, Chen Qian

Our framework MAO leverages large language models as the cornerstone for multi-agent, employing an innovative prompt strategy to ensure efficient collaboration among multi-agent.

Hallucination software testing

Detecting Out-of-Distribution Samples via Conditional Distribution Entropy with Optimal Transport

no code implementations22 Jan 2024 Chuanwen Feng, Wenlong Chen, Ao Ke, Yilong Ren, Xike Xie, S. Kevin Zhou

When deploying a trained machine learning model in the real world, it is inevitable to receive inputs from out-of-distribution (OOD) sources.

Continual Learning

An Incremental Update Framework for Online Recommenders with Data-Driven Prior

no code implementations26 Dec 2023 Chen Yang, Jin Chen, Qian Yu, Xiangdong Wu, Kui Ma, Zihao Zhao, Zhiwei Fang, Wenlong Chen, Chaosheng Fan, Jie He, Changping Peng, Zhangang Lin, Jingping Shao

To address the aforementioned issue, we propose an incremental update framework for online recommenders with Data-Driven Prior (DDP), which is composed of Feature Prior (FP) and Model Prior (MP).

Continual Learning

Parallel Ranking of Ads and Creatives in Real-Time Advertising Systems

no code implementations20 Dec 2023 Zhiguang Yang, Lu Wang, Chun Gan, Liufang Sang, Haoran Wang, Wenlong Chen, Jie He, Changping Peng, Zhangang Lin, Jingping Shao

In this paper, we propose for the first time a novel architecture for online parallel estimation of ads and creatives ranking, as well as the corresponding offline joint optimization model.

Marketing

Post-hoc Bias Scoring Is Optimal For Fair Classification

1 code implementation9 Oct 2023 Wenlong Chen, Yegor Klochkov, Yang Liu

We consider a binary classification problem under group fairness constraints, which can be one of Demographic Parity (DP), Equalized Opportunity (EOp), or Equalized Odds (EO).

Binary Classification Fairness

Calibrating Transformers via Sparse Gaussian Processes

1 code implementation4 Mar 2023 Wenlong Chen, Yingzhen Li

Transformer models have achieved profound success in prediction tasks in a wide range of applications in natural language processing, speech recognition and computer vision.

Bayesian Inference Gaussian Processes +3

JDRec: Practical Actor-Critic Framework for Online Combinatorial Recommender System

no code implementations27 Jul 2022 Xin Zhao, Zhiwei Fang, Yuchen Guo, Jie He, Wenlong Chen, Changping Peng

A combinatorial recommender (CR) system feeds a list of items to a user at a time in the result page, in which the user behavior is affected by both contextual information and items.

Combinatorial Optimization Recommendation Systems

Blending Advertising with Organic Content in E-Commerce: A Virtual Bids Optimization Approach

no code implementations28 May 2021 Carlos Carrion, Zenan Wang, Harikesh Nair, Xianghong Luo, Yulin Lei, Xiliang Lin, Wenlong Chen, Qiyu Hu, Changping Peng, Yongjun Bao, Weipeng Yan

In e-commerce platforms, sponsored and non-sponsored content are jointly displayed to users and both may interactively influence their engagement behavior.

Marketing

Gradient-based tuning of Hamiltonian Monte Carlo hyperparameters

no code implementations1 Jan 2021 Andrew Campbell, Wenlong Chen, Vincent Stimper, José Miguel Hernández-Lobato, Yichuan Zhang

Existing approaches for automating this task either optimise a proxy for mixing speed or consider the HMC chain as an implicit variational distribution and optimize a tractable lower bound that is too loose to be useful in practice.

Cannot find the paper you are looking for? You can Submit a new open access paper.