Search Results for author: Wushao Wen

Found 10 papers, 7 papers with code

Mirror Gradient: Towards Robust Multimodal Recommender Systems via Exploring Flat Local Minima

1 code implementation17 Feb 2024 Shanshan Zhong, Zhongzhan Huang, Daifeng Li, Wushao Wen, Jinghui Qin, Liang Lin

This strategy can implicitly enhance the model's robustness during the optimization process, mitigating instability risks arising from multimodal information inputs.

Multimodal Recommendation

Let's Think Outside the Box: Exploring Leap-of-Thought in Large Language Models with Creative Humor Generation

1 code implementation5 Dec 2023 Shanshan Zhong, Zhongzhan Huang, ShangHua Gao, Wushao Wen, Liang Lin, Marinka Zitnik, Pan Zhou

To this end, we study LLMs on the popular Oogiri game which needs participants to have good creativity and strong associative thinking for responding unexpectedly and humorously to the given image, text, or both, and thus is suitable for LoT study.

Logical Reasoning

LSAS: Lightweight Sub-attention Strategy for Alleviating Attention Bias Problem

1 code implementation9 May 2023 Shanshan Zhong, Wushao Wen, Jinghui Qin, Qiangpu Chen, Zhongzhan Huang

In computer vision, the performance of deep neural networks (DNNs) is highly related to the feature extraction ability, i. e., the ability to recognize and focus on key pixel regions in an image.

SUR-adapter: Enhancing Text-to-Image Pre-trained Diffusion Models with Large Language Models

1 code implementation9 May 2023 Shanshan Zhong, Zhongzhan Huang, Wushao Wen, Jinghui Qin, Liang Lin

Our approach can make text-to-image diffusion models easier to use with better user experience, which demonstrates our approach has the potential for further advancing the development of user-friendly text-to-image generation models by bridging the semantic gap between simple narrative prompts and complex keyword-based prompts.

Knowledge Distillation Text-to-Image Generation

ASR: Attention-alike Structural Re-parameterization

no code implementations13 Apr 2023 Shanshan Zhong, Zhongzhan Huang, Wushao Wen, Jinghui Qin, Liang Lin

This technique enables the mitigation of the extra costs for performance improvement during training, such as parameter size and inference time, through these transformations during inference, and therefore SRP has great potential for industrial and practical applications.

Deepening Neural Networks Implicitly and Locally via Recurrent Attention Strategy

no code implementations27 Oct 2022 Shanshan Zhong, Wushao Wen, Jinghui Qin, Zhongzhan Huang

More and more empirical and theoretical evidence shows that deepening neural networks can effectively improve their performance under suitable training settings.

Switchable Self-attention Module

1 code implementation13 Sep 2022 Shanshan Zhong, Wushao Wen, Jinghui Qin

Attention mechanism has gained great success in vision recognition.

Mix-Pooling Strategy for Attention Mechanism

1 code implementation22 Aug 2022 Shanshan Zhong, Wushao Wen, Jinghui Qin

Recently many effective attention modules are proposed to boot the model performance by exploiting the internal information of convolutional neural networks in computer vision.

Difficulty-aware Image Super Resolution via Deep Adaptive Dual-Network

1 code implementation11 Apr 2019 Jinghui Qin, Ziwei Xie, Yukai Shi, Wushao Wen

To identify whether a region is easy or hard, we propose a novel image difficulty recognition network based on PSNR prior.

Image Super-Resolution

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