Search Results for author: Yi Xin

Found 20 papers, 5 papers with code

Social Learning in Lung Transplant Decision

no code implementations15 Nov 2024 Laura Doval, Federico Echenique Wanying Huang, Yi Xin

We study the allocation of deceased-donor lungs to patients in need of a transplant.

Estimating Nonseparable Selection Models: A Functional Contraction Approach

no code implementations4 Nov 2024 Fan Wu, Yi Xin

We propose a two-step semiparametric maximum likelihood estimator to estimate the selection model and the potential outcome distribution.

Customize Your Visual Autoregressive Recipe with Set Autoregressive Modeling

1 code implementation14 Oct 2024 Wenze Liu, Le Zhuo, Yi Xin, Sheng Xia, Peng Gao, Xiangyu Yue

We reveal that existing AR variants correspond to specific design choices of sequence order and output intervals within the SAR framework, with AR and Masked AR (MAR) as two extreme instances.

Image Generation

High-Fidelity 3D Lung CT Synthesis in ARDS Swine Models Using Score-Based 3D Residual Diffusion Models

no code implementations26 Sep 2024 Siyeop Yoon, Yujin Oh, Xiang Li, Yi Xin, Maurizio Cereda, Quanzheng Li

Acute respiratory distress syndrome (ARDS) is a severe condition characterized by lung inflammation and respiratory failure, with a high mortality rate of approximately 40%.

Computed Tomography (CT) Management +1

Towards Effective User Attribution for Latent Diffusion Models via Watermark-Informed Blending

no code implementations17 Sep 2024 Yongyang Pan, Xiaohong Liu, Siqi Luo, Yi Xin, Xiao Guo, Xiaoming Liu, Xiongkuo Min, Guangtao Zhai

Rapid advancements in multimodal large language models have enabled the creation of hyper-realistic images from textual descriptions.

Recent Trends of Multimodal Affective Computing: A Survey from NLP Perspective

1 code implementation11 Sep 2024 Guimin Hu, Yi Xin, Weimin Lyu, Haojian Huang, Chang Sun, Zhihong Zhu, Lin Gui, Ruichu Cai, Erik Cambria, Hasti Seifi

The goal of this survey is to explore the current landscape of multimodal affective research, identify development trends, and highlight the similarities and differences across various tasks, offering a comprehensive report on the recent progress in multimodal affective computing from an NLP perspective.

Aspect-Based Sentiment Analysis Emotion Recognition in Conversation +3

Enhancing Test Time Adaptation with Few-shot Guidance

no code implementations2 Sep 2024 Siqi Luo, Yi Xin, Yuntao Du, Zhongwei Wan, Tao Tan, Guangtao Zhai, Xiaohong Liu

Furthermore, we propose a two-stage framework to tackle FS-TTA, including (i) fine-tuning the pre-trained source model with few-shot support set, along with using feature diversity augmentation module to avoid overfitting, (ii) implementing test time adaptation based on prototype memory bank guidance to produce high quality pseudo-label for model adaptation.

Diversity domain classification +2

Towards Non-invasive and Personalized Management of Breast Cancer Patients from Multiparametric MRI via A Large Mixture-of-Modality-Experts Model

no code implementations8 Aug 2024 Luyang Luo, Mingxiang Wu, Mei Li, Yi Xin, Qiong Wang, Varut Vardhanabhuti, Winnie CW Chu, Zhenhui Li, Juan Zhou, Pranav Rajpurkar, Hao Chen

MOME exemplifies a discriminative, robust, scalable, and interpretable multimodal model, paving the way for noninvasive, personalized management of breast cancer patients based on multiparametric breast imaging data.

Management

M$^2$IST: Multi-Modal Interactive Side-Tuning for Efficient Referring Expression Comprehension

no code implementations1 Jul 2024 Xuyang Liu, Ting Liu, Siteng Huang, Yi Xin, Yue Hu, Quanjun Yin, Donglin Wang, Honggang Chen

With M$^2$IST, standard transformer-based REC methods present competitive or even superior performance compared to full fine-tuning, while utilizing only 2. 11\% of the tunable parameters, 39. 61\% of the GPU memory, and 63. 46\% of the fine-tuning time required for full fine-tuning.

Referring Expression Referring Expression Comprehension +1

D2O: Dynamic Discriminative Operations for Efficient Generative Inference of Large Language Models

no code implementations18 Jun 2024 Zhongwei Wan, Xinjian Wu, Yu Zhang, Yi Xin, Chaofan Tao, Zhihong Zhu, Xin Wang, Siqi Luo, Jing Xiong, Mi Zhang

Efficient inference in Large Language Models (LLMs) is impeded by the growing memory demands of key-value (KV) caching, especially for longer sequences.

Text Generation

Did Harold Zuercher Have Time-Separable Preferences?

no code implementations12 Jun 2024 Jay Lu, Yao Luo, Kota Saito, Yi Xin

This paper proposes an empirical model of dynamic discrete choice to allow for non-separable time preferences, generalizing the well-known Rust (1987) model.

Towards Understanding the Working Mechanism of Text-to-Image Diffusion Model

no code implementations24 May 2024 Mingyang Yi, Aoxue Li, Yi Xin, Zhenguo Li

We conclude that in the earlier generation stage, the image is mostly decided by the special token [\texttt{EOS}] in the text prompt, and the information in the text prompt is already conveyed in this stage.

Denoising

Sparse-Tuning: Adapting Vision Transformers with Efficient Fine-tuning and Inference

1 code implementation23 May 2024 Ting Liu, Xuyang Liu, Siteng Huang, Liangtao Shi, Zunnan Xu, Yi Xin, Quanjun Yin, Xiaohong Liu

Parameter-efficient fine-tuning (PEFT) has emerged as a popular solution for adapting pre-trained Vision Transformer (ViT) models to downstream applications.

parameter-efficient fine-tuning

Parameter-Efficient Fine-Tuning for Pre-Trained Vision Models: A Survey

1 code implementation3 Feb 2024 Yi Xin, Siqi Luo, Haodi Zhou, Junlong Du, Xiaohong Liu, Yue Fan, Qing Li, Yuntao Du

Large-scale pre-trained vision models (PVMs) have shown great potential for adaptability across various downstream vision tasks.

parameter-efficient fine-tuning Transfer Learning

VMT-Adapter: Parameter-Efficient Transfer Learning for Multi-Task Dense Scene Understanding

no code implementations14 Dec 2023 Yi Xin, Junlong Du, Qiang Wang, Zhiwen Lin, Ke Yan

Extensive experiments on four dense scene understanding tasks demonstrate the superiority of VMT-Adapter(-Lite), achieving a 3. 96%(1. 34%) relative improvement compared to single-task full fine-tuning, while utilizing merely ~1% (0. 36%) trainable parameters of the pre-trained model.

Scene Understanding Transfer Learning

MmAP : Multi-modal Alignment Prompt for Cross-domain Multi-task Learning

no code implementations14 Dec 2023 Yi Xin, Junlong Du, Qiang Wang, Ke Yan, Shouhong Ding

On the one hand, to maximize the complementarity of tasks with high similarity, we utilize a gradient-driven task grouping method that partitions tasks into several disjoint groups and assign a group-shared MmAP to each group.

Decoder Language Modelling +2

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