Yang Yi YOU? Author Swipe

Last 10y

The Faintest, Extremely Variable X-ray Tidal Disruption Event from a Supermassive Black Hole Binary? Open

Huang Mengqiu, Xue Yong-quan, Li Shuo, Liu Fukun, Zhu, Shifu , et al. · 2025

Tidal disruption events (TDEs), which occur when stars enter the tidal radii of supermassive black holes (SMBHs) and are subsequently torn apart by their tidal forces, represent intriguing phenomena that stimulate growing research interest…

BideDPO: Conditional Image Generation with Simultaneous Text and Condition Alignment Open

Zhou De-wei, Li Mingwei, Yang Zongxin, Lu Yu, Xu, Yunqiu , et al. · 2025

Conditional image generation enhances text-to-image synthesis with structural, spatial, or stylistic priors, but current methods face challenges in handling conflicts between sources. These include 1) input-level conflicts, where the condi…

Merging without Forgetting: Continual Fusion of Task-Specific Models via Optimal Transport Open

Pan Zecheng, Chen Zhikang, Li Ding, Zhang Min, Cui Sen , et al. · 2025

Merging models fine-tuned for different tasks into a single unified model has become an increasingly important direction for building versatile, efficient multi-task systems. Existing approaches predominantly rely on parameter interpolatio…

Are Image-to-Video Models Good Zero-Shot Image Editors? Open

Zhang Zechuan, Chen Zhen-yuan, Yang Zongxin, Yang, Yi · 2025

Large-scale video diffusion models show strong world simulation and temporal reasoning abilities, but their use as zero-shot image editors remains underexplored. We introduce IF-Edit, a tuning-free framework that repurposes pretrained imag…

Merging without Forgetting: Continual Fusion of Task-Specific Models via Optimal Transport Open

Pan Zecheng, Chen Zhikang, Li Ding, Zhang Min, Cui Sen , et al. · 2025

Merging models fine-tuned for different tasks into a single unified model has become an increasingly important direction for building versatile, efficient multi-task systems. Existing approaches predominantly rely on parameter interpolatio…

BideDPO: Conditional Image Generation with Simultaneous Text and Condition Alignment Open

Zhou De-wei, Li Mingwei, Yang Zongxin, Lu Yu, Xu, Yunqiu , et al. · 2025

Conditional image generation enhances text-to-image synthesis with structural, spatial, or stylistic priors, but current methods face challenges in handling conflicts between sources. These include 1) input-level conflicts, where the condi…

Are Image-to-Video Models Good Zero-Shot Image Editors? Open

Zhang Zechuan, Chen Zhen-yuan, Yang Zongxin, Yang, Yi · 2025

Large-scale video diffusion models show strong world simulation and temporal reasoning abilities, but their use as zero-shot image editors remains underexplored. We introduce IF-Edit, a tuning-free framework that repurposes pretrained imag…

Mantis: A Versatile Vision-Language-Action Model with Disentangled Visual Foresight Open

Yang Yi, Li Xueqi, Chen Yiyang, Song Jin, Wang, Yihan , et al. · 2025

Recent advances in Vision-Language-Action (VLA) models demonstrate that visual signals can effectively complement sparse action supervisions. However, letting VLA directly predict high-dimensional visual states can distribute model capacit…

Gut microbiota signature in a cohort of Chinese patients with rosacea Open

Zheng Zhao, Lulu Lu, Yang, Yi, Na Gao, Jiangang Hu , et al. · 2025

Mantis: A Versatile Vision-Language-Action Model with Disentangled Visual Foresight Open

Yang Yi, Li Xueqi, Chen Yiyang, Song Jin, Wang, Yihan , et al. · 2025

Recent advances in Vision-Language-Action (VLA) models demonstrate that visual signals can effectively complement sparse action supervisions. However, letting VLA directly predict high-dimensional visual states can distribute model capacit…

Gut microbiota signature in a cohort of Chinese patients with rosacea Open

Zheng Zhao, Lulu Lu, Yang Yi, Na Gao, Jiangang Hu , et al. · 2025

Background: Rosacea is a chronic inflammatory skin disease characterized by diverse symptoms and variable clinical progression, which can significantly impair patients' quality of life and mental health. The exact etiology of rosacea remai…

Multi-Text Guided Few-Shot Semantic Segmentation Open

Jiao Qiang, Yan Bin, Yang Yi, Shi, Mengrui, Zhang Qiang · 2025

Recent CLIP-based few-shot semantic segmentation methods introduce class-level textual priors to assist segmentation by typically using a single prompt (e.g., a photo of class). However, these approaches often result in incomplete activati…

Multi-Text Guided Few-Shot Semantic Segmentation Open

Jiao Qiang, Yan Bin, Yang Yi, Shi, Mengrui, Zhang Qiang · 2025

Recent CLIP-based few-shot semantic segmentation methods introduce class-level textual priors to assist segmentation by typically using a single prompt (e.g., a photo of class). However, these approaches often result in incomplete activati…

EZH2 crosstalk with RNA methylation promotes prostate cancer progression through modulation of m6A autoregulation pathway Open

Yang Yi, Joshua Fry, ChaeHyun Yum, Rui Wang, Siqi Wu , et al. · 2025

N6-methyladenosine (m6A), the most predominant RNA modification in humans, participates in various fundamental and pathological bioprocesses. Dynamic manipulation of m6A deposition in the transcriptome is critical for cancer progression, w…

EZH2 crosstalk with RNA methylation promotes prostate cancer progression through modulation of m6A autoregulation pathway Open

Yang Yi, Joshua Fry, ChaeHyun Yum, Rui Wang, Siqi Wu , et al. · 2025

N6-methyladenosine (m6A), the most predominant RNA modification in humans, participates in various fundamental and pathological bioprocesses. Dynamic manipulation of m6A deposition in the transcriptome is critical for cancer progression, w…

PCA++: How Uniformity Induces Robustness to Background Noise in Contrastive Learning Open

Wu Mingqi, Sun Qiang, Yang Yi · 2025

High-dimensional data often contain low-dimensional signals obscured by structured background noise, which limits the effectiveness of standard PCA. Motivated by contrastive learning, we address the problem of recovering shared signal subs…

PCA++: How Uniformity Induces Robustness to Background Noise in Contrastive Learning Open

Wu, Mingqi, Sun Qiang, Yang Yi · 2025

High-dimensional data often contain low-dimensional signals obscured by structured background noise, which limits the effectiveness of standard PCA. Motivated by contrastive learning, we address the problem of recovering shared signal subs…

PCA++: How Uniformity Induces Robustness to Background Noise in Contrastive Learning Open

Wu Mingqi, Sun Qiang, Yang Yi · 2025

High-dimensional data often contain low-dimensional signals obscured by structured background noise, which limits the effectiveness of standard PCA. Motivated by contrastive learning, we address the problem of recovering shared signal subs…

Analysis of the economic benefits and feasibility of the same-city delivery model for donor human milk (SCDM-DHM) Open

Dingding Yin, Yang Yi, Kang-Mei Huang, Yijun Chen, Huali Zheng , et al. · 2025

The SCDM-DHM is an adaptation of existing international approaches to the unique infrastructure and policy environment in China. The SCDM-DHM improved breastfeeding rate in the NICU without a human milk bank and remained cost-efficient, de…

Analysis of the economic benefits and feasibility of the same-city delivery model for donor human milk (SCDM-DHM) Open

Dingding Yin, Yang Yi, Kangmei Huang, Yijun Chen, Huali Zheng , et al. · 2025

The SCDM-DHM is an adaptation of existing international approaches to the unique infrastructure and policy environment in China. The SCDM-DHM improved breastfeeding rate in the NICU without a human milk bank and remained cost-efficient, de…

An Alternative Method to Confirm the Tidal Inspiral of Hot Jupiter Kepler-1658b Open

Yi-chen Ma, Jinyi Zhou, Yang Yi · 2025

The tidal decay phenomenon of hot Jupiters has been a significant research topic. Multiple hot Jupiters have been observed by missions including the Kepler space telescope and the Transiting Exoplanet Survey Satellite (TESS) to confirm the…

Ringdown of a black hole embedded in a Burkert dark matter halo Open

Yang Yi, Lambiase, Gaetano, Övgün, Ali, Liu Dong, Long Zheng-Wen · 2025

We construct a new static, spherically symmetric black hole spacetime embedded in a dark matter halo whose density follows the cored Burkert profile. Starting from the halo-only geometry determined by the rotation curve relation, we solve …

An axisymmetric shock breakout indicated by prompt polarized emission from the type II supernova 2024ggi Open

Yang Yi, Wen Xudong, Wang, Lifan, Baade, Dietrich, Wheeler, J. Craig , et al. · 2025

The death of massive stars is triggered by an infall-induced bounce shock that disrupts the star. How such a shock is launched and propagates through the star is a decade-long puzzle. Some models assume that the shock can be reenergized by…

Melodia: Training-Free Music Editing Guided by Attention Probing in Diffusion Models Open

Yang Yi, Li Haowen, Li Tianxiang, Cao Boyu, Zhang Xiao-han , et al. · 2025

Text-to-music generation technology is progressing rapidly, creating new opportunities for musical composition and editing. However, existing music editing methods often fail to preserve the source music's temporal structure, including mel…

An Alternative Method to Confirm the Tidal Inspiral of Hot Jupiter Kepler-1658b Open

Yichen Ma, Jinyi Zhou, Yang Yi · 2025

The tidal decay phenomenon of hot Jupiters has been a significant research topic. Multiple hot Jupiters have been observed by missions including the Kepler space telescope and the Transiting Exoplanet Survey Satellite (TESS) to confirm the…

Melodia: Training-Free Music Editing Guided by Attention Probing in Diffusion Models Open

Yang Yi, Li Haowen, Li Tianxiang, Cao Boyu, Zhang Xiao-han , et al. · 2025

Text-to-music generation technology is progressing rapidly, creating new opportunities for musical composition and editing. However, existing music editing methods often fail to preserve the source music's temporal structure, including mel…

Ringdown of a black hole embedded in a Burkert dark matter halo Open

Yang Yi, Lambiase, Gaetano, Övgün, Ali, Liu Dong, Long, Zheng-Wen · 2025

We construct a new static, spherically symmetric black hole spacetime embedded in a dark matter halo whose density follows the cored Burkert profile. Starting from the halo-only geometry determined by the rotation curve relation, we solve …

Melodia: Training-Free Music Editing Guided by Attention Probing in Diffusion Models Open

Yang Yi, Li Haowen, Li Tianxiang, Cao Boyu, Zhang Xiaohan , et al. · 2025

Text-to-music generation technology is progressing rapidly, creating new opportunities for musical composition and editing. However, existing music editing methods often fail to preserve the source music's temporal structure, including mel…

Ringdown of a black hole embedded in a Burkert dark matter halo Open

Yang Yi, Lambiase, Gaetano, Övgün, Ali, Liu Dong, Long, Zheng-Wen · 2025

We construct a new static, spherically symmetric black hole spacetime embedded in a dark matter halo whose density follows the cored Burkert profile. Starting from the halo-only geometry determined by the rotation curve relation, we solve …

Beyond Uniform Deletion: A Data Value-Weighted Framework for Certified Machine Unlearning Open

He, Lisong, Yang Yi, Chang Xiangyu · 2025

As the right to be forgotten becomes legislated worldwide, machine unlearning mechanisms have emerged to efficiently update models for data deletion and enhance user privacy protection. However, existing machine unlearning algorithms frequ…

Fetching topic information...