Chenyang Si

α-Synuclein aggregation and brain atrophy in SNCA-A53T transgenic monkeys are correlated with parkinsonism

Hongjiang Zhang, Lu Zhao, Weizhi Ji, Dingna Duan et autres

Mutations in the SNCA gene encoding α-synuclein underlie familial early-onset Parkinson’s disease. Pathological α-synuclein deposition may commence decades prior to the emergence of cardinal motor symptoms. Long-term investigation of brain and behavioural development in an SNCA-A53T transgenic macaque model offers critical insights …

us (code pays fourni par la source)

AniFeats: Animate 3D Feature Meshes for Character Video Generation

Beijia Lu, Zekai Gu, Zhiyang Dou, Haotian Yuan et autres

Generating high-quality character animation videos is a fascinating yet challenging task. Existing methods use geometry guidance signals like skeletons, normal maps, or depth maps in a diffusion model to generate character videos from a single reference image. Although these approaches have shown …

us, hk, cn, sg (code pays fourni par la source)

One-to-More: High-Fidelity Training-Free Anomaly Generation with Attention Control

Haoxiang Rao, Zhao Wang, Chenyang Si, Yan Lyu et autres

Industrial anomaly detection (AD) is characterized by an abundance of normal images but a scarcity of anomalous ones. Although numerous few-shot anomaly synthesis methods have been proposed to augment anomalous data for downstream AD tasks, most existing approaches require time-consuming training and …

Formation and evolution of mammalian endothelial organotypicity

Qian Xin, Zongcheng Li, Siyuan Hou, Xiaochen Ding et autres

Dataset OverviewThis dataset comprises single-cell transcriptomic profiles of endothelial cells isolated from developing organ primordia across three species: human, monkey, and mouse. The data captures critical developmental windows corresponding to early organogenesis stages.Data InformationSingle‑cell expression data and metadata for human, macaque, and …

cn, ph (code pays fourni par la source)

α-Synuclein aggregation and brain atrophy in SNCA-A53T transgenic monkeys are correlated with parkinsonism

Jingkuan Wei, Shulin Li, Dingna Duan, Kunhua Wu et autres

Mutations in the SNCA gene encoding α-synuclein underlie familial early-onset Parkinson’s disease. Pathological α-synuclein deposition may commence decades prior to the emergence of cardinal motor symptoms. Long-term investigation of brain and behavioural development in an SNCA-A53T transgenic macaque model offers critical insights …

cn, us (code pays fourni par la source)

PosterCopilot: Toward Layout Reasoning and Controllable Editing for Professional Graphic Design

Kezhi Li, Tianyu Lao, Haofan Wang, Liang Wang et autres

Graphic design forms the cornerstone of modern visual communication, serving as a vital medium for promoting cultural and commercial events. Recent advances have explored automating this process using Large Multimodal Models (LMMs), yet existing methods often produce geometrically inaccurate layouts and lack …

DiverseAR: Boosting Diversity in Bitwise Autoregressive Image Generation

Ying Yang, Zhengyao Lv, Haofan Wang, Binxin Yang et autres

In this paper, we investigate the underexplored challenge of sample diversity in autoregressive (AR) generative models with bitwise visual tokenizers. We first analyze the factors that limit diversity in bitwise AR models and identify two key issues: (1) the binary classification nature …

VBench++: Comprehensive and Versatile Benchmark Suite for Video Generative Models

Ziqi Huang, Xiaojie Xu, Yinan He, Jiashuo Yu et autres

Video generation has witnessed significant advancements, yet evaluating these models remains a challenge. A comprehensive evaluation benchmark for video generation is indispensable for two reasons: 1) Existing metrics do not fully align with human perceptions; 2) An ideal evaluation system should provide …

sg, cn (code pays fourni par la source)

FreeMorph: Tuning-Free Generalized Image Morphing with Diffusion Model

Yukang Cao, Chenyang Si, Jinghao Wang, Ziwei Liu

We present FreeMorph, the first tuning-free method for image morphing that accommodates inputs with different semantics or layouts. Unlike existing methods that rely on finetuning pre-trained diffusion models and are limited by time constraints and semantic/layout discrepancies, FreeMorph delivers high-fidelity image morphing …

sg, cn, hk (code pays fourni par la source)

Rethinking Cross-Modal Interaction in Multimodal Diffusion Transformers

Zepeng Lv, Chenyang Si, Wangmeng Zuo, Ziwei Liu

Multimodal Diffusion Transformers (MM-DiTs) have achieved remarkable progress in text-driven visual generation. However, even state-of-the-art MM-DiT models like FLUX struggle with achieving precise alignment between text prompts and generated content. We identify two key issues in the attention mechanism of MM-DiT, namely …

hk, cn, sg (code pays fourni par la source)

Boosting Diffusion U-Net with Free Lunch for Text-to-Image and Text-to-Video Generation

Chenyang Si, Ziqi Huang, Yuming Jiang, Ziwei Liu

sg (code pays fourni par la source)

LongVie: Multimodal-Guided Controllable Ultra-Long Video Generation

Jianxiong Gao, Zhaoxi Chen, Xian Liu, Jianfeng Feng et autres

Controllable ultra-long video generation is a fundamental yet challenging task. Although existing methods are effective for short clips, they struggle to scale due to issues such as temporal inconsistency and visual degradation. In this paper, we initially investigate and identify three key …