YSH

BestWishYsh's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted a paper 1 day ago

Lumos-1: On Autoregressive Video Generation from a Unified Model Perspective

Paper • 2507.08801 • Published 7 days ago • 27

upvoted a paper 3 days ago

SpeakerVid-5M: A Large-Scale High-Quality Dataset for Audio-Visual Dyadic Interactive Human Generation

Paper • 2507.09862 • Published 4 days ago • 46

upvoted 2 papers 9 days ago

A Survey on Latent Reasoning

Paper • 2507.06203 • Published 10 days ago • 80

Tora2: Motion and Appearance Customized Diffusion Transformer for Multi-Entity Video Generation

Paper • 2507.05963 • Published 10 days ago • 10

upvoted 2 papers 10 days ago

VMoBA: Mixture-of-Block Attention for Video Diffusion Models

Paper • 2506.23858 • Published 18 days ago • 30

StreamDiT: Real-Time Streaming Text-to-Video Generation

Paper • 2507.03745 • Published 14 days ago • 28

upvoted an article 11 days ago

view article

Article

Fine-tuning Llama 2 70B using PyTorch FSDP

By and 3 others •

Sep 13, 2023

• 26

upvoted an article 18 days ago

view article

Article

FramePack LoRA Experiment

By •

Apr 19

• 22

upvoted a paper about 1 month ago

PolyVivid: Vivid Multi-Subject Video Generation with Cross-Modal Interaction and Enhancement

Paper • 2506.07848 • Published Jun 9 • 4

upvoted a collection about 1 month ago

🌞 May 2025 - Open works from the Chinese community

Collection

43 items • Updated 30 days ago • 9

upvoted a paper about 1 month ago

UniWorld: High-Resolution Semantic Encoders for Unified Visual Understanding and Generation

Paper • 2506.03147 • Published Jun 3 • 58

upvoted 9 papers about 2 months ago

MAGREF: Masked Guidance for Any-Reference Video Generation

Paper • 2505.23742 • Published May 29 • 9

OmniConsistency: Learning Style-Agnostic Consistency from Paired Stylization Data

Paper • 2505.18445 • Published May 24 • 65

SageAttention2++: A More Efficient Implementation of SageAttention2

Paper • 2505.21136 • Published May 27 • 47

Sci-Fi: Symmetric Constraint for Frame Inbetweening

Paper • 2505.21205 • Published May 27 • 5

ImgEdit: A Unified Image Editing Dataset and Benchmark

Paper • 2505.20275 • Published May 26 • 17

OpenS2V-Nexus: A Detailed Benchmark and Million-Scale Dataset for Subject-to-Video Generation

Paper • 2505.20292 • Published May 26 • 54

Model Merging in Pre-training of Large Language Models

Paper • 2505.12082 • Published May 17 • 37

QuickVideo: Real-Time Long Video Understanding with System Algorithm Co-Design

Paper • 2505.16175 • Published May 22 • 42

Scaling Diffusion Transformers Efficiently via μP

Paper • 2505.15270 • Published May 21 • 34