wangyuchi

YuchiWang's activity

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

authored 2 papers about 19 hours ago

TIDE : Temporal-Aware Sparse Autoencoders for Interpretable Diffusion Transformers in Image Generation

Paper • 2503.07050 • Published Mar 10, 2025

SAIL-Embedding Technical Report: Omni-modal Embedding Foundation Model

Paper • 2510.12709 • Published Oct 14, 2025 • 13

New activity in TIGER-Lab/MMEB-V2 4 months ago

PNG file corruption

3

#8 opened 6 months ago by

Lingshaw

updated a collection 5 months ago

SAIL-Embedding

Collection

Omni-modal Embedding Foundation Model • 1 item • Updated Oct 17, 2025 • 2

upvoted a paper 5 months ago

SAIL-Embedding Technical Report: Omni-modal Embedding Foundation Model

Paper • 2510.12709 • Published Oct 14, 2025 • 13

authored a paper 6 months ago

RICO: Improving Accuracy and Completeness in Image Recaptioning via Visual Reconstruction

Paper • 2505.22613 • Published May 28, 2025 • 9

upvoted a paper 10 months ago

RICO: Improving Accuracy and Completeness in Image Recaptioning via Visual Reconstruction

Paper • 2505.22613 • Published May 28, 2025 • 9

commented a paper 10 months ago

RICO: Improving Accuracy and Completeness in Image Recaptioning via Visual Reconstruction

Paper • 2505.22613 • Published May 28, 2025 • 9 •

2

upvoted a paper 10 months ago

MiniMax-Speech: Intrinsic Zero-Shot Text-to-Speech with a Learnable Speaker Encoder

Paper • 2505.07916 • Published May 12, 2025 • 134

upvoted a paper about 1 year ago

ReCamMaster: Camera-Controlled Generative Rendering from A Single Video

Paper • 2503.11647 • Published Mar 14, 2025 • 148

authored a paper about 1 year ago

VidTwin: Video VAE with Decoupled Structure and Dynamics

Paper • 2412.17726 • Published Dec 23, 2024 • 9

upvoted a paper about 1 year ago

VidTwin: Video VAE with Decoupled Structure and Dynamics

Paper • 2412.17726 • Published Dec 23, 2024 • 9

commented a paper about 1 year ago

VidTwin: Video VAE with Decoupled Structure and Dynamics

Paper • 2412.17726 • Published Dec 23, 2024 • 9 •

3

liked a model about 1 year ago

microsoft/VidTok

Updated Apr 5, 2025 • 42

authored 4 papers over 1 year ago

Towards End-to-End Embodied Decision Making via Multi-modal Large Language Model: Explorations with GPT4-Vision and Beyond

Paper • 2310.02071 • Published Oct 3, 2023 • 4

GAIA: Zero-shot Talking Avatar Generation

Paper • 2311.15230 • Published Nov 26, 2023 • 3

UniEdit: A Unified Tuning-Free Framework for Video Motion and Appearance Editing

Paper • 2402.13185 • Published Feb 20, 2024

PCA-Bench: Evaluating Multimodal Large Language Models in Perception-Cognition-Action Chain

Paper • 2402.15527 • Published Feb 21, 2024