Sean Yu

yushaohan's activity

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

upvoted a paper 2 days ago

Towards Physics of Multimodal Pretraining: Knowledge Flow, Modality Synergy, Early Unification, and Recipes

Paper • 2608.05000 • Published 3 days ago • 51

upvoted 2 papers 3 days ago

UniWorld-Design: From Pixel Generation to Layer-Native Design

Paper • 2608.03971 • Published 4 days ago • 19

AURORA-LM: Autoencoding Unified Representation for Continuous-Latent Diffusion Language Modeling

Paper • 2608.02602 • Published 5 days ago • 77

upvoted a paper 10 days ago

Mage-VL: An Efficient Codec-Native Streaming Multimodal Foundation Model

Paper • 2607.24904 • Published 12 days ago • 35

upvoted a paper 11 days ago

Kimi K3: Open Frontier Intelligence

Paper • 2607.24653 • Published 12 days ago • 483

liked a model 12 days ago

yushaohan/ProGuard-3B

Image-Text-to-Text • 4B • Updated Feb 15 • 61 • 1

liked a dataset 12 days ago

yushaohan/ProGuard-data

Viewer • Updated Jan 12 • 87k • 100 • 1

liked a model 12 days ago

yushaohan/ProGuard-7B

Image-Text-to-Text • 8B • Updated Feb 15 • 51 • 1

upvoted 2 papers about 1 month ago

Vision as Unified Multimodal Generation

Paper • 2607.06560 • Published Jul 7 • 48

NormGuard: Reward-Preserving Norm Constraints in Flow-Matching Reinforcement Learning

Paper • 2606.27771 • Published Jun 26 • 4

upvoted an article about 2 months ago

view article

Article

NEO-unify: Building Native Multimodal Unified Models End to End

• 

sensenova

•

Mar 5

• 174

upvoted a collection about 2 months ago

V-JEPA 2

Collection

A frontier video understanding model developed by FAIR, Meta, which extends the pretraining objectives of https://ai.meta.com/blog/v-jepa-yann • 8 items • Updated Jun 13, 2025 • 228

upvoted a paper about 2 months ago

InterleaveThinker: Reinforcing Agentic Interleaved Generation

Paper • 2606.13679 • Published Jun 11 • 84

upvoted a paper 2 months ago

From Pixels to Words -- Towards Native One-Vision Models at Scale

Paper • 2605.28820 • Published May 27 • 76

upvoted 3 papers 3 months ago

SenseNova-U1: Unifying Multimodal Understanding and Generation with NEO-unify Architecture

Paper • 2605.12500 • Published May 12 • 195

Continuous Latent Diffusion Language Model

Paper • 2605.06548 • Published May 7 • 87

Tuna-2: Pixel Embeddings Beat Vision Encoders for Multimodal Understanding and Generation

Paper • 2604.24763 • Published Apr 27 • 71

commented a paper 3 months ago

WorldMark: A Unified Benchmark Suite for Interactive Video World Models

Paper • 2604.21686 • Published Apr 23 • 36 •

3

upvoted 2 papers 4 months ago

Prompt Relay: Inference-Time Temporal Control for Multi-Event Video Generation

Paper • 2604.10030 • Published Apr 11 • 15

LongCat-Next: Lexicalizing Modalities as Discrete Tokens

Paper • 2603.27538 • Published Mar 29 • 150