Sean Yu

yushaohan's activity

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

upvoted a paper 3 days ago

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

Paper • 2608.05000 • Published 5 days ago • 55

upvoted 2 papers 5 days ago

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

Paper • 2608.03971 • Published 6 days ago • 21

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

Paper • 2608.02602 • Published 7 days ago • 78

upvoted a paper 11 days ago

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

Paper • 2607.24904 • Published 14 days ago • 36

upvoted a paper 12 days ago

Kimi K3: Open Frontier Intelligence

Paper • 2607.24653 • Published 14 days ago • 486

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

• 175

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

upvoted 3 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

MinerU-Diffusion: Rethinking Document OCR as Inverse Rendering via Diffusion Decoding

Paper • 2603.22458 • Published Mar 23 • 139

upvoted a paper 5 months ago

LongCat-Flash-Prover: Advancing Native Formal Reasoning via Agentic Tool-Integrated Reinforcement Learning

Paper • 2603.21065 • Published Mar 22 • 78

upvoted a paper 6 months ago

DeepSight: An All-in-One LM Safety Toolkit

Paper • 2602.12092 • Published Feb 12 • 15

upvoted a collection 7 months ago

ProGuard

Collection

https://yushaohan.github.io/ProGuard/ • 4 items • Updated Jul 3 • 1