Yifei Shen

yshenaw's activity

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

upvoted a collection about 2 hours ago

Mage

Collection

A family of lightweight multimodal models, including understanding and generation. • 7 items • Updated about 3 hours ago • 9

authored a paper 3 days ago

Mage-Flow: An Efficient Native-Resolution Foundation Model for Image Generation and Editing

Paper • 2607.19064 • Published 4 days ago • 64

upvoted 2 papers 3 days ago

SciForma: Structure-Faithful Generation of Scientific Diagrams

Paper • 2607.18091 • Published 5 days ago • 22

Mage-Flow: An Efficient Native-Resolution Foundation Model for Image Generation and Editing

Paper • 2607.19064 • Published 4 days ago • 64

upvoted a paper 17 days ago

SkillOpt-Lite: Better and Faster Agent Self-evolution via One Line of Vibe

Paper • 2607.03451 • Published 22 days ago • 33

submitted a paper to Daily Papers 17 days ago

SkillOpt-Lite: Better and Faster Agent Self-evolution via One Line of Vibe

Paper • 2607.03451 • Published 22 days ago • 33

updated a dataset 24 days ago

yshenaw/SkillOpt_Lite_Benchmarks

Viewer • Updated 24 days ago • 3.83k • 1k

published 2 datasets 24 days ago

yshenaw/SkillOpt_Lite_Benchmarks

Viewer • Updated 24 days ago • 3.83k • 1k

yshenaw/SkillOpt-Lite

Updated 24 days ago • 50

upvoted a paper 2 months ago

ParaVT: Taming the Tool Prior Paradox for Parallel Tool Use in Agentic Video Reinforcement Learning

Paper • 2605.20342 • Published May 19 • 34

liked a dataset 2 months ago

mvp-lab/LLaVA-OneVision-2-Data

Viewer • Updated 4 days ago • 24 • 210k • 32

upvoted a collection 2 months ago

LLaVA-OneVision-2

Collection

2 items • Updated May 20 • 6

upvoted a paper 4 months ago

FileGram: Grounding Agent Personalization in File-System Behavioral Traces

Paper • 2604.04901 • Published Apr 6 • 40

upvoted an article 4 months ago

view article

Article

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

• 

sensenova

•

Mar 5

• 170

upvoted 3 papers 5 months ago

Qwen3-Coder-Next Technical Report

Paper • 2603.00729 • Published Feb 28 • 65

Beyond Language Modeling: An Exploration of Multimodal Pretraining

Paper • 2603.03276 • Published Mar 3 • 107

UniG2U-Bench: Do Unified Models Advance Multimodal Understanding?

Paper • 2603.03241 • Published Mar 3 • 88

submitted a paper to Daily Papers 5 months ago

UniG2U-Bench: Do Unified Models Advance Multimodal Understanding?

Paper • 2603.03241 • Published Mar 3 • 88

upvoted 2 papers 5 months ago

UniT: Unified Multimodal Chain-of-Thought Test-time Scaling

Paper • 2602.12279 • Published Feb 12 • 20

OneVision-Encoder: Codec-Aligned Sparsity as a Foundational Principle for Multimodal Intelligence

Paper • 2602.08683 • Published Feb 9 • 52