Xue Yang

yangxue's activity

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

upvoted a paper 12 days ago

FilmFlow: Agentic System for 3D Virtual Film Cinematography

Paper • 2610.30753 • Published 14 days ago • 29

upvoted a paper 14 days ago

EvaOmni: An Evidence-Grounded Benchmark for Audio-Visual Reasoning

Paper • 2610.28444 • Published 16 days ago • 24

upvoted a paper 26 days ago

Reasoning-Informed Visual Editing

Paper • 2610.12343 • Published 28 days ago • 20

updated a dataset 27 days ago

VisionXLab/RISEBench-plusplus

Viewer • Updated 27 days ago • 1.61k • 1.31k

upvoted a paper 4 months ago

Ideas Have Genomes: Benchmarking Scientific Lineage Reasoning and Lineage-Grounded Idea Generation

Paper • 2607.08758 • Published Jul 9 • 38

updated a dataset 4 months ago

VisionXLab/DisciplineGen-1M

Viewer • Updated Jul 3 • 1.1M • 1.2k • 5

published a dataset 4 months ago

VisionXLab/DisciplineGen-1M

Viewer • Updated Jul 3 • 1.1M • 1.2k • 5

upvoted 4 papers 5 months ago

Moment-Video: Diagnosing Temporal Fidelity of Video MLLMs on Momentary Visual Events

Paper • 2606.02522 • Published Jun 1 • 13

From Raw Experience to Skill Consumption: A Systematic Study of Model-Generated Agent Skills

Paper • 2605.23899 • Published May 22 • 27

PhotoFlow: Agentic 3D Virtual Photography Missions

Paper • 2605.23771 • Published May 22 • 25

SkillOpt: Executive Strategy for Self-Evolving Agent Skills

Paper • 2605.23904 • Published May 22 • 220

updated a dataset 7 months ago

VisionXLab/GRADE

Viewer • Updated Apr 22 • 1.04k • 354 • 8

upvoted an article 7 months ago

view article

Article

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

• 

sensenova

•

Mar 5

• 182

authored a paper 7 months ago

Video-MME-v2: Towards the Next Stage in Benchmarks for Comprehensive Video Understanding

Paper • 2604.05015 • Published Apr 6 • 229

upvoted 2 papers 7 months ago

Video-MME-v2: Towards the Next Stage in Benchmarks for Comprehensive Video Understanding

Paper • 2604.05015 • Published Apr 6 • 229

AURA: Always-On Understanding and Real-Time Assistance via Video Streams

Paper • 2604.04184 • Published Apr 5 • 51

upvoted a collection 8 months ago

FIRM-Reward

Collection

The data and models of the FIRM series. • 13 items • Updated Aug 24 • 1

authored a paper 8 months ago

GRADE: Benchmarking Discipline-Informed Reasoning in Image Editing

Paper • 2603.12264 • Published Mar 12 • 15

liked a dataset 8 months ago

VisionXLab/GRADE

Viewer • Updated Apr 22 • 1.04k • 354 • 8

upvoted a paper 8 months ago

EvoTok: A Unified Image Tokenizer via Residual Latent Evolution for Visual Understanding and Generation

Paper • 2603.12108 • Published Mar 12 • 8