Xue Yang

yangxue's activity

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

authored a paper 12 minutes ago

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

Paper • 2604.05015 • Published 2 days ago • 168

upvoted a paper about 6 hours ago

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

Paper • 2604.05015 • Published 2 days ago • 168

upvoted a paper 1 day ago

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

Paper • 2604.04184 • Published 3 days ago • 41

upvoted a collection 23 days ago

FIRM-Reward

Collection

The data and models of "Trust Your Critic: Robust Reward Modeling and Reinforcement Learning for Faithful Image Editing and Generation" • 8 items • Updated 26 days ago • 1

authored a paper 26 days ago

GRADE: Benchmarking Discipline-Informed Reasoning in Image Editing

Paper • 2603.12264 • Published 27 days ago • 14

liked a dataset 26 days ago

VisionXLab/GRADE

Viewer • Updated 26 days ago • 1.04k • 7.18k • 7

updated a dataset 26 days ago

VisionXLab/GRADE

Viewer • Updated 26 days ago • 1.04k • 7.18k • 7

upvoted 3 papers 26 days ago

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

Paper • 2603.12108 • Published 27 days ago • 8

Trust Your Critic: Robust Reward Modeling and Reinforcement Learning for Faithful Image Editing and Generation

Paper • 2603.12247 • Published 27 days ago • 23

GRADE: Benchmarking Discipline-Informed Reasoning in Image Editing

Paper • 2603.12264 • Published 27 days ago • 14

submitted a paper to Daily Papers 26 days ago

GRADE: Benchmarking Discipline-Informed Reasoning in Image Editing

Paper • 2603.12264 • Published 27 days ago • 14

updated a collection 26 days ago

FIRM-Reward

Collection

The data and models of "Trust Your Critic: Robust Reward Modeling and Reinforcement Learning for Faithful Image Editing and Generation" • 8 items • Updated 26 days ago • 1

updated a collection 28 days ago

FIRM-Reward

Collection

The data and models of "Trust Your Critic: Robust Reward Modeling and Reinforcement Learning for Faithful Image Editing and Generation" • 8 items • Updated 26 days ago • 1

upvoted 3 papers 28 days ago

InternVL-U: Democratizing Unified Multimodal Models for Understanding, Reasoning, Generation and Editing

Paper • 2603.09877 • Published 29 days ago • 47

Stepping VLMs onto the Court: Benchmarking Spatial Intelligence in Sports

Paper • 2603.09896 • Published 29 days ago • 26

Holi-Spatial: Evolving Video Streams into Holistic 3D Spatial Intelligence

Paper • 2603.07660 • Published about 1 month ago • 85