zpy

zpy777's activity

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

upvoted a paper 2 days ago

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

Paper • 2604.05015 • Published 4 days ago • 219

upvoted 2 papers 7 days ago

LongCat-Next: Lexicalizing Modalities as Discrete Tokens

Paper • 2603.27538 • Published 12 days ago • 137

AI Can Learn Scientific Taste

Paper • 2603.14473 • Published 25 days ago • 417

liked a dataset 27 days ago

markov-ai/computer-use-large

Updated 25 days ago • 119k • 143

authored a paper 28 days ago

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

Paper • 2603.12247 • Published 28 days ago • 23

upvoted 3 papers 28 days ago

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

Paper • 2603.12108 • Published 28 days ago • 8

GRADE: Benchmarking Discipline-Informed Reasoning in Image Editing

Paper • 2603.12264 • Published 28 days ago • 14

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

Paper • 2603.12247 • Published 28 days ago • 23

submitted a paper to Daily Papers 28 days ago

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

Paper • 2603.12247 • Published 28 days ago • 23

published 2 datasets 28 days ago

VisionXLab/FIRM-Gen

Viewer • Updated Feb 27 • 293k • 1.3k

VisionXLab/FIRM-Edit-Instruction

Viewer • Updated Feb 28 • 190k • 249

published a dataset 30 days ago

VisionXLab/FIRM-Edit-Consistency

Viewer • Updated Feb 28 • 180k • 293

updated a collection 30 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 30 days ago • 3

updated a dataset 30 days ago

VisionXLab/FIRM-Bench

Viewer • Updated 30 days ago • 8 • 1.38k

updated a collection about 1 month 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 30 days ago • 3