KeyKy

kangyang's activity

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

upvoted a paper 9 days ago

VBVR-Pro: A Scalable and Verifiable Suite for Native Visual Reasoning

Paper • 2608.26105 • Published 11 days ago • 269

upvoted a paper 11 days ago

LAION-BVD: A 10-Million-Hour Open Video Dataset for Multimodal Pre-training

Paper • 2608.24845 • Published 12 days ago • 15

upvoted a paper about 1 month ago

ReToken: One Token to Improve Vision-Language Models for Visual Retrieval

Paper • 2607.28627 • Published Jul 30 • 9

New activity in google/gemma-4-12B 3 months ago

ValueError: Cannot use apply_chat_template because this processor does not have a chat template.

#3 opened 3 months ago by

kangyang

liked a model 5 months ago

moonshotai/Kimi-K2.6

Image-Text-to-Text • 1T • Updated May 19 • 622k • • 1.6k

upvoted 2 papers 5 months ago

Vero: An Open RL Recipe for General Visual Reasoning

Paper • 2604.04917 • Published Apr 6 • 34

LongCat-Next: Lexicalizing Modalities as Discrete Tokens

Paper • 2603.27538 • Published Mar 29 • 151

New activity in meituan-longcat/LongCat-Next 5 months ago

repeat input_ids.size(1) in dim1

1

#3 opened 5 months ago by

kangyang

New activity in zai-org/GLM-4.6V-Flash 9 months ago

GLM-4.6V-Flash 也需要用Glm4vMoeForConditionalGeneration初始化吗

2

#10 opened 9 months ago by

kangyang

commented a paper 9 months ago

Chain-of-Visual-Thought: Teaching VLMs to See and Think Better with Continuous Visual Tokens

Paper • 2511.19418 • Published Nov 24, 2025 • 29 •

4

liked a dataset over 2 years ago

cosmicman/CosmicManHQ-1.0

Updated Jun 15, 2024 • 150 • 40