Xilin Wei

Wiselnn's activity

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

updated 2 models 5 days ago

Wiselnn/Qwen2-VL-tad_rope-128frames-8k-context-330k-llava-video

Updated 5 days ago • 1

Wiselnn/Qwen2-VL-vanilla_rope-128frames-8k-context-330k-llava-video

Updated 5 days ago • 1

updated a collection 5 days ago

VideoRoPE: What Makes for Good Video Rotary Position Embeddi

Collection

A storage repo for VideoRoPE. • 5 items • Updated 5 days ago • 2

published 2 models 5 days ago

Wiselnn/Qwen2-VL-tad_rope-128frames-8k-context-330k-llava-video

Updated 5 days ago • 1

Wiselnn/Qwen2-VL-vanilla_rope-128frames-8k-context-330k-llava-video

Updated 5 days ago • 1

updated a model 5 days ago

Wiselnn/Qwen2-VL-m_rope-128frames-8k-context-330k-llava-video

Updated 5 days ago • 1

updated a collection 5 days ago

VideoRoPE: What Makes for Good Video Rotary Position Embeddi

Collection

A storage repo for VideoRoPE. • 5 items • Updated 5 days ago • 2

updated a model 5 days ago

Wiselnn/Qwen2-VL-videorope-128frames-8k-context-330k-llava-video

Updated 5 days ago • 3

published 2 models 5 days ago

Wiselnn/Qwen2-VL-m_rope-128frames-8k-context-330k-llava-video

Updated 5 days ago • 1

Wiselnn/Qwen2-VL-videorope-128frames-8k-context-330k-llava-video

Updated 5 days ago • 3

liked a dataset 11 days ago

facebook/natural_reasoning

Viewer • Updated Feb 21 • 1.15M • 4.61k • 498

upvoted 2 papers 18 days ago

VCR-Bench: A Comprehensive Evaluation Framework for Video Chain-of-Thought Reasoning

Paper • 2504.07956 • Published 19 days ago • 45

MM-IFEngine: Towards Multimodal Instruction Following

Paper • 2504.07957 • Published 19 days ago • 34

New activity in Wiselnn/VideoRoPE 22 days ago

Add link to paper and task category

#2 opened 22 days ago by

nielsr

New activity in facebook/multi-token-prediction about 2 months ago

How to generate multiple tokens at once?

1

1

#14 opened about 2 months ago by

Wiselnn

upvoted a paper about 2 months ago

Unified Reward Model for Multimodal Understanding and Generation

Paper • 2503.05236 • Published Mar 7 • 123

upvoted a collection about 2 months ago

VideoRoPE: What Makes for Good Video Rotary Position Embeddi

Collection

A storage repo for VideoRoPE. • 5 items • Updated 5 days ago • 2

updated a collection about 2 months ago

VideoRoPE: What Makes for Good Video Rotary Position Embeddi

Collection

A storage repo for VideoRoPE. • 5 items • Updated 5 days ago • 2