Jie Huang

JJJYmmm's activity

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

upvoted a paper 15 days ago

Revisiting Multimodal Positional Encoding in Vision-Language Models

Paper • 2510.23095 • Published 22 days ago • 20

authored 2 papers 18 days ago

Revisiting Multimodal Positional Encoding in Vision-Language Models

Paper • 2510.23095 • Published 22 days ago • 20

RefHCM: A Unified Model for Referring Perceptions in Human-Centric Scenarios

Paper • 2412.14643 • Published Dec 19, 2024

New activity in Qwen/Qwen3-VL-32B-Instruct 22 days ago

How about running by llama.cpp

2

#1 opened 27 days ago by

rosspanda0

'Qwen3VLConfig' object has no attribute 'vocab_size'

👀 1

1

#3 opened 27 days ago by

vladciocan88

New activity in Qwen/Qwen3-VL-235B-A22B-Instruct about 2 months ago

No output_router_logits / load_balancing_loss_func for Qwen3VLMoE?

3

#9 opened about 2 months ago by

plcedoz38

updated a dataset 6 months ago

HumanPCR/HumanPCR

Viewer • Updated May 23 • 442 • 184

published a dataset 6 months ago

HumanPCR/HumanPCR

Viewer • Updated May 23 • 442 • 184

updated 2 datasets 6 months ago

HumanPCR/HumanPCR

Viewer • Updated May 23 • 442 • 184

HumanPCR/HumanPCR

Viewer • Updated May 23 • 442 • 184