Peng Shangpin

psp-dada's activity

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

upvoted a paper 26 days ago

Beyond Data Scaling: Representation-Centric Continued Pre-training for Vision-Language-Action Models

Paper • 2608.27550 • Published about 1 month ago • 84

authored a paper about 1 month ago

Beyond Correctness: Benchmarking and Aligning Response Behaviors in Hybrid-Thinking MLLMs

Paper • 2608.12781 • Published Aug 17 • 35

upvoted a paper about 1 month ago

Beyond Correctness: Benchmarking and Aligning Response Behaviors in Hybrid-Thinking MLLMs

Paper • 2608.12781 • Published Aug 17 • 35

updated a dataset about 1 month ago

psp-dada/TableVerse-5K

Viewer • Updated Jun 29 • 4.84k • 572

New activity in psp-dada/ChartArena about 1 month ago

[bot] Conversion to Parquet

#1 opened 4 months ago by

parquet-converter

New activity in psp-dada/TableVerse-5K about 1 month ago

[bot] Conversion to Parquet

#1 opened 3 months ago by

parquet-converter

updated a model 2 months ago

tencent/HunyuanOCR

Image-Text-to-Text • 1B • Updated 29 days ago • 703k • 825

New activity in tencent/HunyuanOCR 2 months ago

VLLM when have more then 3 concurrent connection to do OCR it will fail

1

#20 opened 10 months ago by

CHONGYOEYAT

run with api is too slow

1

#13 opened 10 months ago by

medisean

there was an idea

1

#23 opened 10 months ago by

Dro33

哥们，这效果也太差了

🔥 2

11

#34 opened 3 months ago by

AlexLee111

authored 2 papers 2 months ago

HyMobileAgent: Data-Environment Co-Scaling for Efficient GUI Agents

Paper • 2607.14548 • Published Jul 16

Training Open Models for Agentic Phone Use

Paper • 2606.23049 • Published Jun 22 • 18

liked a model 2 months ago

tencent/HunyuanOCR

Image-Text-to-Text • 1B • Updated 29 days ago • 703k • 825

upvoted a paper 2 months ago

HunyuanOCR-1.5: Making Lightweight OCR VLMs Faster and Better

Paper • 2607.04884 • Published Jul 6 • 10

authored 3 papers 3 months ago

PhoneHarness: Harnessing Phone-Use Agents through Mixed GUI, CLI, and Tool Actions

Paper • 2606.14832 • Published Jun 12 • 12

StrucTab: A Structured Optimization Framework for Table Parsing

Paper • 2606.29905 • Published Jun 29

HunyuanOCR-1.5: Making Lightweight OCR VLMs Faster and Better

Paper • 2607.04884 • Published Jul 6 • 10

updated 2 models 3 months ago

psp-dada/Qwen2.5-VL-7B-Instruct-SENTINEL

Image-Text-to-Text • Updated Jul 2 • 1

psp-dada/Qwen2-VL-7B-Instruct-SENTINEL

Image-Text-to-Text • Updated Jul 2 • 1