Hao Wang

conan1024hao's activity

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

upvoted a paper about 15 hours ago

Sparse Autoencoders as Plug-and-Play Firewalls for Adversarial Attack Detection in VLMs

Paper • 2605.07447 • Published 5 days ago • 3

submitted a paper to Daily Papers 1 day ago

Sparse Autoencoders as Plug-and-Play Firewalls for Adversarial Attack Detection in VLMs

Paper • 2605.07447 • Published 5 days ago • 3

updated a model 4 months ago

mtri-admin/qwen2.5-vl-3b-sae-lm-layer0-finevisionmax-500k

Updated 3 days ago

updated 8 models 5 months ago

mtri-admin/qwen2.5-vl-3b-sae-lm-layer11-finevisionmax-500k

Updated 3 days ago

mtri-admin/qwen2.5-vl-3b-sae-lm-layer22-finevisionmax-500k

Updated 3 days ago

mtri-admin/qwen2.5-vl-3b-sae-vision-block20-finevisionmax-500k

Updated 3 days ago

mtri-admin/qwen2.5-vl-3b-sae-vision-block10-finevisionmax-500k

Updated 3 days ago

mtri-admin/qwen2.5-vl-3b-sae-vision-block0-finevisionmax-500k

Updated 3 days ago

mtri-admin/qwen2.5-vl-3b-sae-vision-block30-finevisionmax-500k

Updated 3 days ago

mtri-admin/qwen2.5-vl-3b-sae-projection-mlp2-finevisionmax-500k

Updated 3 days ago

mtri-admin/qwen2.5-vl-3b-sae-lm-layer33-finevisionmax-500k

Updated 3 days ago

liked 2 datasets 5 months ago

HuggingFaceM4/FineVisionMax

Viewer • Updated Oct 21, 2025 • 24.2M • 14k • 27

HuggingFaceM4/FineVision

Viewer • Updated Oct 21, 2025 • 24.2M • 107k • 484

liked a dataset 6 months ago

nlp-waseda/KnowRecall

Viewer • Updated May 22, 2025 • 45k • 769 • 2

authored a paper 8 months ago

VIR-Bench: Evaluating Geospatial and Temporal Understanding of MLLMs via Travel Video Itinerary Reconstruction

Paper • 2509.19002 • Published Sep 23, 2025 • 3

upvoted a paper 8 months ago

VIR-Bench: Evaluating Geospatial and Temporal Understanding of MLLMs via Travel Video Itinerary Reconstruction

Paper • 2509.19002 • Published Sep 23, 2025 • 3

commented a paper 8 months ago

VIR-Bench: Evaluating Geospatial and Temporal Understanding of MLLMs via Travel Video Itinerary Reconstruction

Paper • 2509.19002 • Published Sep 23, 2025 • 3 •

2

liked a Space 8 months ago

Running

224

FineVision: Open Data is All You Need

📝

224

A new open-source dataset for training VLMs

updated a dataset 9 months ago

Amasia-MLLM/AmasiaIns-1M

Preview • Updated Aug 5, 2025 • 214

New activity in nlp-waseda/VisRecall 11 months ago

[bot] Conversion to Parquet

#1 opened 12 months ago by

parquet-converter