Caleb Fahlgren PRO

cfahlgren1's activity

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

updated a dataset about 5 hours ago

cfahlgren1/3d-model-samples

Viewer • Updated about 5 hours ago • 15

published a dataset about 5 hours ago

cfahlgren1/3d-model-samples

Viewer • Updated about 5 hours ago • 15

upvoted a paper about 6 hours ago

Score Centering Stabilizes Off-policy Reinforcement Learning

Paper • 2609.20807 • Published Sep 17 • 4

liked a dataset about 8 hours ago

CohereLabs/10-2026-qwen-investigation-traces

Traces • Updated about 8 hours ago • 1 • 42

New activity in CohereLabs/10-2026-qwen-investigation-traces about 8 hours ago

add trace viewer support

#2 opened about 8 hours ago by

cfahlgren1

updated a dataset about 8 hours ago

cfahlgren1/10-2026-qwen-investigation-traces-pi

Traces • Updated about 8 hours ago • 1

published 2 datasets about 8 hours ago

cfahlgren1/10-2026-qwen-investigation-traces-pi

Traces • Updated about 8 hours ago • 1

cfahlgren1/10-2026-qwen-investigation-traces

Traces • Updated about 9 hours ago • 1

updated a dataset about 9 hours ago

cfahlgren1/10-2026-qwen-investigation-traces

Traces • Updated about 9 hours ago • 1

liked a Space about 11 hours ago

Running

1

OpenUSD Explorer

🧊

1

Explore OpenUSD objects on a quiet canvas.

liked a Space about 13 hours ago

Running

16

Alignment Hub

📚

16

Explore AI model misbehavior reports and incidents

liked a Space about 16 hours ago

Running on Zero

Agents

1

Detector Scope

🔬

1

Auditable AI-text detection with sparse-autoencoder features

upvoted 2 papers about 16 hours ago

Building Auditable AI Text Detectors with Sparse Autoencoders

Paper • 2610.30006 • Published 6 days ago • 10

Reading, Writing, Sharing, and Interacting with the World through Video

Paper • 2610.31668 • Published 5 days ago • 275

updated a dataset about 19 hours ago

cfahlgren1/hub-stats

Viewer • Updated about 19 hours ago • 5.94M • 19.7k • 84

liked a dataset 1 day ago

hcltech-robotics/simreadybench

RL Environment • Updated about 4 hours ago • 5.18k • 4.33k • 2

updated a Space 1 day ago

Running

Refusal Direction — Qwen3.5-4B

🧭

Where a prompt lands on Qwen3.5-4B's refusal direction

published a Space 1 day ago

Running

Refusal Direction — Qwen3.5-4B

🧭

Where a prompt lands on Qwen3.5-4B's refusal direction

updated a model 1 day ago

cfahlgren1/Qwen3.5-4B-layers0-11

Text Generation • 2B • Updated 1 day ago • 185

published a model 1 day ago

cfahlgren1/Qwen3.5-4B-layers0-11

Text Generation • 2B • Updated 1 day ago • 185