Alignment Security and Safety Lab

ASSELab's activity

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

JonasDornbusch 

updated 3 models 16 days ago

ASSELab/DAT-Llama-3-8B-Instruct

Text Generation • 8B • Updated 16 days ago • 129 • 2

ASSELab/DAT-Qwen2.5-14B-Instruct

Text Generation • 15B • Updated 16 days ago • 26

ASSELab/Diffusion-Llama-3-8B-Instruct

Text Generation • 8B • Updated 16 days ago • 38

JonasDornbusch 

updated a collection 16 days ago

DAT

Collection

Distributional Adversarial Training utilizes cont. adv. training on diffusion-based adv. examples to close a gap in population-robust risk estimation. • 4 items • Updated 16 days ago • 1

JonasDornbusch 

in ASSELab/DAT-Qwen2.5-14B-Instruct 18 days ago

Upload merged model

#1 opened 18 days ago by

JonasDornbusch

JonasDornbusch 

updated a collection 18 days ago

DAT

Collection

Distributional Adversarial Training utilizes cont. adv. training on diffusion-based adv. examples to close a gap in population-robust risk estimation. • 4 items • Updated 16 days ago • 1

JonasDornbusch 

published a model 18 days ago

ASSELab/DAT-Qwen2.5-14B-Instruct

Text Generation • 15B • Updated 16 days ago • 26

JonasDornbusch 

in ASSELab/Diffusion-Llama-3-8B-Instruct 18 days ago

Upload merged model

#1 opened 18 days ago by

JonasDornbusch

JonasDornbusch 

published a model 18 days ago

ASSELab/Diffusion-Llama-3-8B-Instruct

Text Generation • 8B • Updated 16 days ago • 38

JonasDornbusch 

in ASSELab/DAT-Llama-3-8B-Instruct 18 days ago

DAT Llama

#2 opened 18 days ago by

JonasDornbusch

Upload merged model

#1 opened 18 days ago by

JonasDornbusch

JonasDornbusch 

published a model 18 days ago

ASSELab/DAT-Llama-3-8B-Instruct

Text Generation • 8B • Updated 16 days ago • 129 • 2