Clément Dumas

Butanium's activity

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

upvoted a collection 3 months ago

RM Sycophancy (LLaMa)

Collection

https://alignment.anthropic.com/2025/auditing-mo-replication/ • 9 items • Updated Feb 15 • 2

upvoted a paper 4 months ago

Open Character Training: Shaping the Persona of AI Assistants through Constitutional AI

Paper • 2511.01689 • Published Nov 3, 2025 • 4

upvoted a collection 6 months ago

Open Character Training

Collection

https://arxiv.org/abs/2511.01689 • 8 items • Updated Nov 4, 2025 • 6

upvoted 2 collections 9 months ago

Tiny dummy models

Collection

Randomly initialized tiny models for debugging/testing purpose • 162 items • Updated 27 days ago • 6

Faithful Dataset

Collection

8 items • Updated Jul 2, 2025 • 1

upvoted a collection 10 months ago

gemma-2-9b-it-taboo

Collection

Data and Taboo models trained for arxiv.org/abs/2505.14352 • 41 items • Updated Sep 30, 2025 • 2

upvoted 2 papers over 1 year ago

Unpacking SDXL Turbo: Interpreting Text-to-Image Models with Sparse Autoencoders

Paper • 2410.22366 • Published Oct 28, 2024 • 84

Self-Recognition in Language Models

Paper • 2407.06946 • Published Jul 9, 2024 • 25