arxiv:2505.22914
Denis Tarasov
Adagrad
AI & ML interests
RL, NLP
Recent Activity
upvoted
a
paper
about 16 hours ago
Sanity Checks for Sparse Autoencoders: Do SAEs Beat Random Baselines?
upvoted
a
paper
7 months ago
T-LoRA: Single Image Diffusion Model Customization Without Overfitting
upvoted
a
paper
8 months ago
Heeding the Inner Voice: Aligning ControlNet Training via Intermediate
Features Feedback
Organizations
models
0
None public yet
datasets
0
None public yet