entfane/toxic_chat
Viewer
• Updated
• 1.25M • 13
Nikita Kezins
entfane
AI & ML interests
LLM post-training, adversarial training, safety, knowledge transfer
Recent Activity
upvoted a paper 1 day ago
Blockwise Advantage Estimation for Multi-Objective RL with Verifiable Rewards liked
a dataset 6 days ago
nvidia/Nemotron-Terminal-Corpus updated
a Space 6 days ago
entfane/gpt2-toxic-classifier Organizations
