徐伯阳
biangbiang888
·
AI & ML interests
offline rl, interpretability, jailbreaks, alignment, sycophancy
Recent Activity
upvoted a paper 6 minutes ago
Speculative Forcing for Efficient Autoregressive Video Generation liked a model 1 day ago
jackhhao/jailbreak-classifier liked a model 1 day ago
Heoni/llama-3-KoEn-8b_sft_ep2_merged_red_teaming_20240614Organizations
None yet