Uncensored Is Not Unbiased: Abliteration Removes Refusals but Not Script-Dependent Bias About Taiwan Paper • 2610.29342 • Published 8 days ago • 1
Combining Long-Term Memory and LLMs Comes at a High Cost: From Prompt Injection to Persistent Compromise Paper • 2610.28810 • Published 9 days ago • 1
Harmful Responses Are Jailbreak Templates: Transferring Autoregressive Jailbreaks to Diffusion Language Models Paper • 2610.31331 • Published 6 days ago • 1
Favorite Uncensored Drivers Collection These models have no refusals and require no jailbreaks. • 69 items • Updated about 7 hours ago • 26