Bruna Bazaluk
@brunabazaluk.bsky.social
Computer Scientist
Master student applying for a Phd position
causality, probabilistic AI
https://www.ime.usp.br/~bazaluk/
Master student applying for a Phd position
causality, probabilistic AI
https://www.ime.usp.br/~bazaluk/
when it's your first big conference submission, your paper has 3 pages more than it should and you have 1 day to make it fit
September 30, 2025 at 8:20 PM
when it's your first big conference submission, your paper has 3 pages more than it should and you have 1 day to make it fit
Reposted by Bruna Bazaluk
The 41st Conference on #Uncertainty in #AI will be held in Rio de Janeiro 🇧🇷, July 21-25!
The CfP is out 👉 www.auai.org/uai2025/call...
🚨 Feb 10: Paper submission
🗣️ Apr 3-10: rebuttal period
🎉/💀 May 6: Author notification
#UAI2025 #ML #stats #learning #reasoning #uncertainty
The CfP is out 👉 www.auai.org/uai2025/call...
🚨 Feb 10: Paper submission
🗣️ Apr 3-10: rebuttal period
🎉/💀 May 6: Author notification
#UAI2025 #ML #stats #learning #reasoning #uncertainty
December 3, 2024 at 5:07 PM
The 41st Conference on #Uncertainty in #AI will be held in Rio de Janeiro 🇧🇷, July 21-25!
The CfP is out 👉 www.auai.org/uai2025/call...
🚨 Feb 10: Paper submission
🗣️ Apr 3-10: rebuttal period
🎉/💀 May 6: Author notification
#UAI2025 #ML #stats #learning #reasoning #uncertainty
The CfP is out 👉 www.auai.org/uai2025/call...
🚨 Feb 10: Paper submission
🗣️ Apr 3-10: rebuttal period
🎉/💀 May 6: Author notification
#UAI2025 #ML #stats #learning #reasoning #uncertainty
Reposted by Bruna Bazaluk
What happens if we tokenize cat as [ca, t] rather than [cat]?
LLMs are trained on just one tokenization per word, but they still understand alternative tokenizations. We show that this can be exploited to bypass safety filters without changing the text itself.
#AI #LLMs #tokenization #alignment
LLMs are trained on just one tokenization per word, but they still understand alternative tokenizations. We show that this can be exploited to bypass safety filters without changing the text itself.
#AI #LLMs #tokenization #alignment
March 11, 2025 at 11:13 PM
What happens if we tokenize cat as [ca, t] rather than [cat]?
LLMs are trained on just one tokenization per word, but they still understand alternative tokenizations. We show that this can be exploited to bypass safety filters without changing the text itself.
#AI #LLMs #tokenization #alignment
LLMs are trained on just one tokenization per word, but they still understand alternative tokenizations. We show that this can be exploited to bypass safety filters without changing the text itself.
#AI #LLMs #tokenization #alignment