Punya Syon Pandey

10 posts

Punya Syon Pandey banner
Punya Syon Pandey

Punya Syon Pandey

@psyonp

Katılım Şubat 2025
23 Takip Edilen137 Takipçiler
Zhijing Jin
Zhijing Jin@ZhijingJin·
Punya @psyonp is an impressive UofT undergrad student. He reached out to our @JinesisLab in the 1st year of his undergrad; now as a 2nd-year undergrad, his contributed to 8 papers in our lab. 3 first-author papers at #EACL2026 #IASEAI2026 and #ICLR2026 🎉[Stellar Student Sharing]
Zhijing Jin tweet media
English
7
11
288
23.3K
Punya Syon Pandey
Punya Syon Pandey@psyonp·
I'm deeply grateful to my advisors @ZhijingJin and @radamihalcea, as well as my collaborators Hai Son Le and Devansh Bhardwaj for their support throughout this project at the Jinesis AI Lab at the University of Toronto. Stay tuned for our codebase!
English
0
0
3
210
Punya Syon Pandey
Punya Syon Pandey@psyonp·
Excited to share that our paper "SocialHarmBench: Revealing LLM Vulnerabilities to Socially Harmful Requests" has been accepted at ICLR 2026 🎉. In this work, we introduce the first adversarial evaluation benchmark specifically designed to probe sociopolitical risks in LLMs.
English
2
3
12
3.9K
Zhijing Jin
Zhijing Jin@ZhijingJin·
Humbled to take on my 1st ACL Officer position, as Co-Chair of #ACL Ethics Committee. I look forward to promoting Responsible AI in #NLProc community & ensuring ethical research. In my term, I also hope to bridge the narrative w/ AI Safety and various social considerations of AI.
Zhijing Jin tweet media
English
5
7
77
6.4K
Punya Syon Pandey
Punya Syon Pandey@psyonp·
A quick look into DeepSeek’s safety guard: We find DeepSeek’s Llama Distill is >2x⚠️ as vulnerable to jailbreaking attacks as the original Llama. Seems to be a large safety risk. Stay tuned for our upcoming work @psyonp @SimkoSamuel @ZhijingJin
Punya Syon Pandey tweet media
English
0
2
5
2.9K