Zhengyu Zhao (赵正宇) (@jeremyzhaozy) 's Twitter Profile
Zhengyu Zhao (赵正宇)

@jeremyzhaozy

Faculty member@xjtu1896 ⬅️ Postdoc @CISPA ⬅️ PhD @Radboud_Uni. Machine Learning Security

ID: 813622801651245056

linkhttp://zhengyuzhao.github.io calendar_today27-12-2016 05:49:27

165 Tweet

248 Followers

295 Following

Jia-Bin Huang (@jbhuang0604) 's Twitter Profile Photo

How to cope with paper rejection? Rejection SUCKS! It feels awful that months of hard work did not pay off. 😭 How do we hold a positive outlook when dealing with rejection? A thread of lessons (learned from many rejections) 🧵

Science girl (@gunsnrosesgirl3) 's Twitter Profile Photo

"Success isn't linear" by Yoann Bourgeois Success is not a straight line upwards, it’s a journey with many falls, and the strength to get up, no matter how hard the fall.

Gautam Kamath (@thegautamkamath) 's Twitter Profile Photo

Some say you should be generous with citations, because they cost you nothing. This is not true. You actually *profit* from citing prior work. I learn about a lot of papers via Google Scholar when I get cited. Besides being good scholarship, citing helps discoverability. 1/2

Julian Togelius (@togelius) 's Twitter Profile Photo

Not long ago, breakthroughs in AI research often came from lone academics or small teams using desktop hardware. These days, not so much. Are you anxious about how to stay competitive in AI as an academic? Georgios N. Yannakakis and I wrote this piece for you: arxiv.org/abs/2304.06035

Not long ago, breakthroughs in AI research often came from lone academics or small teams using desktop hardware. These days, not so much. Are you anxious about how to stay competitive in AI as an academic?
<a href="/yannakakis/">Georgios N. Yannakakis</a> and I wrote this piece for you:
arxiv.org/abs/2304.06035
Wei Xue (@wxue4) 's Twitter Profile Photo

After graduating from CLS, I am very honoured to be awarded the NWO Nieuws Rubicon fellowship to support my two-year postdoc on mutual intelligibility between German, English and Dutch LST @ Saarland University together with Prof. Bernd Möbius! nwo.nl/en/researchpro…

Andrew Akbashev (@andrew_akbashev) 's Twitter Profile Photo

Your PhD is about the evolution of your mindset. It proceeds through personal research experience, mentorship and development of key skills. This is why PhD in STEM: - is NOT about a thesis (very few people will read it) - is NOT about finish your advisor’s project - is NOT

Your PhD is about the evolution of your mindset.

It proceeds through personal research experience, mentorship and development of key skills.

This is why PhD in STEM:

- is NOT about a thesis (very few people will read it)
- is NOT about finish your advisor’s project
- is NOT
Dimitris Papailiopoulos (@dimitrispapail) 's Twitter Profile Photo

Carlini got fed up breaking every adversarial defense that gets published (rightfully so), and is now using GPT4 to automate it. This is a legit statement paper, with transparency on methods, that should be read as a criticism of the related literature arxiv.org/abs/2307.15008

Carlini got fed up breaking every adversarial defense that gets published (rightfully so), and is now using GPT4 to automate it. 

This is a legit statement paper, with transparency on methods, that should be read as a criticism of the related literature

arxiv.org/abs/2307.15008
M. Larson (@ngrams) 's Twitter Profile Photo

Are you interested in speech technology and (adversarial) machine learning? Apply to do your PhD in the area of speech processing for data protection Radboud University in beautiful Nijmegen, Netherlands: ru.nl/en/working-at/…

Tianshuo Cong (@tianshuocong) 's Twitter Profile Photo

We propose a quite simple-but-effective approach, FigStep, to jailbreak large vision-language models. 📣 Just a screenshot and a benign textual prompt can jailbreak LLaVA, MiniGPT-4, and even GPT-4V! ⚠️ Check our paper: arxiv.org/abs/2311.05608

We propose a quite simple-but-effective approach, FigStep, to jailbreak large vision-language models. 📣

Just a screenshot and a benign textual prompt can jailbreak LLaVA, MiniGPT-4, and even GPT-4V! ⚠️

Check our paper: arxiv.org/abs/2311.05608
Yug3n9 (@yugengliu) 's Twitter Profile Photo

🚀Just updated: We present our longitudinal robustness tests on LLaMA (v1, v2, v2 Chat, v3, and v3 Instruct), GPT-3.5 (v0613, v1106, and v0125), and GPT-4 (v0613, v1106, v0125, and v0409) across three critical categories: misclassification, jailbreak, and hallucination!

Krikamol (Hiring Postdoc) (@krikamol) 's Twitter Profile Photo

🚀 An incredible postdoc fellowship with Michael Backes and his team @CISPA! If you're passionate about information security, privacy, or trustworthy machine learning, this is your dream opportunity! 🌟 🗓️ Apply by May 30th, 2024! michaelbackes.eu/careerCISPA.ht… RT 🙏🙏🙏🙏

Arnaud Bertrand (@rnaudbertrand) 's Twitter Profile Photo

The Economist: "China has become a scientific superpower" Rare for me - maybe even unprecedented - to praise the Economist but this might be the seminal article on the current status of China's scientific might. Let's take a look 🧵 economist.com/science-and-te…

Rylan Schaeffer (@rylanschaeffer) 's Twitter Profile Photo

When do universal image jailbreaks transfer between Vision-Language Models (VLMs)? Our goal was to find GCG-like universal image jailbreaks to transfer against black-box API-based VLMs e.g. Claude 3, GPT4-V, Gemini We thought this would be easy - but we were wrong! 1/N

When do universal image jailbreaks transfer between Vision-Language Models (VLMs)?

Our goal was to find GCG-like universal image jailbreaks to transfer against black-box API-based VLMs
e.g. Claude 3, GPT4-V, Gemini

We thought this would be easy - but we were wrong!

1/N
Andrew Ng (@andrewyng) 's Twitter Profile Photo

The buzz over DeepSeek this week crystallized, for many people, a few important trends that have been happening in plain sight: (i) China is catching up to the U.S. in generative AI, with implications for the AI supply chain. (ii) Open weight models are commoditizing the