Picture

Zeming Wei @weizeming25

First-year Ph.D. student @PKU1898, ex-visiting student @UCBerkeley, research intern @BytedanceTalk. I focus on developing Trustworthy AI/ML. weizeming.github.io Beijing Joined August 2017
  • Tweets
    79
  • Followers
    274
  • Following
    493
  • Likes
    623
Zeming Wei retweeted
sunjiao123sun_ Profile Picture

Jiao Sun @sunjiao123sun_

10 months ago

Mitigating racial bias from LLMs is a lot easier than removing it from humans! Can’t believe this happened at the best AI conference @NeurIPSConf We have ethical reviews for authors, but missed it for invited speakers? 😡

Zeming Wei retweeted
yifeiwang77 Profile Picture

Yifei Wang @yifeiwang77

11 months ago

Yes. AI could even lead to a decline of science since we may stop to ask why and how. We need to make AI more interpretable — not only for AI but also for humanity.

khoomeik Profile Picture

Rohan Pandey @khoomeik

12 months ago

Yes. AI could even lead to a decline of science since we may stop to ask why and how. We need to make AI more interpretable — not only for AI but also for humanity.

Zeming Wei retweeted
yifeiwang77 Profile Picture

Yifei Wang @yifeiwang77

a year ago

Our theory on LLM self-correction has been accepted to #NeurIPS2024 ! A good time to revisit it after the GPT-o1 release:)

yifeiwang77 Profile Picture

Yifei Wang @yifeiwang77

a year ago

Our theory on LLM self-correction has been accepted to #NeurIPS2024 ! A good time to revisit it after the GPT-o1 release:)

Zeming Wei retweeted
yifeiwang77 Profile Picture

Yifei Wang @yifeiwang77

a year ago

Excited to share that our LLM self-correction paper received the Spotlight Award (top 3) at ICML’24 ICL workshop! iclworkshop.github.io

yifeiwang77 Profile Picture

Yifei Wang @yifeiwang77

a year ago

Excited to share that our LLM self-correction paper received the Spotlight Award (top 3) at ICML’24 ICL workshop! iclworkshop.github.io https://t.co/czLajJiX1c

Zeming Wei retweeted
yifeiwang77 Profile Picture

Yifei Wang @yifeiwang77

2 years ago

😎So excited to see that our In-context Attack (ICA) method has been leveraged by Anthrophic to break down the most prominent LLMs -- simply by extending # in-context examples! What a lesson of scaling!😆 See how this idea originates w/ @weizeming25 arxiv.org/abs/2310.06387

AnthropicAI Profile Picture

Anthropic @AnthropicAI

2 years ago

😎So excited to see that our In-context Attack (ICA) method has been leveraged by Anthrophic to break down the most prominent LLMs -- simply by extending # in-context examples! What a lesson of scaling!😆 See how this idea originates w/ @weizeming25 arxiv.org/abs/2310.06387

weizeming25 Profile Picture

Zeming Wei @weizeming25

2 years ago

Glad to share that I just reached 100 citations according to Google Scholar. Thanks all coauthors! scholar.google.com/citations?user…

Zeming Wei retweeted
llm_sec Profile Picture

LLM Security @llm_sec

2 years ago

Jatmo: Prompt Injection Defense by Task-Specific Finetuning "It harnesses a teacher instruction-tuned model to generate a task-specific dataset, which is then used to fine-tune a base model (i.e., a non-instruction-tuned model). Jatmo only needs a task prompt and a dataset of…

Trends for United States

GiveRep V1
Pete Hegseth
60,6 B posts
Quantico
26,8 B posts
Cardi
254 B posts
Patton
2.906 posts
Good Tuesday
30,2 B posts
#tuesdayvibe
1.583 posts
Generals
56,4 B posts
Wikipedia
61,4 B posts
#Postseason
7.417 posts
Latto
33,5 B posts
Taco Tuesday
10,3 B posts
Grokipedia
8.527 posts
$CRWV
3.688 posts
Commander in Chief
7.091 posts
Schumer
294 B posts
#FELIXxLVSS26
166 B posts
War Department
17,6 B posts
Medicaid
55 B posts
St. Jerome
1.461 posts

You might like

probe to improve | Ph.D. @VTEngineering | Amazon Research Fellow | #AI_safety 🦺 #AI_security 🛡 | I deal with the dark side of machine learning.
Yi Zeng 曾祎
@EasonZeng623
1K Followers
CS Ph.D. Student @NYU_Courant, Visiting Researcher @metaai | Prev: @MSFTResearch, @AlibabaGroup, https://t.co/EVVU493Kwp, @sjtu1896
Xichen Pan
@xichen_pan
632 Followers
CS PhD candidate @UCLA, Student Researcher @GoogleDeepMind | Prev. Research Intern @GoogleAI @MSFTResearch @AWS | LLM post-training, synthetic data
Yihe Deng
@Yihe__Deng
3K Followers
PhD Student @MIT | Previously: @Harvard, @stanfordnlp, @TU_Muenchen and @LMU_Muenchen
Yanchen Liu
@_yanchenliu
139 Followers
machine learning researcher, assistant professor at QMUL
Ziquan
@Ziquan12
101 Followers
PhD student@UTokyo interested in Computer Vision
Julian Guerreiro
@JJAGuerreiro
89 Followers
PHD student @ Princeton
Tianhao Wang ("Jiache...
@JiachenWang97
327 Followers
Phd student @TAMU working on stochastic optimization for large-scale AI; Alumni of @RiceUniversity; @cuhksz. Open for 26 summer intern; Opinions are my own.
Yufeng Yang
@yufengyang1999
289 Followers