Minsuk Kahng
@minsukkahng
Followers
1K
Following
3K
Media
7
Statuses
601
Research Scientist @Google PAIR in DeepMind. Prev, Prof. @OregonState. PhD @GeorgiaTech. Research on Data Visualization, Responsible AI, Human-AI Interaction
Atlanta, GA
Joined July 2009
With the Gemma 2 launch, we’ve updated our LLM Comparator tool with a Python library! This lets you more easily run the tool with your own models.
github.com
LLM Comparator is an interactive data visualization tool for evaluating and analyzing LLM responses side-by-side, developed by the PAIR team. - PAIR-code/llm-comparator
We're excited to unveil Gemma 2. 🛠️. Available in both 9B and 27B parameters, it delivers the best performance for its size - unlocking more possibilities for developers to build and deploy with AI. →
0
2
9
Google has launched a new academic research funding program! Unrestricted gifts; 6 focused areas; due July 17.
Applications will open on June 27 for the Google Academic Research Awards, a new program that supports academic research in computing and technology that makes a positive difference in the world. Learn more at →
0
0
8
This article summarizes our project towards safe and responsible development of text-to-image models. Our paper will be presented at #FAccT2024 this week.
Learn how the Adversarial Nibbler challenge provides the holistic evaluation of gen text-to-image model robustness against harmful image generation & long-tail safety issues, by using community-driven red teaming to build a diverse set of harmful prompts.
0
0
5
Many thanks to the LLM Comparator team at @GoogleAI PAIR: @iftenney, @mahimapushkarna, @lxieyang, James Wexler, @emilyrreif, Krystal Kallarackal, @minsuk_chang, @ryanmullins, @tolgab0, @LudovicPeran, Michael Terry, @iislucas.
0
1
7
Very excited to open-source LLM Comparator!.This new #visualization tool lets you analyze LLM responses side-by-side. It’s been used for evaluating LLMs @Google, and we're proud to release it as part of Google's Responsible GenAI Toolkit.
medium.com
By Minsuk Kahng, Ryan Mullins, Ludovic Peran
1
12
65
RT @fredhohman: #visxai at #ieeevis is back. always such a fun event. submit your work and show it off!.
0
5
0
So proud of you, Donny! I truly enjoyed mentoring you @OregonState. Very excited about your new journey @GT_Vis!.
Life update: very happy to be joining @GeorgiaTech @ICatGT in the Fall as a PhD student advised by @EndertAlex.
1
1
7
RT @lxieyang: Can't decide between #Maui or #BigIsland w.r.t. transpo, hotels, food, beeches, etc.? Our upcoming #CHI2024 paper presents S….
arxiv.org
Sensemaking in unfamiliar domains can be challenging, demanding considerable user effort to compare different options with respect to various criteria. Prior research and our formative study found...
0
8
0
Very cool and would be really useful! Especially love the test case generation and edit suggestions.
Excited to share a tool @a13xba and I have been building! .<| 𝗲𝗻𝗱𝗼𝗳𝘁𝗲𝘅𝘁 |> is an AI-powered prompt editor that helps you write better prompts with suggested edits, automatic rewrites, and test case generation. We'd love to get your feedback:
1
0
4
Fantastic to see this work you did at PAIR come out!.
How might we promote responsible AI among LLM app developers?. Introducing Farsight—in situ widgets that bring responsible AI to early prompt-based AI prototyping. Given a prompt, Farsight highlights relevant AI incidents & potential harms. 👉 #CHI2024
0
1
6
RT @iftenney: Super excited for the Gemma model release, and with it a new debugging tool we built on 🔥LIT - use gradient-based salience to….
ai.google.dev
0
4
0
RT @GoogleAI: Applications are open for the Research Scholar Program, an effort that aims to strengthen long-term collaboration w/ the acad….
research.google
Learn more about our faculty and student programs and events that support the research community by providing research engagement opportunities.
0
66
0
Sad to miss #ieeevis this year, but I’m very excited about our new paper from PAIR!.
New paper on visualizing linguistic diversity of data generated by LLMs. Excited to present this (remotely) at #IEEEVIS! .Collaboration with @minsukkahng and @savvas_petridis at @GoogleAI . Paper: Tool:
1
1
14
RT @emilyrreif: New paper on visualizing linguistic diversity of data generated by LLMs. Excited to present this (remotely) at #IEEEVIS! .C….
0
16
0
PAIR is hiring a research scientist!.
PAIR is looking for a Research Scientist interested in making hard ML problems (like understanding langauge) much smaller. In Paris, and working closely with fun interactive explorable visualizations too. See:
0
2
6
RT @HariSubramonyam: 1/ 📝 New paper alert! 🚀 We take a closer look at claims made in research around VIS4ML, which presents tools that use….
0
11
0
RT @GoogleAI: Today we describe the many efforts of the People + AI Research (PAIR) team within Google Research, which conducts foundationa….
0
132
0
RT @adamrpearce: Confidently Incorrect Models to Humble Ensembles by @Nithum, @balajiln and Jasper Snoek. https://t….
0
7
0