Jun Wang

818 posts

Jun Wang banner
Jun Wang

Jun Wang

@seawan

Professor of Computer Science, UCL

iPhone: 51.514099,-0.153842 เข้าร่วม Kasım 2007
92 กำลังติดตาม892 ผู้ติดตาม
elvis
elvis@omarsar0·
Fine-tuning LLM Agents without Fine-tuning LLMs Catchy title and very cool memory technique to improve deep research agents. Great for continuous, real-time learning without gradient updates. Here are my notes:
elvis tweet media
English
52
211
1.2K
139.5K
Jun Wang
Jun Wang@seawan·
@omarsar0 Thanks for sharing our work! We felt an external memory and case based reasoning could revolutionise the way a LLM agent learns with minimum efforts. It is time to get rid of llm post training and gradient descent.
English
0
0
0
206
Jun Wang รีทวีตแล้ว
Grace Hui Yang
Grace Hui Yang@GraceHuiYang·
I guess we will have a lot to talk about #ChatGPT in our upcoming #wsdm2023 tutorial “proactive conversational agents.” I don’t have any concern/complaint/resistance for this intelligent new being. I look forward to my own evolution via interactions w/ this true AI.
Grace Hui Yang@GraceHuiYang

Home, Sweet Home. Will be presenting a WSDM'23 Tutorial on "proactive conversational agents" w/ @lizi_liao and @chirag_shah in Singapore, Sweet Singapore.

English
0
1
13
2.3K
Jun Wang รีทวีตแล้ว
@arjen@idf.social 🕊️🇺🇦
So proud! Our new hire @HarrieOos wins SIGIR best paper with a single-authored contribution, and former student @seawan has an honerable mention for the Test-of-time award for his paper on Portfolio theory for IR!! #SIGIR2021
English
3
8
63
0
Jun Wang รีทวีตแล้ว
Google DeepMind
Google DeepMind@GoogleDeepMind·
We provide a new theoretical analysis to understand how they happen, and what we can do about them: arxiv.org/abs/1902.10730
Google DeepMind tweet media
English
8
106
471
0
Jun Wang
Jun Wang@seawan·
Our recent work on AI playing Contract Bridge card game.
English
1
3
7
0