Gerasimos Lampouras
@glampouras_NLP
Followers
178
Following
69
Media
17
Statuses
71
Call me Makis :) Team Leader of the London NLP Team at Huawei Noah's Ark Lab. Geek extra-ordinaire. I can be found in the bluer skies as well.
London, England
Joined February 2021
RT @milangritta: 1) Delighted to introduce our latest work🥳 (under review) 🙃 🔗🔗. We propose **DReSD: Dense Retrieva….
0
5
0
"Code-Optimise: Self-Generated Preference Data for Correctness and Efficiency" with Leonidas Gee, @milangritta, Ignacio Iacobacci NAACL 2025 (Findings) [Paper]
0
0
2
"Mixture of Attentions for Speculative Decoding" with @matthieu_zimmer, @milangritta, @hbouammar, Jun Wang .ICLR 2025 .[Paper] [Code]
1
0
3
"Human-like Episodic Memory for Infinite Context LLMs" with @zfountas, Martin Benfeghoul, Adnan Oomerjee, @fenchri, @hbouammar, Jun Wang .ICLR 2025 .[Paper] [Code]
1
0
2
A strong start of the year with some great paper acceptances, congratulations to all my collaborators! For our less fortunate submissions: improve, rewrite, and let's try again :) #ICLR2025 #NAACL2025 . Specifics below :D.
2
0
11
Also Internship Positions for the London NLP Team are open year-round. Apply below:.
1
3
11
Our London NLP team is exploring some exciting and ambitious research directions on LLM efficiency, inference and reasoning. Join us and help us realize them! Take a look at our Research Engineer listing for more details :).
1
4
9
RT @hbouammar: I am excited to present Agent K as the first end-to-end agent (i.e., autonomous from Kaggle URL to submissions that win comp….
0
43
0
Research Scientist (permanent) positions just opened in our NLP team in London - Huawei Noah's Ark Lab! Looking for experienced researchers to help us tackle some interesting (and persistent) questions :) . Take a look and apply if interested:.
0
8
16
NAACL was a while ago, but we finally have the code and data publicly available for this!! Check it out!.
Delighted to present our #naacl2024 paper, #HumanRankEval: Automatic Evaluation of #LMs as Conversational Assistants with @glampouras_NLP and @iiacobacNLP providing fast, reliable and private evaluation of instruction-tuned #LLMs. A truly new eval paradigm, no #gpt4-as-a-judge :)
0
0
10
Some insights from our latest pre-print!!.
🚀 Excited to share our new pre-print: "Human-like Episodic Memory for Infinite Context LLMs"! We introduce EM-LLM, a novel approach integrating cognitive science insights into LLMs for vastly extended context processing: What we did:.· 📊 We treat LLMs'
0
0
8
RT @s_parisot: Excited to present MuLAn at #CVPR2024! Our dataset addresses compositional text2image generation with multi-layer, instance-….
0
1
0
Full-time and part-time internship positions are also open year-round, and we are flexible on starting dates and duration (within reason of' course :).
0
0
2
Looking to grow our NLP team in London - Huawei Noah's Ark Lab! We have positions for Research Scientists (permanents) and Engineers (contractors), where they will conduct academic and applied research in NLP and ML. Details below:.
1
5
10
Some career news :) And btw, I have always wanted to do this kind of update post, hehe.
1
0
16
Second keynote will be given by Dimitra Gkatzia (@gkatzia; Edinburgh Napier University) on "Dealing with Data & Evaluation Challenges in Low-Resource NLG and Dialogue". Location: Marie Louise 2 (7th floor of Radisson hotel).Program:
0
1
6
Join us this Thursday at the 1st #SCICHAT workshop at #EACL2024! First keynote will be given by Ondřej Dušek (@tuetschek; Charles University, Czech Republic) on "Looking for LLMs’ Limits in Dialogue & Data-to-Text". Location: Marie Louise 2 (7th floor of Radisson hotel)
2
4
13
RT @fenchri: If you are in Malta 🇲🇹 (hi!👋), come join me today at the Generation session (Marie Louise 2 - Radisson Blu Hotel) 14:00 - 15:….
0
1
0