Associate Professor of Computer Science at Heriot-Watt University & Head of ML and Co-founder at Alana @HeriotWattUni. Researching #NLG #NLProc #NLP
Joined February 2009
- Tweets 111
- Following 397
- Followers 368
- Likes 503
1 Photos and videos
Feb 17
There is still time to submit your work on our Information Disorder workshop taking place at LREC 2026!
Feb 10
📢 Deadline extended (24 Feb 2026) – Information Disorder Workshop (InDor)
🧠 InDor aims to advance interdisciplinary NLP research on Information Disorder, with a strong focus on theory, datasets, evaluation, cultural context and real-world impact.
🔗 information-disorder-worksho…
1
2
209
1 May 2025
Looking for a cool place to work on NLP, Generative AI, Robotics, ML (among other things)? Join us as an Assistant Professor at HWU; there is still time to apply! Deadline extended to 11/5/2025. linkedin.com/jobs/view/42058…
1
118
Yannis Konstas retweeted
24 Jul 2024
So very, very proud to share our new paper “Voices in a Crowd: Searching for Clusters of Unique Perspectives” (arXiv:2407.14259), a novel framework on how to organically find clusters of unique voices (perspectives) in datasets. 🧵 for summary, co-authors @amitkparekh_ @sinantie
1
3
11
893
9 Jul 2024
Do multimodal models always follow our instructions (in a robotic manipulation environment)? Well... Check out the latest work by @amitkparekh_ @NikVits @ale_suglia !
9 Jul 2024
What if your multimodal model succeeds when given nonsensical instructions? What if it even succeeds without being told explicitly what to do? Have we finally achieved AGI?
We answer at least two of those questions w/ @NikVits @ale_suglia @sinantie (🧵for more)
9
466
21 Jun 2024
Want to find out more about egocentric video understanding? Check out AlanaVLM!
21 Jun 2024
Excited to announce that the Embodied AI team at @helloalana developed AlanaVLM, a new foundation model for egocentric video understanding. Best open-weight model which rivals GPT-4V on spatial reasoning questions in OpenEQA.
Thread below!
arxiv.org/abs/2406.13807
#AI #NLProc
8
223
Yannis Konstas retweeted
30 May 2024
Exciting news! We are now working with University Hospitals of Derby and Burton NHS Foundation Trust to help clinicians quickly access and search the latest medical guidelines. Faster, smarter medical support is coming! @NHS
5
11
1,149
Yannis Konstas retweeted
12 Mar 2024
📢WE ARE BACK!💥
It's official! The Athens Natural Language Processing Summer School @AthensNlp is taking place in 2024 in Athens Greece 🇬🇷!
📅Save the dates 19 - 25 September 2024.
Use #AthNLP2024 for updates!
9
21
1,796
12 Mar 2024
I am really excited to be giving a TEDx Youth talk on online Gender-Based Violence and AI/NLP. Thanks a lot, #TEDxYouthStGeorgesEdinburgh for hosting. Special thanks to @GerrardPoppy and @NikVits for the discussions to prepare the talk! #VoicesOfTheFuture #tedxstge.
8 Mar 2024
🌟📣 Announcing our #TEDxYouthStGeorgesEdinburgh #VoicesOfTheFuture 2024 speaker lineup! We're excited to welcome Yannis Konstas to the #TEDxYouth stage.💻Follow TEDx Youth St Georges Edinburgh on Facebook for more updates 👉👉 ow.ly/xRqC50QOrfI #IdeasWorthSpreading #TEDx
1
4
244
Yannis Konstas retweeted
4 Mar 2024
Just under 24 hours to go for the @SafeConvAI deadline! 🚨 Collocated wth @LRECCOLING
@t_dinkar
@peppeatta
@sinantie
@verena_rieser
@dirk_hovy
Full details here:
27 Feb 2024
🚨🚨🚨
4
11
1,513
31 Jan 2024
New postdoc position! Are you interested in online Gender-Based Violence identification and counterspeech generation? If so, come and work with us at @iLab_hwu @HeriotWattUni! The deadline for applications is 26 February. #NLProc enzj.fa.em3.oraclecloud.com/…
4
12
1,704
Yannis Konstas retweeted
26 Jan 2024
Our survey paper is now available on @JAIR_Editor: jair.org/index.php/jair/arti…
Many thanks to my co-authors @oliverlemon and @sinantie for supporting me in this great effort!
Looking forward to hearing your feedback, especially on the future research directions section!
10 Oct 2023
Another great news today: our survey paper "Visually Grounded Language Learning: a review of language games, datasets, tasks and models" was accepted by JAIR. This was part of my PhD thesis completed under the supervision of @oliverlemon and @sinantie!
2
6
35
5,664
Yannis Konstas retweeted
6 Jan 2024
New Paper 🎉: arxiv.org/pdf/2401.01814.pdf
Can language models relearn removed concepts?
Model editing aims to eliminate unwanted concepts through neuron pruning. LLMs demonstrate a remarkable capacity to adapt and regain conceptual representations which have been removed
🧵1/8
2
77
273
42,636
Yannis Konstas retweeted
18 Dec 2023
Welcome to iLab Wrapped!!🎉🎉
It's the end of 2023, so let's take a dive into some of the Interaction Lab's papers.
Please follow your favourite authors so you can keep up with their work beyond their time at @iLab_hwu
(apologies if the thread updates slowly - @Addlesee_AI)
1
5
18
3,957
Yannis Konstas retweeted
10 Oct 2023
[1/N] Happy to share that our paper “Multitask Multimodal Prompted Training for Interactive Embodied Task Completion” has been accepted at #EMNLP2023! 🎉 @MNikandrou @amitkparekh_ @hsbhathiya @ale_suglia
2
7
33
4,424
Yannis Konstas retweeted
3 Jun 2023
🎉 New paper to appear at ACL 2023 : arxiv.org/abs/2305.17553
Large Language Models (LLMs) are powerful tools, but they can memorize false or outdated associations. Model editing techniques promise to solve this, but do they really work?
1/
2
20
131
28,790
Yannis Konstas retweeted
26 May 2023
New paper: arxiv.org/abs/2305.15507
LLMs are good at programing tasks, and they are now being widely used to assist code generation.
But do they actually understand the semantics of programming languages, or do they rely on superficial, "shortcut" correlations?
Let's find out!
1/
32
211
1,249
686,154
3 May 2023
"The Dangers of trusting Stochastic Parrots: Faithfulness and Trust in Open-domain Conversational Question Answering" was accepted at findings of #ACL2023!
Joint work with Sabrina Chiesurin,@dmkpls,Marco Antonio Sobrevilla Cabezudo,@arash_eshghi, @g_papaioannou, @verena_rieser
1
8
32
2,349
3 May 2023
We use open-domain question answering systems as our test-bed for task based dialog generation and compare several models, with a focus on highlighting the danger of systems that appear to be trustworthy by "parroting" user input while providing an unfaithful response.
2/3
1
209
3 May 2023
The full paper will be available to the community very soon, so stay tuned!
3/3
1
174