Justus-Jonas Erker 🇪🇺 @ EACL 2026 🇲🇦

77 posts

Justus-Jonas Erker 🇪🇺 @ EACL 2026 🇲🇦 banner
Justus-Jonas Erker 🇪🇺 @ EACL 2026 🇲🇦

Justus-Jonas Erker 🇪🇺 @ EACL 2026 🇲🇦

@J_st_s

PhD Candidate @UKPLab | interested in representation learning, RAG & LLM Agents | MSc. AI from @MaastrichtU | prev. @DFKI #NLProc Supervisor: @Nils_Reimers

Maastricht Katılım Haziran 2016
363 Takip Edilen108 Takipçiler
Justus-Jonas Erker 🇪🇺 @ EACL 2026 🇲🇦 retweetledi
UKP Lab
UKP Lab@UKPLab·
We are delighted to share that @IGurevych , the Director of the @UKPLab , has been recognized as one of the 𝗧𝗼𝗽 𝟭𝟬𝟬 𝗺𝗼𝘀𝘁 𝗶𝗻𝗳𝗹𝘂𝗲𝗻𝘁𝗶𝗮𝗹 𝘄𝗼𝗺𝗲𝗻 𝗶𝗻 𝘁𝗵𝗲 𝗚𝗲𝗿𝗺𝗮𝗻 𝗲𝗰𝗼𝗻𝗼𝗺𝘆 by @manager_magazin and @BCG ! 🎉 (1/🧵)
manager magazin@manager_magazin

Im Krisenjahr 2024 sind noch mehr Frauen in Spitzenpositionen der deutschen Wirtschaft vorgerückt. Die wichtigsten Topmanagerinnen, Unternehmerinnen, Aufsichtsrätinnen und Wegbereiterinnen für den Wandel vereint diese Liste. #ref=rss" target="_blank" rel="nofollow noopener">manager-magazin.de/unternehmen/to…

English
2
3
18
3K
Justus-Jonas Erker 🇪🇺 @ EACL 2026 🇲🇦 retweetledi
The Royal Society
The Royal Society@royalsociety·
The Milner Award and Lecture 2025 is awarded to Professor Iryna Gurevych for her major contributions to natural language processing (NLP) and artificial intelligence that combine deep understanding of human language and cognitive faculty with the latest paradigms in machine learning. #RSMedals royalsociety.org/medals-and-pri… Picture Credit: TU Darmstadt; Rüdiger Dunker
The Royal Society tweet media
English
1
9
48
5.9K
Justus-Jonas Erker 🇪🇺 @ EACL 2026 🇲🇦 retweetledi
TU Darmstadt
TU Darmstadt@TUDarmstadt·
Eine besondere Auszeichnung: Die TU-Informatikerin Iryna Gurevych @IGurevych erhält als erste Wissenschaftlerin in Deutschland und als erste Universitätsprofessorin den renommierten „Milner Award” der britischen @royalsociety . Herzlichen Glückwunsch! tu-darmstadt.de/universitaet/a…
UKP Lab@UKPLab

The @RoyalSociety has just announced that @IGurevych will receive the 2025 #MilnerAward! Our director is being honored for contributions to #NLProc & #AI, combining an understanding of human cognitive abilities with the latest Machine Learning paradigms. royalsociety.org/medals-and-pri…

Deutsch
1
2
24
1.6K
Justus-Jonas Erker 🇪🇺 @ EACL 2026 🇲🇦 retweetledi
UKP Lab
UKP Lab@UKPLab·
Meet the man who can tell you everything about Triple Encoders: Our colleague @J_st_s who presented a paper co-authored with @_florianmai (@CW_KULeuven), @Nils_Reimers (@cohere), @Gerasimoss (@MaastrichtU) and @IGurevych (@UKPLab) at #ACL2024NLP 🇹🇭! x.com/UKPLab/status/…
UKP Lab tweet media
UKP Lab@UKPLab

Modular Sentence Representations Are All You Need! Idea: encode distances between pairwise utterances and keep the context! Come with us on a journey of weightless sequential distributed composition! 🧵 (1/8) #ACL2024NLP Poster: Tue 10:30 📰 arxiv.org/abs/2402.12332

English
1
3
27
2K
Justus-Jonas Erker 🇪🇺 @ EACL 2026 🇲🇦 retweetledi
Jerry Spanakis 🟥 🦋 gerasimoss.bsky.social
Jerry Spanakis 🟥 🦋 gerasimoss.bsky.social@gerasimoss·
Happening now till 1200 at poster 15! @J_st_s is eagerly waiting #acl2024nlp
Jerry Spanakis 🟥 🦋 gerasimoss.bsky.social tweet media
Jerry Spanakis 🟥 🦋 gerasimoss.bsky.social@gerasimoss

#acl2024nlp main: @J_st_s master thesis work @UM_DACS+@UKPLab: Triple-encoders improve contextualization & efficiency without re-encoding, achieving better zero-shot generalization & performance compared to bi-encoders🤖💡 📄: arxiv.org/abs/2402.12332 x.com/UKPLab/status/… >>

English
0
2
19
1.3K
Justus-Jonas Erker 🇪🇺 @ EACL 2026 🇲🇦 retweetledi
Jerry Spanakis 🟥 🦋 gerasimoss.bsky.social
Jerry Spanakis 🟥 🦋 gerasimoss.bsky.social@gerasimoss·
#acl2024nlp main: @J_st_s master thesis work @UM_DACS+@UKPLab: Triple-encoders improve contextualization & efficiency without re-encoding, achieving better zero-shot generalization & performance compared to bi-encoders🤖💡 📄: arxiv.org/abs/2402.12332 x.com/UKPLab/status/… >>
UKP Lab@UKPLab

@AndreasWaldis @hslu @yufanghou @IBMResearch @IGurevych @imbugene @XiaodanZhu2048 @QueensECE @IngenuityLabs @androneil54 @gg42554 @Uni_WUE @M_Jonibek @SuJinyan6 @ArtemShelmanov @aktsvigun @OAfzal2 @AlhamFikri @nyhabash @preslav_nakov @mbzuai @TUDarmstadt @IstiCnr @NYUAbuDhabi @Furkansahinuc @ilokuznetsov @IBigoulaeva @rachneet4 @harish @BathNLP »Triple-Encoders: Representations That Fire Together, Wire Together« by @J_st_s (@UKPLab), @_florianmai (@CW_KULeuven), @Nils_Reimers (@cohere), @Gerasimoss Spanakis (@MaastrichtU) and @IGurevych (9/🧵) #ACL2024NLP 📑 arxiv.org/abs/2402.12332

English
1
1
5
1.7K
Justus-Jonas Erker 🇪🇺 @ EACL 2026 🇲🇦 retweetledi
UKP Lab
UKP Lab@UKPLab·
@AndreasWaldis @hslu @yufanghou @IBMResearch @IGurevych @imbugene @XiaodanZhu2048 @QueensECE @IngenuityLabs @androneil54 @gg42554 @Uni_WUE @M_Jonibek @SuJinyan6 @ArtemShelmanov @aktsvigun @OAfzal2 @AlhamFikri @nyhabash @preslav_nakov @mbzuai @TUDarmstadt @IstiCnr @NYUAbuDhabi @Furkansahinuc @ilokuznetsov @IBigoulaeva @rachneet4 @harish @BathNLP »Triple-Encoders: Representations That Fire Together, Wire Together« by @J_st_s (@UKPLab), @_florianmai (@CW_KULeuven), @Nils_Reimers (@cohere), @Gerasimoss Spanakis (@MaastrichtU) and @IGurevych (9/🧵) #ACL2024NLP 📑 arxiv.org/abs/2402.12332
UKP Lab tweet media
English
1
2
7
737
Justus-Jonas Erker 🇪🇺 @ EACL 2026 🇲🇦 retweetledi
UKP Lab
UKP Lab@UKPLab·
We are happy to announce that 11 papers authored or co-authored by UKP members have been accepted for publication at this year's @aclmeeting in Bangkok 🇹🇭. Congratulations to everyone involved! 💐 #ACL2024NLP 📑 informatik.tu-darmstadt.de/ukp/ukp_home/u… The accepted papers are (1/🧵):
UKP Lab tweet media
English
1
6
32
3.5K
Justus-Jonas Erker 🇪🇺 @ EACL 2026 🇲🇦 retweetledi
UKP Lab
UKP Lab@UKPLab·
🚨 Sentence Transformers v2.3.0 has just been released! Sentence Transformers is a framework developed at @UKPLab that allows an easy fine-tuning of custom embeddings models, to achieve maximal performance on your specific task. Release notes: github.com/UKPLab/sentenc…
English
1
7
17
1.4K
Justus-Jonas Erker 🇪🇺 @ EACL 2026 🇲🇦 retweetledi
Yann LeCun
Yann LeCun@ylecun·
Auto-Regressive LLMs have a role to play: turning abstract ideas into token sequences (words, actions, code...). But abstract ideas should be elaborated through planning/reasoning in representation space. AR-LLMs go directly from prompt to answer, skipping the step of reasoning in representation space altogether.
Aravind Srinivas@AravSrinivas

i'm skeptical of @ylecun's JEPA models fully deprecating autoregressive LLMs. but he's just been right time and again; with deep neural nets first, parallel sequence models (instead of recurrent), the cake and unsupervised learning (over RL). so betting against him is a bad idea.

English
54
104
912
393.1K
Justus-Jonas Erker 🇪🇺 @ EACL 2026 🇲🇦 retweetledi
UKP Lab
UKP Lab@UKPLab·
We are glad to welcome Justus-Jonas Erker (@j_st_s) at @UKPLab, who worked before at the @DFKI & @MaastrichtU 👋 In his PhD, Justus researches representation learning for long-dependency context modeling in dialog systems. You can find him here: erker.ai #NLProc
UKP Lab tweet media
English
0
1
13
910
Justus-Jonas Erker 🇪🇺 @ EACL 2026 🇲🇦 retweetledi
Sam Altman
Sam Altman@sama·
intelligence is an emergent property of physics
English
915
783
7.6K
1.4M
Justus-Jonas Erker 🇪🇺 @ EACL 2026 🇲🇦 retweetledi
Jerry Spanakis 🟥 🦋 gerasimoss.bsky.social
Jerry Spanakis 🟥 🦋 gerasimoss.bsky.social@gerasimoss·
Hey #ACL2023NLP peeps, I will be in Toronto 🇨🇦 open to chat & also presenting 1️⃣ Vendorlink (f/@vageeshsaxena) ⏰12/Jul 11-1230 twitter.com/gerasimoss/sta… 2️⃣ Imagination is all you need! (f/@J_st_s): ⏰10/Jul 19-21, 11/Jul 11-1230, 14/Jul 1520-17 (CODI) twitter.com/gerasimoss/sta…
Jerry Spanakis 🟥 🦋 gerasimoss.bsky.social@gerasimoss

The second paper is the work of @J_st_s (w/ Stefan Schaffer) on Curved Contrastive Learning: We "imagine" the likelihood of future patterns in multi-turn dialogues, specifically by ordering future goal utterances that are multiple turns away, given a dialogue context >> 4/5

English
0
1
11
819

Keşfet

@IGurevych @UKPLab @manager_magazin @BCG @royalsociety @CW_KULeuven @Nils_Reimers @cohere