Justus-Jonas Erker ๐Ÿ‡ช๐Ÿ‡บ @ EACL 2026 ๐Ÿ‡ฒ๐Ÿ‡ฆ (@J_st_s) header
Justus-Jonas Erker ๐Ÿ‡ช๐Ÿ‡บ @ EACL 2026 ๐Ÿ‡ฒ๐Ÿ‡ฆ (@J_st_s) profile picture

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

Maastricht
Joined June 2016
Photo by Justus-Jonas Erker ๐Ÿ‡ช๐Ÿ‡บ @ EACL 2026 ๐Ÿ‡ฒ๐Ÿ‡ฆ (@J_st_s)Photo by Justus-Jonas Erker ๐Ÿ‡ช๐Ÿ‡บ @ EACL 2026 ๐Ÿ‡ฒ๐Ÿ‡ฆ (@J_st_s)Photo by Justus-Jonas Erker ๐Ÿ‡ช๐Ÿ‡บ @ EACL 2026 ๐Ÿ‡ฒ๐Ÿ‡ฆ (@J_st_s)
Justus-Jonas Erker ๐Ÿ‡ช๐Ÿ‡บ @ EACL 2026 ๐Ÿ‡ฒ๐Ÿ‡ฆ retweeted
We are delighted to share that @IGurevych , the Director of the @UKPLab , has been recognized as one of theย ๐—ง๐—ผ๐—ฝ ๐Ÿญ๐Ÿฌ๐Ÿฌ ๐—บ๐—ผ๐˜€๐˜ ๐—ถ๐—ป๐—ณ๐—น๐˜‚๐—ฒ๐—ป๐˜๐—ถ๐—ฎ๐—น ๐˜„๐—ผ๐—บ๐—ฒ๐—ป ๐—ถ๐—ป ๐˜๐—ต๐—ฒ ๐—š๐—ฒ๐—ฟ๐—บ๐—ฎ๐—ป ๐—ฒ๐—ฐ๐—ผ๐—ป๐—ผ๐—บ๐˜†ย by @manager_magazin and @BCG !ย ๐ŸŽ‰ (1/๐Ÿงต)
2
3
2
18
3,227
Justus-Jonas Erker ๐Ÿ‡ช๐Ÿ‡บ @ EACL 2026 ๐Ÿ‡ฒ๐Ÿ‡ฆ retweeted
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-โ€ฆ Picture Credit: TU Darmstadt; Rรผdiger Dunker
1
9
1
48
5,936
Justus-Jonas Erker ๐Ÿ‡ช๐Ÿ‡บ @ EACL 2026 ๐Ÿ‡ฒ๐Ÿ‡ฆ retweeted
Eine besondere Auszeichnung: Die TU-Informatikerin Iryna Gurevych @IGurevych erhรคlt als erste Wissenschaftlerin in Deutschland und als erste Universitรคtsprofessorin den renommierten โ€žMilner Awardโ€ der britischen @royalsociety . Herzlichen Glรผckwunsch! tu-darmstadt.de/universitaetโ€ฆ
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-โ€ฆ
1
2
22
1,584
Justus-Jonas Erker ๐Ÿ‡ช๐Ÿ‡บ @ EACL 2026 ๐Ÿ‡ฒ๐Ÿ‡ฆ retweeted
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 ๐Ÿ‡น๐Ÿ‡ญ! nitter.cf/UKPLab/status/18229951โ€ฆ
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! ๐Ÿงต (1/8) #ACL2024NLP Poster: Tue 10:30 ๐Ÿ“ฐ arxiv.org/abs/2402.12332
1
3
27
1,984
Justus-Jonas Erker ๐Ÿ‡ช๐Ÿ‡บ @ EACL 2026 ๐Ÿ‡ฒ๐Ÿ‡ฆ retweeted
Happening now till 1200 at poster 15! @J_st_s is eagerly waiting #acl2024nlp
Replying to @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-encoders๐Ÿค–๐Ÿ’ก ๐Ÿ“„: arxiv.org/abs/2402.12332 nitter.cf/UKPLab/status/17950163โ€ฆ >>
2
19
1,346
Justus-Jonas Erker ๐Ÿ‡ช๐Ÿ‡บ @ EACL 2026 ๐Ÿ‡ฒ๐Ÿ‡ฆ retweeted
Consider following the authors @J_st_s (@UKPLab), @_florianmai (@CW_KULeuven), @Nils_Reimers (@cohere), @Gerasimoss Spanakis (@MaastrichtU) and @IGurevych for more information or an exchange of ideas. (8/๐Ÿงต) See you this week at #ACL2024NLP in Thailand ๐Ÿ‡น๐Ÿ‡ญ!
2
6
510
Justus-Jonas Erker ๐Ÿ‡ช๐Ÿ‡บ @ EACL 2026 ๐Ÿ‡ฒ๐Ÿ‡ฆ retweeted
Meet our fellow researchers representing @UKPLab at this year's @ACLmeeting: @IGurevych, @QianRuan_, @J_st_s, @androneil54, @trumancfy, Sheng Lu, @haishuofang, @Furkansahinuc, @KexinWang2049, @LHaausing, @AndreasWaldis, and a very special guest from @BathNLP, @Harish! #ACL2024NLP
9
1
41
3,058
Justus-Jonas Erker ๐Ÿ‡ช๐Ÿ‡บ @ EACL 2026 ๐Ÿ‡ฒ๐Ÿ‡ฆ retweeted
#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-encoders๐Ÿค–๐Ÿ’ก ๐Ÿ“„: arxiv.org/abs/2402.12332 nitter.cf/UKPLab/status/17950163โ€ฆ >>
1
1
1
5
1,667
Justus-Jonas Erker ๐Ÿ‡ช๐Ÿ‡บ @ EACL 2026 ๐Ÿ‡ฒ๐Ÿ‡ฆ retweeted
ยปTriple-Encoders: Representations That Fire Together, Wire Togetherยซ by @J_st_s (@UKPLab), @_florianmai (@CW_KULeuven), @Nils_Reimers (@cohere), @Gerasimoss Spanakis (@MaastrichtU) and @IGurevych (9/๐Ÿงต) #ACL2024NLP ๐Ÿ“‘ arxiv.org/abs/2402.12332
1
2
1
7
742
Justus-Jonas Erker ๐Ÿ‡ช๐Ÿ‡บ @ EACL 2026 ๐Ÿ‡ฒ๐Ÿ‡ฆ retweeted
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 ๐Ÿ‡น๐Ÿ‡ญ. Congratulations to everyone involved! ๐Ÿ’ #ACL2024NLP ๐Ÿ“‘ informatik.tu-darmstadt.de/uโ€ฆ The accepted papers are (1/๐Ÿงต):
1
6
32
3,520
Justus-Jonas Erker ๐Ÿ‡ช๐Ÿ‡บ @ EACL 2026 ๐Ÿ‡ฒ๐Ÿ‡ฆ retweeted
Attention #NLProc community! ๐Ÿ“ข Join the Perspective Argument Retrieval Shared Task, co-located with #argmining_2024 & #ACL2024NLP. Dive into the challenge of retrieving arguments tailored to diverse demographic profiles! ๐ŸŽจ ๐Ÿš€ blubberli.github.io/perspectโ€ฆ ๐Ÿ—ซ perspectivear-zzl7474.slack.โ€ฆ
2
11
2
18
6,425
Justus-Jonas Erker ๐Ÿ‡ช๐Ÿ‡บ @ EACL 2026 ๐Ÿ‡ฒ๐Ÿ‡ฆ retweeted
๐Ÿšจ 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/sentence-tโ€ฆ
1
7
17
1,444
Justus-Jonas Erker ๐Ÿ‡ช๐Ÿ‡บ @ EACL 2026 ๐Ÿ‡ฒ๐Ÿ‡ฆ retweeted
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.
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.
54
104
13
902
393,129
Many thanks to @_florianmai for an amazing talk at the @UKPLab on Attention alternatives.
3
16
1,053
Justus-Jonas Erker ๐Ÿ‡ช๐Ÿ‡บ @ EACL 2026 ๐Ÿ‡ฒ๐Ÿ‡ฆ retweeted
We are glad to welcome Justus-Jonas Erker (@j_st_s) at @UKPLab, who worked before at the @DFKI & @MaastrichtU ๐Ÿ‘‹ In his PhD, Justus researches representation learning for long-dependency context modeling in dialog systems. You can find him here: erker.ai/ #NLProc
1
13
912
Justus-Jonas Erker ๐Ÿ‡ช๐Ÿ‡บ @ EACL 2026 ๐Ÿ‡ฒ๐Ÿ‡ฆ retweeted
intelligence is an emergent property of physics
903
771
320
7,467
1,362,839
Justus-Jonas Erker ๐Ÿ‡ช๐Ÿ‡บ @ EACL 2026 ๐Ÿ‡ฒ๐Ÿ‡ฆ retweeted
For the die-hard-still-hungry-for-NLP @J_st_s is ready to pitch you our work on curved contrastive learning for sequence modelling (short- and long-term dialogue planning). โ€œImagination is all you needโ€ #CODI2023 #ACL2023NLP #NLProc
4
12
1,415
Justus-Jonas Erker ๐Ÿ‡ช๐Ÿ‡บ @ EACL 2026 ๐Ÿ‡ฒ๐Ÿ‡ฆ retweeted
Hey #ACL2023NLP peeps, I will be in Toronto ๐Ÿ‡จ๐Ÿ‡ฆ open to chat & also presenting 1๏ธโƒฃ Vendorlink (f/@vageeshsaxena) โฐ12/Jul 11-1230 nitter.cf/gerasimoss/status/1654โ€ฆ 2๏ธโƒฃ Imagination is all you need! (f/@J_st_s): โฐ10/Jul 19-21, 11/Jul 11-1230, 14/Jul 1520-17 (CODI) nitter.cf/gerasimoss/status/1654โ€ฆ
Replying to @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
1
11
820
Justus-Jonas Erker ๐Ÿ‡ช๐Ÿ‡บ @ EACL 2026 ๐Ÿ‡ฒ๐Ÿ‡ฆ retweeted
๐Ÿค— Happy summer break from the #MNLP reading group! We will reconvene in September! @ThalesBertaglia @J_st_s @Khartraxx @antoiloui @HaoyangGui60578 @CatalinaGoanta
2
7
538
Justus-Jonas Erker ๐Ÿ‡ช๐Ÿ‡บ @ EACL 2026 ๐Ÿ‡ฒ๐Ÿ‡ฆ retweeted
Another lovely meeting of the Maastricht NLP Reading Group (master students, PhDs and UDs). This time we discussed MetaFormer (from Computer Vision) and the simple but powerful pooling i/o self-attention @J_st_s @abdrahman_issam @UM_DACS
5
12
885