@camuljak.bsky.social
π€ 9
π₯ 9
π 13
reposted by
2 months ago
At EACL '26, TakeLab members are presenting two papers. Feel free to stop by if you'd like to chat about simple tricks to improve LLM token embeddings, principled evaluation of synthetic data, coffee, or life in general. Details below ππ§΅
@eaclmeeting.bsky.social
#EACL2026
#NLProc
π²π¦
1
7
3
For some reason my account got suspended after posting this. Weird moderation. Having restored my account, I'm reposting to increase visibility.
add a skeleton here at some point
4 months ago
0
1
0
We already know prompt repetition is a handy hack to improve a decoder-only LMβs performance as it allows the model to βseeβ bidirectionally, an ability otherwise suppressed by the causal mask. But what happens if we increase the number of repetitions? π€π§΅
@eaclmeeting.bsky.social
#EACL2026
4 months ago
1
5
5
reposted by
Martin Tutek
7 months ago
Very honored to be one out of seven outstanding papers at this years' EMNLP :) Huge thanks to my amazing collaborators
@fatemehc.bsky.social
@anamarasovic.bsky.social
@boknilev.bsky.social
, this would not have been possible without them!
2
23
8
reposted by
Akhil Arora
10 months ago
Back from
#ICML2025
π¬, and off π to NorrkΓΆping πΈπͺ for
#ic2s2
CLAN (
cs.au.dk/~clan/
) members are presenting 2 papers: 1 spotlight and 1 oral. See π§΅for posters and summaries π Reach out to chat about observational studies, causality, LLM agents, human-centered AI etc.
loading . . .
CLAN for AI Research on Language and Networks
CLAN for AI Research on Language and Networks, or **CLAN** for short, is a research group and a part of the larger [DIS Group](https://cs.au.dk/research/data-intensive-systems) in the [Department of C...
https://cs.au.dk/~clan/
1
4
2
reposted by
Martin Tutek
11 months ago
We did a cool group project exploring diachronic embeddings for Croatian and found that (among other things) embeddings trained on later periods are more positive when plugged into models trained on earlier time periods. Check out the thread π§΅ & come talk to us in Vienna about this & other works π»
add a skeleton here at some point
0
2
1
you reached the end!!
feeds!
log in