Angelika Romanou
@agromanou.bsky.social did:plc:b6wriy4nqf3aqpromaz4o4cn
PhD candidate at EPFL doing research in #NLProc 👩🏻💻 https://agromanou.github.io/
No Bluesky desde
- Seguidores
- 532
- Seguindo
- 316
- Posts
- 19
- Dias nos rankings
- 0
Resumo
Angelika Romanou (@agromanou.bsky.social) é um usuário do Bluesky desde 17 novembro 2024. Tem 532 seguidores, segue 316 contas e publicou 19 posts.
Aparições nos rankings
Os melhores dias em que posts desta conta entraram na lista diária do Debya.
Esta conta ainda não apareceu em um ranking diário.
Posts curtidos recentemente
Curtidas públicas da rede Bluesky.
Keynote talk: Apertus: Democratizing Open and Compliant LLMs for Global Language Environments. Imanol Schlag introduces Apertus, a fully open suite of LLMs with a focus on compliance, transparency, and multilingual representation training across 1000+ languages. 🌍🤖
Ver post5/ Looking closer, feature sharing has limits: in Hindi & Arabic, overlap stays low even at 341B tokens. This may be due to richer agreement systems (e.g., verbs agreeing w/ subjects & objects) forcing BLOOM to keep language-specific features—or simply data scarcity!
Ver post4/ In #multilingual models, cross-language feature overlap starts low and rises with training. At 6B tokens in BLOOM, most detectors are language-specific or for punctuation; by 341B tokens shared crosslingual features emerge, capturing syntactic abstractions over token patterns.
Ver post3/ Which features matter early but fade, and which gain importance later? In Pythia, token-level detectors drop out, while higher-level grammatical features—like plural-noun detectors and nouns formed from verbs (e.g., runner from run)—strengthen by 286B tokens.
Ver post2/ We align critical checkpoints for a task with sparse crosscoders, measure each feature’s causal role, and introduce RelIE to compare their influence across checkpoints. This lets us trace how internal features shift—and when they matter—in models like Pythia, OLMo, and BLOOM.
Ver post
Contas que bloqueia
No Bluesky, bloqueios são registros públicos.
Esta conta não bloqueia ninguém.