İçeriğe geç

Angelika Romanou

@agromanou.bsky.social did:plc:b6wriy4nqf3aqpromaz4o4cn

PhD candidate at EPFL doing research in #NLProc 👩🏻‍💻 https://agromanou.github.io/

Bluesky’a katılma tarihi:

Takipçi
532
Takip edilen
316
Post
19
Sıralamaya girdiği gün
0

Özet

Angelika Romanou (@agromanou.bsky.social), 17 Kasım 2024 tarihinde katılan bir Bluesky kullanıcısı. 532 takipçisi var, 316 hesabı takip ediyor ve 19 post paylaştı.

Sıralama geçmişi

Bu hesabın postlarının Debya günlük listesine girdiği en iyi günler.

Bu hesap henüz günlük sıralamaya girmedi.

Son beğendiği postlar

Bluesky ağındaki herkese açık beğeniler.

  • MELT Workshop@meltworkshop.bsky.social

    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. 🌍🤖

    Postu göster
  • Deniz Bayazit@bayazitdeniz.bsky.social

    5/ 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!

    Postu göster
  • Deniz Bayazit@bayazitdeniz.bsky.social

    4/ 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.

    Postu göster
  • Deniz Bayazit@bayazitdeniz.bsky.social

    3/ 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.

    Postu göster
  • Deniz Bayazit@bayazitdeniz.bsky.social

    2/ 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.

    Postu göster

Daha fazlası için üye girişi yap

Blokladığı hesaplar

Bluesky’da bloklar herkese açık kayıtlardır.

Bu hesap kimseyi bloklamıyor.