🔄 In a Training Loop

Daniel Gallagher

DanielGallagherIRE

·

https://danielgall500.github.io/

AI & ML interests

I like encoders because they don't talk back.

Recent Activity

liked a Space 2 days ago

infini-gram-mini/infini-gram-mini

liked a model 5 days ago

convaiinnovations/laya

upvoted a paper 5 days ago

LLM-as-Jev: LLMs Are Already Jev-Style Decision Models -- When and How to Fine-Tune Them

View all activity

Organizations

upvoted a paper 5 days ago

LLM-as-Jev: LLMs Are Already Jev-Style Decision Models -- When and How to Fine-Tune Them

Paper • 2610.02076 • Published Oct 4 • 17

upvoted an article about 1 month ago

Article

UltraBERT: One Encoder for Classification and Retrieval

dmis-lab

•

Oct 14

• 68

upvoted a paper 3 months ago

When Attention Goes Blind: Numerical Failure in ALiBi Positional Encodings

Paper • 2608.03994 • Published Aug 4 • 9

upvoted a collection 5 months ago

TiME

The TiME collection gathers monolingual BERT-style encoders for 16 languages (xs, s, m). Each model outputs embeddings distilled from XLM-R large. • 48 items • Updated Mar 2 • 2

upvoted a paper 5 months ago

Learning to Detect Language Model Training Data via Active Reconstruction

Paper • 2602.19020 • Published Feb 22 • 2