12 8 1

Bruno Hays

BrunoHays

AI & ML interests

None yet

Recent Activity

updated a dataset 10 days ago

BrunoHays/english-en-x-code-switching-main-lang-samples-merged

published a dataset 10 days ago

BrunoHays/english-en-x-code-switching-main-lang-samples-merged

updated a dataset 10 days ago

BrunoHays/english-en-x-code-switching-main-lang-samples

View all activity

Organizations

upvoted 2 articles 10 months ago

Article

Introducing ColQwen-Omni: Retrieve in every modality

manu

•

Jul 17, 2025

• 76

Article

SmolLM3: smol, multilingual, long-context reasoner

eliebak, cmpatino, anton-l, edbeeching, m-ric, nouamanetazi, akseljoonas, guipenedo, hynky, clefourrier, SaylorTwift, kashif, qgallouedec, hlarcher, glutamatt, Xenova, reach-vb, ngxson, craffel, lewtun, loubnabnl, lvwerra, thomwolf

•

Jul 8, 2025

• 773

upvoted a paper 10 months ago

Should We Still Pretrain Encoders with Masked Language Modeling?

Paper • 2507.00994 • Published Jul 1, 2025 • 81

upvoted a paper about 1 year ago

Qwen2.5-Omni Technical Report

Paper • 2503.20215 • Published Mar 26, 2025 • 172

upvoted 2 articles over 1 year ago

Article

Open-R1: a fully open reproduction of DeepSeek-R1

eliebak, lvwerra, lewtun

•

Jan 28, 2025

• 889

Article

You could have designed state of the art positional encoding

FL33TW00D-HF

•

Nov 25, 2024

• 478

upvoted 2 papers over 1 year ago

Enhancing Training Efficiency Using Packing with Flash Attention

Paper • 2407.09105 • Published Jul 12, 2024 • 17

GroUSE: A Benchmark to Evaluate Evaluators in Grounded Question Answering

Paper • 2409.06595 • Published Sep 10, 2024 • 38

Bruno Hays

AI & ML interests

Recent Activity

Organizations

BrunoHays's activity

Introducing ColQwen-Omni: Retrieve in every modality

SmolLM3: smol, multilingual, long-context reasoner

Open-R1: a fully open reproduction of DeepSeek-R1

You could have designed state of the art positional encoding