12 7 5

Tom Schelsen

TomSchelsen

AI & ML interests

None yet

Recent Activity

new activity 11 days ago

Hcompany/Holo3-35B-A3B:Quickstart guide link on model card leads to 404

commentedon an article 20 days ago

Build a Domain-Specific Embedding Model in Under a Day

commentedon an article about 1 month ago

Qwen3.5 Full Multimodal SFT Example (Arm64 GH200)

View all activity

Organizations

None yet

upvoted an article 4 months ago

Article

Tokenization in Transformers v5: Simpler, Clearer, and More Modular

Dec 18, 2025

•

124

upvoted a collection 6 months ago

ARC-Encoders

Collection

Pretrained ARC-Encoders and a fine-tuning dataset: context compression for unmodified LLMs. • 6 items • Updated 17 days ago • 4

upvoted an article 8 months ago

Article

Luth: Efficient French Specialization for Small Language Models

Aug 11, 2025

•

upvoted an article 9 months ago

Article

Should We Still Pretrain Encoders with Masked Language Modeling?

Jul 2, 2025

•

upvoted an article 10 months ago

Article

Mastering Tensor Dimensions in Transformers

Jan 12, 2025

•

159

upvoted an article about 1 year ago

Article

🇪🇺 EU AI Act: Comments on the Third Code of Practice Draft 🇪🇺

Mar 13, 2025

•

upvoted a paper over 1 year ago

Reducing the Footprint of Multi-Vector Retrieval with Minimal Performance Impact via Token Pooling

Paper • 2409.14683 • Published Sep 23, 2024 • 11

Tom Schelsen

AI & ML interests

Recent Activity

Organizations

TomSchelsen's activity

Tokenization in Transformers v5: Simpler, Clearer, and More Modular

Luth: Efficient French Specialization for Small Language Models

Should We Still Pretrain Encoders with Masked Language Modeling?

Mastering Tensor Dimensions in Transformers

🇪🇺 EU AI Act: Comments on the Third Code of Practice Draft 🇪🇺