Andrey PRO

Bochkov's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

published an article 2 days ago

view article

Article

FEM-ASM: Modular Language Computation

• 

Bochkov

•

2 days ago

updated 2 models 2 days ago

Bochkov/modular-reasoning-0p5b-g6p5-demo

Text Generation • 0.5B • Updated 2 days ago • 694

Bochkov/fem-multi-mesh-1p7b

Text Generation • 2B • Updated 2 days ago • 738

submitted a paper to Daily Papers 2 days ago

Beyond the Parameter Monolith: Reconstructive Memories, Executable Skills, and Residual Assembly for Language Models

Paper • 2610.04012 • Published 9 days ago • 2

authored 3 papers 2 days ago

Language Models Without a Trainable Input Embedding Table: Learning from Fixed Minimal Binary Token Codes

Paper • 2605.09751 • Published May 10

Do Language Models Need a Trainable Input Embedding Table? Fixed Minimal Token Codes at 1.7B-Class Scale

Paper • 2610.04002 • Published 9 days ago • 4

Beyond the Parameter Monolith: Reconstructive Memories, Executable Skills, and Residual Assembly for Language Models

Paper • 2610.04012 • Published 9 days ago • 2

updated a Space 2 days ago

Running

README

🐢

published a dataset 2 days ago

Bochkov/bvv-edu-corpus-lite-v1.6

Viewer • Updated Jul 21 • 481k • 3

published an article 3 days ago

view article

Article

Token Identity Is Not Meaning: What Fixed-Input Language Models Can Teach Us

• 

Bochkov

•

3 days ago

published a Space 3 days ago

Running

README

🐢

updated 3 collections 3 days ago

Language Models Without a Trainable Input Embedding Table

Collection

This collection is provided for reproducibility of the paper's main claim • 4 items • Updated 3 days ago

Beyond the Parameter Monolith: Modular Language Modeling

Collection

This collection is provided for reproducibility of the paper's main claim • 3 items • Updated 3 days ago

Do Language Models Need a Trainable Input Embedding Table?

Collection

This collection is provided for reproducibility of the paper's main claim • 4 items • Updated 3 days ago

updated 3 models 3 days ago

Bochkov/ab_ext_gf2

Text Generation • 2B • Updated 3 days ago • 533

Bochkov/ab_ext_binary16

Text Generation • 2B • Updated 3 days ago • 568

Bochkov/ab_ext_learned

Text Generation • 2B • Updated 3 days ago • 599

submitted a paper to Daily Papers 3 days ago

Do Language Models Need a Trainable Input Embedding Table? Fixed Minimal Token Codes at 1.7B-Class Scale

Paper • 2610.04002 • Published 9 days ago • 4

updated a collection 9 days ago

Beyond the Parameter Monolith: Modular Language Modeling

Collection

This collection is provided for reproducibility of the paper's main claim • 3 items • Updated 3 days ago