Zhengxu Yu

fredreick's activity

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

upvoted a paper 1 day ago

Memento 3: Model-Based Recursive Self-Improvement through Reflective Rulebooks

Paper • 2610.11794 • Published 3 days ago • 28

New activity in multimodalart/jev-decision-index 22 days ago

Add LitJev (Jev-schema decision layer for the Qwen family)

3

#2 opened 22 days ago by

fredreick

upvoted a paper about 2 months ago

Large Discovery Models: Empirically-grounded Model-Based Open-Ended Search

Paper • 2608.15669 • Published Aug 16 • 63

commented 2 papers 6 months ago

From Skills to Talent: Organising Heterogeneous Agents as a Real-World Company

Paper • 2604.22446 • Published Apr 24 • 127 •

5

From Skills to Talent: Organising Heterogeneous Agents as a Real-World Company

Paper • 2604.22446 • Published Apr 24 • 127 •

5

submitted a paper to Daily Papers 6 months ago

From Skills to Talent: Organising Heterogeneous Agents as a Real-World Company

Paper • 2604.22446 • Published Apr 24 • 127

authored a paper 6 months ago

From Skills to Talent: Organising Heterogeneous Agents as a Real-World Company

Paper • 2604.22446 • Published Apr 24 • 127

upvoted 2 papers 6 months ago

From Skills to Talent: Organising Heterogeneous Agents as a Real-World Company

Paper • 2604.22446 • Published Apr 24 • 127

InfoSeeker: A Scalable Hierarchical Parallel Agent Framework for Web Information Seeking

Paper • 2604.02971 • Published Apr 3 • 8

upvoted a paper 7 months ago

Memento-Skills: Let Agents Design Agents

Paper • 2603.18743 • Published Mar 19 • 59

updated a dataset over 1 year ago

fredreick/STM

Viewer • Updated May 1, 2025 • 111k • 2

published a dataset over 1 year ago

fredreick/STM

Viewer • Updated May 1, 2025 • 111k • 2

New activity in bjdwh/ST_data_urbangpt over 1 year ago

Error

1

#2 opened over 2 years ago by

zbximoy

liked a dataset about 2 years ago

openai/gsm8k

Benchmark • Updated Mar 23 • 17.6k • 1.03M • 1.96k

updated 4 models about 2 years ago

fredreick/zephyr-7b-dpo-qlora

Updated Sep 15, 2024

fredreick/zephyr-7b-sft-qlora

Updated Sep 15, 2024

fredreick/zephyr-7b-sft-full

Updated Sep 14, 2024

fredreick/zephyr-7b-dpo-full

Updated Aug 30, 2024

liked a model over 2 years ago

meta-llama/Llama-2-7b

Text Generation • Updated Apr 17, 2024 • 126 • 4.57k