Nguyễn Minh Phúc

DatPySci's activity

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

authored 2 papers about 3 hours ago

Why Do Reasoning Models Lose Coverage? The Role of Data and Forks in the Road

Paper • 2605.17026 • Published May 16 • 6

The Reasoning Boundary Paradox: How Reinforcement Learning Constrains Language Models

Paper • 2510.02230 • Published Oct 2, 2025

upvoted an article 21 days ago

view article

Article

Navigating the RLHF Landscape: From Policy Gradients to PPO, GAE, and DPO for LLM Alignment

• 

NormalUhr

•

Feb 11, 2025

• 135

updated a model 23 days ago

DatPySci/Checkpoints

Updated 23 days ago

published a model 27 days ago

DatPySci/Checkpoints

Updated 23 days ago

updated 2 models about 1 month ago

DatPySci/check

Updated Sep 14 • 1

DatPySci/AR-Diff

Updated Sep 11

liked a model about 2 months ago

zai-org/GLM-5.3

Text Generation • 753B • Updated 5 days ago • 1.83M • • 2.26k

published 2 models 2 months ago

DatPySci/check

Updated Sep 14 • 1

DatPySci/AR-Diff

Updated Sep 11

updated a dataset 3 months ago

DatPySci/OpenThoughts-mixture-preprocessed

Viewer • Updated Aug 4 • 114k • 56

published a dataset 3 months ago

DatPySci/OpenThoughts-mixture-preprocessed

Viewer • Updated Aug 4 • 114k • 56

updated a dataset 3 months ago

DatPySci/OpenThoughts-114k-preprocessed

Viewer • Updated Aug 4 • 114k • 46

published a dataset 3 months ago

DatPySci/OpenThoughts-114k-preprocessed

Viewer • Updated Aug 4 • 114k • 46

updated a dataset 3 months ago

DatPySci/Self-Distillation-Qwen2.5-7B-Instruct-medreason-prefix-instruct-tokenized

Viewer • Updated Jul 31 • 32.7k • 18

published a dataset 3 months ago

DatPySci/Self-Distillation-Qwen2.5-7B-Instruct-medreason-prefix-instruct-tokenized

Viewer • Updated Jul 31 • 32.7k • 18

updated a dataset 3 months ago

DatPySci/Self-Distillation-Qwen3-4B-Thinking-2507-medreason-prefix-instruct-tokenized

Viewer • Updated Jul 31 • 32.7k • 20

published a dataset 3 months ago

DatPySci/Self-Distillation-Qwen3-4B-Thinking-2507-medreason-prefix-instruct-tokenized

Viewer • Updated Jul 31 • 32.7k • 20

updated a dataset 3 months ago

DatPySci/Self-Distillation-Qwen3-8B-medreason-prefix-instruct-tokenized

Viewer • Updated Jul 31 • 32.7k • 19

published a dataset 3 months ago

DatPySci/Self-Distillation-Qwen3-8B-medreason-prefix-instruct-tokenized

Viewer • Updated Jul 31 • 32.7k • 19