Miaow Lab @ CityUHK

Miaow-Lab's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Articles

louiswng 

updated a dataset 23 days ago

Miaow-Lab/RLVR-Linearity-Dataset

Viewer • Updated 23 days ago • 40.3k • 44

louiswng 

updated a model 26 days ago

Miaow-Lab/RLVR-Linearity-Checkpoints

Text Generation • Updated 26 days ago

louiswng 

updated a collection 29 days ago

RLVR Linearity

Collection

RL training and evaluation datasets, and checkpoints in 'Not All Steps are Informative: On the Linearity of LLMs’ RLVR Training' • 3 items • Updated 29 days ago

louiswng 

published a model 29 days ago

Miaow-Lab/RLVR-Linearity-Checkpoints

Text Generation • Updated 26 days ago

louiswng 

updated a collection 29 days ago

RLVR Linearity

Collection

RL training and evaluation datasets, and checkpoints in 'Not All Steps are Informative: On the Linearity of LLMs’ RLVR Training' • 3 items • Updated 29 days ago

louiswng 

published a dataset about 1 month ago

Miaow-Lab/RLVR-Linearity-Dataset

Viewer • Updated 23 days ago • 40.3k • 44

halfrot 

authored a paper over 1 year ago

HAF-RM: A Hybrid Alignment Framework for Reward Model Training

Paper • 2407.04185 • Published Jul 4, 2024

halfrot 

authored 2 papers almost 2 years ago

ARKS: Active Retrieval in Knowledge Soup for Code Generation

Paper • 2402.12317 • Published Feb 19, 2024

ALaRM: Align Language Models via Hierarchical Rewards Modeling

Paper • 2403.06754 • Published Mar 11, 2024

halfrot 

authored a paper over 2 years ago

DS-1000: A Natural and Reliable Benchmark for Data Science Code Generation

Paper • 2211.11501 • Published Nov 18, 2022