Kawin Ethayarajh

kawine's activity

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

upvoted a paper 11 days ago

Mecha-nudges for Machines

Paper • 2603.23433 • Published Mar 24 • 1

upvoted a paper 9 months ago

Humanline: Online Alignment as Perceptual Loss

Paper • 2509.24207 • Published Sep 29, 2025 • 12

published a model 9 months ago

kawine/Qwen2.5-1.5B-Instruct_128

Updated Sep 13, 2025

New activity in stanfordnlp/SHP about 1 year ago

Any Discussion in the original paper

4

#3 opened about 2 years ago by

jAEhEEkIM

Notifications from parquet-converter

1

#2 opened over 2 years ago by

parquet-converter

New activity in stanfordnlp/SHP-2 about 1 year ago

[bot] Conversion to Parquet

#2 opened over 2 years ago by

parquet-converter

upvoted an article almost 2 years ago

view article

Article

How NuminaMath Won the 1st AIMO Progress Prize

• 
• 
• +6

yfleureau, liyongsea, edbeeching, lewtun, benlipkin, romansoletskyi, vwxyzjn, kashif

•

Jul 11, 2024

• 128

upvoted a paper about 2 years ago

Insights into Alignment: Evaluating DPO and its Variants Across Multiple Tasks

Paper • 2404.14723 • Published Apr 23, 2024 • 10

updated a collection over 2 years ago

Archangel

Collection

Archangel is a suite of human feedback-aligned LLMs, released as part of the Human-Aware Loss Functions (HALOs) project by Ethayarajh et al. (2024). • 77 items • Updated Feb 2, 2024 • 2