Evangeline Shen's picture

5 2

Evangeline Shen

Evangelinejy

·

AI & ML interests

None yet

Recent Activity

updated a model 2 days ago

chess-pre-to-post/sft_trajectory_no_labels

updated a model 3 days ago

chess-pre-to-post/rl_trajectory_sep_no_labels

updated a model 14 days ago

chess-pre-to-post/rl_C6p5e18_20m_alpha0.030_beta0.008

View all activity

Organizations

upvoted a paper 26 days ago

When Can LLMs Learn to Reason with Weak Supervision?

Paper • 2604.18574 • Published about 1 month ago • 25

upvoted a paper 30 days ago

Improving Data Efficiency for LLM Reinforcement Fine-tuning Through Difficulty-targeted Online Data Selection and Rollout Replay

Paper • 2506.05316 • Published Jun 5, 2025 • 1

upvoted a collection 30 days ago

rlvr-weak-supervision

Models from "When Can LLMs Learn to Reason with Weak Supervision?" — Llama-3.2-3B with continual pre-training and Thinking SFT. • 3 items • Updated 30 days ago • 2

upvoted a paper 5 months ago

When Reasoning Meets Its Laws

Paper • 2512.17901 • Published Dec 19, 2025 • 62

upvoted a paper 12 months ago

MiCRo: Mixture Modeling and Context-aware Routing for Personalized Preference Learning

Paper • 2505.24846 • Published May 30, 2025 • 15