6 14 40

nathan lile

nlile

https://NathanThinks.com

AI & ML interests

None yet

Recent Activity

authored a paper 3 days ago

Big-Math: A Large-Scale, High-Quality Math Dataset for Reinforcement Learning in Language Models

new activity 3 days ago

SynthLabsAI/Big-Math-RL-Verified:Release of data without filtering for solve rate

updated a dataset 3 days ago

SynthLabsAI/Big-Math-RL-Verified

View all activity

Organizations

nlile's activity

upvoted a collection 3 days ago

Big-Math

Collection

This collection contains assets associated with the Big-Math dataset, a high-quality collection of over 250,000 math questions with verifiable answers • 3 items • Updated 3 days ago • 3

upvoted a paper 3 days ago

Big-Math: A Large-Scale, High-Quality Math Dataset for Reinforcement Learning in Language Models

Paper • 2502.17387 • Published 13 days ago • 5

upvoted 2 papers 6 days ago

Cognitive Behaviors that Enable Self-Improving Reasoners, or, Four Habits of Highly Effective STaRs

Paper • 2503.01307 • Published 7 days ago • 30

Chain of Draft: Thinking Faster by Writing Less

Paper • 2502.18600 • Published 12 days ago • 44

upvoted a paper 10 days ago

FSPO: Few-Shot Preference Optimization of Synthetic Preference Data in LLMs Elicits Effective Personalization to Real Users

Paper • 2502.19312 • Published 11 days ago • 5

upvoted a paper about 2 months ago

Towards System 2 Reasoning in LLMs: Learning How to Think With Meta Chain-of-Though

Paper • 2501.04682 • Published Jan 8 • 91

upvoted 2 papers 4 months ago

OpenCoder: The Open Cookbook for Top-Tier Code Large Language Models

Paper • 2411.04905 • Published Nov 7, 2024 • 115

Direct Preference Optimization Using Sparse Feature-Level Constraints

Paper • 2411.07618 • Published Nov 12, 2024 • 16

upvoted a paper 5 months ago

Generative Reward Models

Paper • 2410.12832 • Published Oct 2, 2024 • 6

upvoted a collection 5 months ago

PERSONA

Collection

Collection of various datasets related to the PERSONA paper. • 5 items • Updated Oct 28, 2024 • 2

upvoted a collection 6 months ago

NuminaMath

Collection

Datasets and models for training SOTA math LLMs. See our GitHub for training & inference code: https://github.com/project-numina/aimo-progress-prize • 7 items • Updated 27 days ago • 76

upvoted a paper 8 months ago

PERSONA: A Reproducible Testbed for Pluralistic Alignment

Paper • 2407.17387 • Published Jul 24, 2024 • 20

upvoted an article 10 months ago

Article

The N Implementation Details of RLHF with PPO

Oct 24, 2023

• 40

upvoted a paper about 1 year ago

Suppressing Pink Elephants with Direct Principle Feedback

Paper • 2402.07896 • Published Feb 12, 2024 • 11