Pre-training

community

AI & ML interests

None defined yet.

JW17

authored 2 papers 8 months ago

AlphaPO -- Reward shape matters for LLM alignment

Paper • 2501.03884 • Published Jan 7, 2025 • 2

Online Difficulty Filtering for Reasoning Oriented Reinforcement Learning

Paper • 2504.03380 • Published Apr 4, 2025

JW17

authored a paper 10 months ago

When AI Co-Scientists Fail: SPOT-a Benchmark for Automated Verification of Scientific Research

Paper • 2505.11855 • Published May 17, 2025 • 10

JW17

authored 3 papers over 1 year ago

Stable Language Model Pre-training by Reducing Embedding Variability

Paper • 2409.07787 • Published Sep 12, 2024

Cross-lingual Transfer of Reward Models in Multilingual Alignment

Paper • 2410.18027 • Published Oct 23, 2024

Margin-aware Preference Optimization for Aligning Diffusion Models without Reference

Paper • 2406.06424 • Published Jun 10, 2024 • 15

JW17

authored a paper almost 2 years ago

ORPO: Monolithic Preference Optimization without Reference Model

Paper • 2403.07691 • Published Mar 12, 2024 • 72