Eric Lan's picture

Eric Lan

Eric-Lan

·

https://ericglan.github.io/

AI & ML interests

Post-Training, Reinforcement Fine-Tuning, Reinforcement Learning, LLM, Agentic AI, Reasoning, Diffusion Model

Recent Activity

authored a paper 16 days ago

Can RL Teach Long-Horizon Reasoning to LLMs? Expressiveness Is Key

upvoted a paper 18 days ago

Can RL Teach Long-Horizon Reasoning to LLMs? Expressiveness Is Key

liked a model 6 months ago

huseyinatahaninan/Qwen2.5-7B-Instruct-CI

View all activity

Organizations

upvoted a paper 18 days ago

Can RL Teach Long-Horizon Reasoning to LLMs? Expressiveness Is Key

Paper • 2605.06638 • Published 20 days ago • 15

upvoted a paper 10 months ago

MaPPO: Maximum a Posteriori Preference Optimization with Prior Knowledge

Paper • 2507.21183 • Published Jul 27, 2025 • 15

upvoted a paper 12 months ago

Contextual Integrity in LLMs via Reasoning and Reinforcement Learning

Paper • 2506.04245 • Published May 29, 2025 • 4

upvoted a paper over 1 year ago

SePPO: Semi-Policy Preference Optimization for Diffusion Alignment

Paper • 2410.05255 • Published Oct 7, 2024 • 5

upvoted a paper almost 2 years ago

Iterative Nash Policy Optimization: Aligning LLMs with General Preferences via No-Regret Learning

Paper • 2407.00617 • Published Jun 30, 2024 • 7