Milad Aghajohari's picture

Milad Aghajohari

miladink

·

AI & ML interests

NLP, ML, Multi-Agent RL, SSL, AI

Recent Activity

upvoted a paper 20 days ago

InftyThink+: Effective and Efficient Infinite-Horizon Reasoning via Reinforcement Learning

upvoted a paper 4 months ago

Grounding Computer Use Agents on Human Demonstrations

authored a paper 5 months ago

LOQA: Learning with Opponent Q-Learning Awareness

View all activity

Organizations

upvoted a paper 20 days ago

InftyThink+: Effective and Efficient Infinite-Horizon Reasoning via Reinforcement Learning

Paper • 2602.06960 • Published 24 days ago • 13

upvoted a paper 4 months ago

Grounding Computer Use Agents on Human Demonstrations

Paper • 2511.07332 • Published Nov 10, 2025 • 106

upvoted a paper 5 months ago

The Markovian Thinker

Paper • 2510.06557 • Published Oct 8, 2025 • 31

upvoted a paper over 1 year ago

VinePPO: Unlocking RL Potential For LLM Reasoning Through Refined Credit Assignment

Paper • 2410.01679 • Published Oct 2, 2024 • 27