Milad Aghajohari's picture

2 3 3

Milad Aghajohari

miladink

·

AI & ML interests

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

Recent Activity

upvoted a paper about 2 months ago

Grounding Computer Use Agents on Human Demonstrations

authored a paper 3 months ago

LOQA: Learning with Opponent Q-Learning Awareness

authored a paper 3 months ago

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

View all activity

Organizations

upvoted a paper about 2 months ago

Grounding Computer Use Agents on Human Demonstrations

Paper • 2511.07332 • Published Nov 10, 2025 • 105

authored 3 papers 3 months ago

LOQA: Learning with Opponent Q-Learning Awareness

Paper • 2405.01035 • Published May 2, 2024

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

Paper • 2410.01679 • Published Oct 2, 2024 • 27

The Markovian Thinker

Paper • 2510.06557 • Published Oct 8, 2025 • 30

upvoted a paper 3 months ago

The Markovian Thinker

Paper • 2510.06557 • Published Oct 8, 2025 • 30

commented a paper 3 months ago

Inference-Time Hyper-Scaling with KV Cache Compression

Paper • 2506.05345 • Published Jun 5, 2025 • 27 •

updated 3 models 4 months ago

MathMindsAGI/DT_1.5B_3X8K_YOLO_BF_20250823Tamia_seed_2746318213

Updated Aug 30, 2025 • 13

MathMindsAGI/DT_1.5B_3X8K_YOLO_BF_20250823Tamia_seed_2746318213

Updated Aug 30, 2025 • 13

MathMindsAGI/DT_1.5B_3X8K_YOLO_BF_20250823Tamia_seed_2746318213

Updated Aug 30, 2025 • 13