Murad Aghazada's picture

7 1

Murad Aghazada

mrdghzd

·

AI & ML interests

LLM Efficiency, Reasoning, and Alignment

Recent Activity

upvoted a paper 15 days ago

Temporal Alignment Guidance: On-Manifold Sampling in Diffusion Models

upvoted a paper 23 days ago

Hybrid Architectures for Language Models: Systematic Analysis and Design Insights

upvoted a paper about 1 month ago

No Prompt Left Behind: Exploiting Zero-Variance Prompts in LLM Reinforcement Learning via Entropy-Guided Advantage Shaping

View all activity

Organizations

None yet

mrdghzd 's datasets

None public yet