Ljubomir Josifovski

ljupco

https://ljubomirj.github.io/

ljupc0
ljubomirj
ljubomirjosifovski
ljupco.bsky.social

AI & ML interests

Now - ML/AI, agents, forecasting, science & engineering. Previous - systematic trading, research & development. Prior - speech recognition in noise, speech synthesis, machine learning.

Recent Activity

upvoted a paper about 7 hours ago

EAGLE-3: Scaling up Inference Acceleration of Large Language Models via Training-Time Test

liked a model 1 day ago

miromind-ai/MiroThinker-1.7-mini

liked a model 1 day ago

miromind-ai/MiroThinker-1.7

View all activity

Organizations

None yet

Ljubomir Josifovski

AI & ML interests

Recent Activity

Organizations

ljupco 's collections 6

OptiMind: Teaching LLMs to Think Like Optimization Experts

Agentic Context Engineering: Evolving Contexts for Self-Improving Language Models

Demystifying Reinforcement Learning in Agentic Reasoning

Set Block Decoding is a Language Model Inference Accelerator

QeRL: Beyond Efficiency -- Quantization-enhanced Reinforcement Learning for LLMs

Demystifying Reinforcement Learning in Agentic Reasoning

Agentic Context Engineering: Evolving Contexts for Self-Improving Language Models

The Markovian Thinker

Test-Time Scaling with Reflective Generative Model

Reverse-Engineered Reasoning for Open-Ended Generation

OptiMind: Teaching LLMs to Think Like Optimization Experts

QeRL: Beyond Efficiency -- Quantization-enhanced Reinforcement Learning for LLMs

Demystifying Reinforcement Learning in Agentic Reasoning

Agentic Context Engineering: Evolving Contexts for Self-Improving Language Models

Demystifying Reinforcement Learning in Agentic Reasoning

Agentic Context Engineering: Evolving Contexts for Self-Improving Language Models

The Markovian Thinker

Set Block Decoding is a Language Model Inference Accelerator

Test-Time Scaling with Reflective Generative Model

Reverse-Engineered Reasoning for Open-Ended Generation