🔄 In a Training Loop

Milton Montiel

miltmont

·

https://discretized.dev

MiltMont

AI & ML interests

Reinforcement learning

Recent Activity

upvoted a paper 1 day ago

Advances in Agentic Computer Graphics

upvoted a paper 1 day ago

SpecOPD: Branch-Parallel On-Policy Distillation for Speculative Decoding

upvoted a paper 1 day ago

MUON-RT Reusing the Teacher's Trajectory for Momentum-Free Muon for LLM Self-Distillation

View all activity

Organizations

buckets 1

miltmont/traces

models 0

None public yet

datasets 0

None public yet