22y

22yuu

2 1

AI & ML interests

None yet

Recent Activity

liked a Space 9 days ago

HuggingFaceTB/smol-training-playbook

upvoted a paper 12 days ago

Influence-Directed Distillation: Solving the Diversity Bottleneck in Sampled-Token On-Policy Distillation

upvoted a paper 12 days ago

It Takes Two to Match: Co-Evolving Generative Retriever with Reinforcement Learning

View all activity

Organizations

None yet

liked a Space 9 days ago

The Smol Training Playbook

The secrets to building world-class LLMs

upvoted 2 papers 12 days ago

Influence-Directed Distillation: Solving the Diversity Bottleneck in Sampled-Token On-Policy Distillation

Paper • 2608.29846 • Published 16 days ago • 16

It Takes Two to Match: Co-Evolving Generative Retriever with Reinforcement Learning

Paper • 2609.00638 • Published 14 days ago • 74