Demystifying On-Policy Distillation: Roles, Pathologies, and Regulations
On-policy distillation (OPD) has become a key paradigm in LLM post-training, yet its training dynamics remain poorly understood. We present a systematic study examining the role, pathologies, and regulations of OPD. We first clarify the rol
https://arxiv.org/abs/2607.13399v1 ↗Thesis fit
Good fit
Within your typical scope; diligence still required.
In your usual scope
Idea match
Light
How close the company’s idea is to your thesis statement
Sector
llm, ai
Overlap with sectors you care about
Geography
Unknown
Location unknown — scores 0
Your thesis: “We back exceptional technical founders building AI-first products and infrastructure, deploying $100K checks within 24 hours.”
Founder → stable
Traction → stable
Idea vs market ↑ improving
▸ Add / edit details
Correct facts used on the next screening or memo.
People
R
Rui Wang
1.0
low confidence
H
Hongru Wang
1.0
low confidence
Y
Yi Chen
1.0
low confidence
B
Boyang Xue
1.0
low confidence
T
Tianqing Fang
1.0
low confidence
W
Wenhao Yu
1.0
low confidence
K
Kam-Fai Wong
1.0
low confidence
Activity & evidence
Similar baseline plays (YC · idea space)
Unsloth AI
· Active
Open-Source Reinforcement Learning (RL) & Fine-tuning for LLMs.
founders not scraped yet
Affinity
· Active
A compliance training platform built for regulated industries.
founders not scraped yet
Forage
· Acquired
Online job simulations for companies to train, and then hire, students
Pasha Rayan
Thomas Brunskill
FunctionUp (FanPlay)
· Acquired
A skill-tech platform that runs placement bootcamps
Bharat Gupta
Pritesh Kumar