← back

Full-data accuracy with fewer labels for training and fine-tuning machine-learni

Machine-learning force fields (MLFFs) are reliable only near their training distribution, making efficient construction of diverse training sets a major bottleneck for both train-from-scratch and foundation fine-tuning workflows. Active lea

https://arxiv.org/abs/2607.14486v1 ↗
Thesis fit
Good fit

Within your typical scope; diligence still required.

Edit thesis
In your usual scope
Idea match Light

How close the company’s idea is to your thesis statement

Sector 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 → stable
Generate memo
▸ Add / edit details

Correct facts used on the next screening or memo.

People

S
Sheng Bi
1.0
low confidence
Y
Yi-Ze Wang
1.0
low confidence
J
Jun Cheng
1.0
low confidence

Activity & evidence

arXiv Full-data accuracy with fewer labels for training and fine-tuning machine-learning force fields · based on signal ▸

Similar baseline plays (YC · idea space)

Mystic · Active
Low latency API to run and deploy ML models
founders not scraped yet
Velum Labs · Active
The OS for data quality across any stack
founders not scraped yet
Feyn · Active
Custom models trained on your data
founders not scraped yet
Replicate · Acquired
Run machine learning models in the cloud
Ben Firshman Andreas Jansson
Marft · Inactive
Marft creates embeddable machine learning models for application…
founders not scraped yet