← back

Data-Efficient Adaptation of LLMs via Attention Head Reweighting

Learning effectively from limited data is critical in domains like security where labeled examples are scarce. Large language models (LLMs) have demonstrated some capabilities for data-efficient learning, especially through parameter-effici

https://arxiv.org/abs/2607.13425v1 ↗
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 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 ↓ declining
Generate memo
▸ Add / edit details

Correct facts used on the next screening or memo.

People

T
Tuomas Oikarinen
1.0
low confidence
Z
Zixiao Chen
1.0
low confidence
C
Charlotte Siska
1.0
low confidence
T
Tsui-Wei Weng
1.0
low confidence
C
Chandan Singh
1.0
low confidence
J
Jianfeng Gao
2.0
low confidence

Activity & evidence

arXiv Data-Efficient Adaptation of LLMs via Attention Head Reweighting · based on signal ▸
arXiv GFlowRL: Scaling Distribution-Matching RL to Large Language Models · authored signal ▸

Similar baseline plays (YC · idea space)

Mundo AI · Active
High Quality Multilingual Training Data for AI Models
founders not scraped yet
Automorphic · Active
Infuse knowledge into language models with just 10 samples
founders not scraped yet
Compresr · Active
LLM context compression for better accuracy
founders not scraped yet
Kalpa Labs · Active
Scaling Generalist Speech models
founders not scraped yet
Luel · Active
Turning everyday words and actions into usable training data.
founders not scraped yet