D-cut: Adaptive Verification Depth Pruning for Batched Speculative Decoding
Speculative decoding accelerates large language model (LLM) inference without compromising output quality. Recent parallel drafting methods further improve single-request performance by decoupling draft length from drafting latency, enablin
https://arxiv.org/abs/2607.14647v1 ↗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
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
▸ Add / edit details
Correct facts used on the next screening or memo.
People
T
Tianyu Liu
1.0
low confidence
R
Rui Cen
1.0
low confidence
J
Junhan Shi
1.0
low confidence
J
Jiebin Zhang
1.0
low confidence
G
Guangshuo Qin
1.0
low confidence
H
Hong Liu
1.0
low confidence
S
Song Liu
1.0
low confidence
G
Guanghua Yu
1.0
low confidence
J
Jianchen Zhu
1.0
low confidence
Activity & evidence
Similar baseline plays (YC · idea space)
Pipeshift
· Active
Ultra-low latency inference cloud for real-time workloads
founders not scraped yet
Automorphic
· Active
Infuse knowledge into language models with just 10 samples
founders not scraped yet